DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
Claims 1-20 were previously pending in this application. The amendment filed 01 April 2026 has been entered and the following has occurred: Claims 1, 13, & 19 have been amended. Claims 2-3, 11, 14-15, & 17 have been cancelled. Claims 21-26 have been added.
Claims 1, 4-10, 12-13, 16, & 18-26 remain pending in the application.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1, 4-10, 12-13, 16, & 18-26 are rejected under 35 U.S.C. 101 because the claimed invention is directed to a judicial exception (i.e., a law of nature, a natural phenomenon, or an abstract idea) without significantly more.
The claims recite subject matter within a statutory category as a process (claims 13, 16, 18 & 23-26), machine (claims 19-22), and manufacture (claims 1, 4-10, & 12) (Subject Matter Eligibility (SME) Test Step 1: Yes) which recite steps of:
receive a medical history for a patient;
conduct, using a large language model (LLM), a text conversation with the patient using a user interface (UI) to obtain a plurality of responses;
determine, using a first artificial intelligence (AI) module, one or more social determinants of health (SDOHs) for the patient based on the plurality of responses;
determine, using a second AI module, a personality profile of the patient based on the plurality of responses;
receive biometric information for the patient from at least one biometric device;
store the medical history, the plurality of responses, and the biometric information in the non-transitory computer-readable memory medium;
determine a potential atrial fibrillation (AF) diagnosis based at least in part on the medical history and the biometric information;
based on determining the potential AF diagnosis:
automatically provide the potential AF diagnosis to a medical call center; and
receive, from the medical call center, a care schedule for the patient that is based at least in part on the potential AF diagnosis;
determine, using a machine learning software, an intervention proposal for the patient based at least in part on care schedule, the one or more SDOHs, and the personality profile, wherein behavioral change significance of the intervention proposal is determined based at least in part on a willingness to intervene indicated by the personality profile; and
display the intervention proposal on a display.
These steps of receiving a medical history for a patient, conducting a text conversation with the patient using a user interface to obtain patient responses, receive biometric information for the patient from at least one biometric device, storing the medical history and the biometric information, determining an intervention proposal based at least in part on the medical history, the plurality of responses, and the biometric information, and displaying the intervention proposal, as drafted, under the broadest reasonable interpretation, includes performance of the limitation in the mind but for recitation of generic computer components. That is, other than reciting steps as performed by the generic computer components, nothing in the claim element precludes the step from practically being performed in the mind. For example, but for the receiving medical history of a patient and biometric information of the patient from a biometric device language, conducting a conversation with the patient, receiving medical history and biometric information of the patient in the context of this claim encompasses a mental process of a user or doctor querying a patient about their health conditions and/or medical history through conversation, and measuring various vitals or other data on the patient using medical devices. Similarly, the limitation of storing the medical history and the biometric information, as drafted, is a process that, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, such as the doctor storing the various information in a hand-written or electronic record following receiving said information. For example, but for the determining an intervention proposal based on the medical history, responses, SDOHs personality profile, and/or biometric information language, determining an intervention in the context of this claim encompasses a mental process of a doctor performing diagnosis on the patient based on the queried medical history, conversation, and/or biometric information recorded by the medical device, and developing a treatment plan for atrial fibrillation based on said atrial fibrillation diagnosis. Furthermore, contacting a call center to inform them of a diagnosis and receiving a care schedule for the patient amounts to a provider contacting a call center and receive a potential care schedule for the patient based upon the provider’s diagnosis. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea.
These steps of receiving a medical history for a patient, conducting a text conversation with the patient using a user interface to obtain patient responses, receive biometric information for the patient from at least one biometric device, storing the medical history and the biometric information, determining an intervention proposal based at least in part on the care schedule, SDOHs, personality profile, etc., contacting and displaying the intervention proposal, as drafted, under the broadest reasonable interpretation, include certain methods of organizing human activity. For instance, MPEP 2106.04(a)(2)(II)(C), gives an example of managing personal behavior or relationships or interactions between people, such as a mental process that a neurologist should follow when testing a patient for nervous system malfunctions. The steps recited heavily relate to said example of a mental process that a neurologist should follow at least by reciting various aspects of diagnosing a patient with atrial fibrillation and developing an intervention proposal based on various aspects of the patient and the diagnosis. Furthermore, at the very least, the newly amended steps of determining and utilizing aspects of collecting human activity regarding SDOHs, a personality profile, etc. for diagnosis and treatment purposes, and managing a behavior of the patient regarding their typical treatment process or the interaction between a provider and said patient regarding developing a treatment and/or treatment plan for the patient. Accordingly, the claim recites an abstract idea, i.e. methods of organizing human activity.
Dependent claims recite additional subject matter which further narrows or defines the abstract idea embodied in the claims (such as claims 4-10, 12, 16, 18, 20, & 21-26, reciting particular aspects of how determining intervention proposals, determining one or more medical diagnoses, identifying care gaps, conducting text conversations, determining various information related to a patient, may be performed in the mind but for recitation of generic computer components) (SME Test Step 2A, Prong 1: Yes).
This judicial exception is not integrated into a practical application. In particular, the additional elements do not integrate the abstract idea into a practical application, other than the abstract idea per se, because the additional elements amount to no more than limitations which:
amount to mere instructions to apply an exception (such as recitation of a non-transitory computer-readable memory medium, a processor, a computing device, a large language model (LLM), a user interface (UI), a biometric device, machine learning software, amounts to invoking computers as a tool to perform the abstract idea, see Applicant’s Spec [0029] for non-transitory computer-readable memory medium, Spec [0032] for a processor; Spec [0010] for a computing device; Spec [0078]-[0079] for a large language model; Spec [0073] & Fig. 7 for a user interface; Spec [0062] for a biometric device; Spec [0053]-[0054] for machine learning software, see MPEP 2106.05(f));
add insignificant extra-solution activity to the abstract idea (such as recitation of receiving a medical history for a patient, receiving biometric information for at least one biometric device, conducting a text conversation with a patient to obtain a plurality of responses, contacting a call center and receiving a care schedule for the patient amounts to mere data gathering; recitation of storing the medical history, the plurality of responses, and the biometric information amounts to selecting a particular data source or type of data to be manipulated; recitation of storing the medical history, the plurality of responses, and the biometric information in the non-transitory computer-readable memory medium, determining social determinants of health, a personality profile, a potential atrial fibrillation diagnosis, and an intervention proposal based on the medical history, the plurality of responses, SDOHs, care schedule, personality, and the biometric information, displaying the intervention proposal on a display amounts to insignificant application, see MPEP 2106.05(g));
generally link the abstract idea to a particular technological environment or field of use (such as recitation of a large language model, machine learning, or other generic computing software performing the abstract idea recited, see MPEP 2106.05(h)).
Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims (such as claims 4-10, 12, 16, 18, 20, & 21-26, which recite a non-transitory computer-readable memory medium, a computing device, a display, one or more health software applications, one or more AI modules, a user interface (UI), see Applicant’s Specification [0029] for a recite a non-transitory computer-readable memory medium; Spec [0010] for a computing device, Spec [0044] for a display, Spec [0065] for one or more health software applications, Spec [0061] for one or more AI modules, Spec [0073] & Fig. 7 for a user interface (UI), additional limitations which amount to invoking computers as a tool to perform the abstract idea; claims 6-10, 14, 22, & 24-26, which recite limitations relating to providing one or more potential medical diagnoses, receiving a care schedule, , receiving health information from one or more health software applications, conducting one or more text conversations to receive patient information, receiving a plurality of risk conditions, additional limitations which add insignificant extra-solution activity to the abstract idea which amounts to mere data gathering; claims 4, 6, 12, 16, 18, 20, 22, & 24, which recite limitations relating to making one or more determinations based on manipulation of one or more received data, identifying a care gap from the medical information received, outputting and/or displaying various received/determined information, modifying a behavior profile of the patient based on varying information, additional limitations which add insignificant extra-solution activity to the abstract idea by selecting a particular data source or type of data to be manipulated; claims 4-5, 7-8, 12, 16, & 18, which recite limitations relating to one or more user interface implementations, such as displaying information in a UI for interaction by a user, additional limitations which amount to insignificant application; claims 4-10, 12, 16, 18, 20, & 21-26 which generally recite the limitations and steps recited for use in medical diagnosis and/or medical intervention planning, additional limitations which generally link the abstract idea to a particular technological environment or field of use). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation and do not impose a meaningful limit to integrate the abstract idea into a practical application (SME Test Step 2A, Prong 2: No).
The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to discussion of integration of the abstract idea into a practical application, the additional elements amount to no more than mere instructions to apply an exception, add insignificant extra-solution activity to the abstract idea, and generally link the abstract idea to a particular technological environment or field of use. Additionally, the additional limitations, other than the abstract idea per se, amount to no more than limitations which:
amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields (such as receiving a medical history for a patient, receiving biometric information for at least one biometric device, conducting a text conversation with a patient to obtain a plurality of responses, contacting a call center and receiving a care schedule for the patient, e.g., receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i); social determinants of health, a personality profile, a potential atrial fibrillation diagnosis, and an intervention proposal based on the medical history, the plurality of responses, SDOHs, care schedule, personality, and the biometric information, utilizing machine learning to perform said determinations, e.g., performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii); maintaining one or more intervention proposals over time, e.g., electronic recordkeeping, Alice Corp., MPEP 2106.05(d)(II)(iii); of storing the medical history, the plurality of responses, and the biometric information in the non-transitory computer-readable memory medium, e.g., storing and retrieving information in memory, Versata Dev. Group, MPEP 2106.05(d)(II)(iv); receiving a medical history for a patient, which under BRI, includes extraction of said data from an electronic or physical record, e.g., electronic scanning or extracting data from a physical document, Content Extraction, MPEP 2106.05(d)(II)(v); conducting a text conversation with a patient using a user interface and/or displaying the intervention proposal on a display, e.g., a web browser’s back and forward button functionality, i.e. UI functionality, Internet Patent Corp., MPEP 2106.05(d)(II)(ii)).
Dependent claims recite additional subject matter which, as discussed above with respect to integration of the abstract idea into a practical application, amount to invoking computers as a tool to perform the abstract idea. Dependent claims recite additional subject matter which amount to limitations consistent with the additional elements in the independent claims (such as claims 4-10, 12, 16, 18, 20, & 21-26, additional limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields, claims 6-10, 22, & 24-26, which recite limitations relating to providing one or more potential medical diagnoses, receiving a care schedule, receiving health information from one or more health software applications, conducting one or more text conversations to receive patient information, receiving a plurality of risk conditions, e.g., receiving or transmitting data over a network, Symantec, MPEP 2106.05(d)(II)(i); claims 4, 6-10, 12, 16, 18, 20, 22, & 24-26, which recite limitations relating to making one or more determinations based on manipulation of one or more received data, identifying a care gap from the medical information received, modifying a behavior profile of the patient based on varying information, e.g., performing repetitive calculations, Flook, MPEP 2106.05(d)(II)(ii); claims 12 & 18, which recite modifying, i.e. maintaining, one or more degrees of compliance and/or a behavior profile for a user, e.g., electronic recordkeeping, Alice Corp., MPEP 2106.05(d)(II)(iii); claims 4-10, 12, 16, 18, & 20-26, which recite limitations relating to storage of computerized instructions for performance of the steps recited, storing various received medical history, data, etc., of a user, e.g., storing and retrieving information in memory, Versata Dev. Group, MPEP 2106.05(d)(II)(iv); claims 2, 6-10, & 20-26, which recite limitations relating to providing one or more potential medical diagnoses, receiving a care schedule, receiving health information from one or more health software applications, conducting one or more text conversations to receive patient information, receiving a plurality of risk conditions, which under BRI, include extraction from a physical and/or electronic document, e.g., electronic scanning or extracting data from a physical document, Content Extraction, MPEP 2106.05(d)(II)(v); claims 4-5, 7-8, 12, 16, & 18, which recite limitations relating to one or more user interface implementations, such as displaying information in a UI for interaction by a user, e.g., a web browser’s back and forward button functionality, Internet Patent Corp., MPEP 2106.05(d)(II)(ii)). Looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually. There is no indication that the combination of elements improves the functioning of a computer or improves any other technology. Their collective functions merely provide conventional computer implementation (SME Test Step 2B: No).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1, 4-10, 12-13, 16, & 18-26 are rejected under 35 U.S.C. 103 as being unpatentable over Khan et al. (U.S. Patent Publication No. 2024/0013928), hereinafter “Khan”, in view of Rosenberg et al. (U.S. Patent Publication No. 2023/0307112), hereinafter “Rosenberg”, further in view of Lima et al. (U.S. Patent Publication No. 2024/0395392), hereinafter “Lima”, further in view of White et al. (U.S. Patent Publication No. 2023/0187031), hereinafter “White”.
Note: While the filing date of Khan (07/10/2023) is not earlier than the priority date of the instant application (06/20/2023), an associated provisional application was filed for Khan and filed on 07/21/2022, and therefore constitutes prior art under 35 U.S.C. 102(d)(2) as long as the associated subject matter is described in the provisional application.
Claim 1 –
Regarding Claim 1, Khan discloses a non-transitory computer-readable memory medium comprising program instructions which, when executed by a processor, cause a computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
receive a medical history for a patient (See Khan Par [0090] which discloses a risk score determination module being configured to process data including medical visit data, medical history, mental health conditions, medical device use, treatments, etc., all constituting a medical history for a patient);
conduct, using a large language model (LLM), a text conversation with the patient using a user interface (UI) to obtain a plurality of responses (See Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the LLM/GUI is not found in the provisional application of Khan and therefore does not constitute as prior art, and is therefore instead met by the disclosures of Rosenberg and Lima as discussed in the rejection further below);
determine, using a first artificial intelligence (Al) module, one or more social determinants of health (SDOHs) for the patient based on the plurality of responses (See Khan Par [0091] & [0157]-[0158] which discloses a Social Determinants of Health (SDOH) risk score being used by the risk score determinations module; See Khan Par [0086] which discloses that the risk determination module additionally includes a user interface module and a machine learning model training module, i.e. a subsect/species of artificial intelligence);
determining, using a second AI module, a personality profile of the patient based on the plurality of responses (See Khan Par [0068] which discloses obtaining various behaviors including exercise habits, shopping habits, patient survey answers, and other lifestyle information, and is therefore understood to constitute a “personality profile” without further specifying a specific embodiment of “personality” and/or “profile”; See Khan Par [0081] which discloses the use of a machine learning model, i.e. a species of an artificial intelligence module, to determine the PPS, care gap score, risk score, change in risk score, patient’s willingness, i.e. behavior, etc.; See Khan Par [0158] which discloses the use of said behaviors, i.e. exercise habits, shopping habits, patient survey answers, and other lifestyle information, for determining a patient’s risk score by a risk score determination module, such that at Khan Par [0161]-[0162], the system identifies care plan considerations for the patient based on the determined risk score, which is based on said behaviors, as discussed above);
receive biometric information for the patient from at least one biometric device (See Khan Par [0090] which discloses a risk score determination module being configured to process data including medical visit data, medical history, mental health conditions, medical device use, treatments, etc., all constituting a medical history for a patient; See Khan Par [0141] which specifically discloses the use of various monitors for receiving biometric information relating to a patient, including diabetic patients obtaining: glucose screening & control, lipid screening & control, blood pressure screening & control, i.e. measured by biometric devices);
store the medical history, the plurality of responses, and the biometric information in the non-transitory computer-readable memory medium (See Khan par [0210] which disclose data structures being stored in one or more non-transitory computer-readable storage media in any suitable form that have fields related through location; See Khan Par [0060] which discloses any data received or sourced may be stored, upon obtaining said data, in a manner that enables sufficient processing of such data for determining different healthcare factors, PPS, and/or one or more interventions for one or more patients; See Khan Par [0017] & [0207] which disclose the computer structures for performing storing of various information);
determine, using a machine learning software, an intervention proposal for the patient based on the care schedule, the one or more SDOHs and the personality profile, wherein a behavioral change significance at least in part on a willingness to intervene indicated by the personality profile (See Khan Par [0058] which discloses providing the values and/or patient healthcare data as input to a machine learning model trained to predict the PPS, the PPS enabling a more accurate prediction of current and future healthcare needs, i.e. most likely intervention proposals or medical plans, of different patients; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc., and while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing the determination of intervention throughout the disclosure versus merely estimating costs associated with future healthcare needs, which would most likely include intervention proposals and/or medical plans; therefore, the explicit recitation of “machine learning” performing the task of determining the intervention proposal is instead met by Rosenberg as reasoned in the rejection further below, and the explicit mention of the algorithm considering the “care schedule” when developing the intervention proposal is instead met by White as recited below); and
display the intervention proposal on a display (See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc.).
As discussed above, while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing and/or determining the intervention throughout the provisional application of Khan. Further, the provisional application of Khan does not seem to have explicit support for the use of a large language model when conducting the text conversation with the patient. Therefore, Khan does not entirely meet the following limitations:
conduct, using a large language model (LLM), a text conversation with the patient using a user interface (UI) to obtain a plurality of responses;
determine, using a machine learning software, an intervention proposal based at least in part on the medical history, the plurality of responses, and the biometric information;
determine a potential atrial fibrillation (AF) diagnosis based at least in part on the medical history and the biometric information;
based on determining the potential AF diagnosis:
automatically provide the potential AF diagnosis to a medical call center; and
receive, from the medical call center, a care schedule for the patient that is based at least in part on the potential AF diagnosis.
Therefore, Rosenberg discloses conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses (See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient) and determine, using a machine learning software, an intervention proposal based at least in part on the medical history, the plurality of responses, and the biometric information (See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received), determine a potential atrial fibrillation (AF) diagnosis based at least in part on the medical history and the biometric information (See Rosenberg Par [0056] & [0352]-[0354] which discloses the system utilizing one or more standardized algorithms for determining the probability that the one or more measurements and/or patient information are indicative of atrial fibrillation) automatically provide the potential AF diagnosis to a medical call center (See Rosenberg Par [0134]-[0135] which discloses a patient interface and treatment apparatus communicating with a clinic or call center regarding in-home rehabilitation). The disclosure of Rosenberg is directly applicable to the disclosure of Khan because both disclosures share limitations and capabilities, such as being directed towards the automated generation of medical interventions for a patient based on received patient data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, which already discloses conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137]). It would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, which also discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Therefore, while the combined disclosure of Khan and Rosenberg generally discloses conducting a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, Khan and Rosenberg do not seem to explicitly recite the use of a large language model when conducting the text conversation with the patient as given by the following limitation:
conduct, using a large language model (LLM), a text conversation with the patient using a user interface (UI) to obtain a plurality of responses.
However, Lima discloses conduct, using a large language model (LLM), a text conversation with the patient using a user interface (UI) to obtain a plurality of responses (See Lima Par [0043]-[0044] & [0064]-[0070] which discloses after a user prompt is submitted to the foundation model via a chatbot user interface/website, this text-based information is processed by a large language model, therefore constituting conducting, using a large language model, a text conversation with the patient using a UI). The disclosure of Lima is directly applicable to the combined disclosure of Khan and Rosenberg, because the disclosures share limitations and capabilities, such as being directed towards automated generation of medical treatments for a patient based on received patient data/inputs.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined disclosure of Khan and Rosenberg, which already discloses conducting a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, to further include employing a large language model to perform processing of said text conversation, as disclosed by Lima, because utilizing a large language model, e.g. the foundation model of Lima, allows for analyzing far more medical data than a human counterpart with only minimally guided or self-supervised learning (See Lima Par [0044]).
While Khan, Rosenberg, and Lima generally disclose the patient interface and treatment apparatus being used as part of an in-home rehabilitation system, such that a clinic or call center can be notified and utilized to setup said in-home rehabilitation efforts, Khan, Rosenberg, and Lima do not disclose receiving a care schedule from the call center, and/or determining the intervention proposal further based on said care schedule as given by the following limitations:
receive a care schedule from the medical call center to provide to the patient;
determine the intervention proposal further for the patient based at least in part on the care schedule.
However, White discloses receiving a care schedule from the medical call center to provide to the patient (See White Par [0078] which discloses a therapy machine that performs a home treatment; See White Par [0051] which discloses a prescribed therapy or program corresponds to one or more parameters that define how a medical fluid delivery machine is to operate to administer a treatment to a patient, and further specifically mentions at White Par [0087] that one or more prescribed therapies or programs remotely from a clinician server and/or a clinician database, such that the parameters specify how the therapy machine is to administer one or more scheduled treatments to a patient, i.e. a care schedule) and determine the intervention proposal further based at least in part on the care schedule (See further White Par [0087] which further disclose implementing said care schedule to determine appropriate treatment dates and/or total treatment duration and to update any of the prescribed therapy parameters via server implementation, i.e. determining the intervention proposal based on the received care schedule). The disclosure of White is directly applicable to the already-combined disclosure of Khan, Rosenberg, and Lima, because the disclosures share limitations and capabilities, such as being directed towards automated generation of medical interventions for a patient based on received patient data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the already-combined disclosure of Khan, Rosenberg, and Lima which generally discloses notifying a clinic or call center regarding patient diagnostic data, to further include receiving a care schedule from the medical call center to provide to the patient and determining the intervention proposal further based at least in part on the received care schedule, as disclosed by White, because this allows for receiving one or more prescribed therapies or programs remotely from a clinician server and/or a clinician database, such as for utilization of a therapy machine that provides home treatment to a patient. (See White Par [0078] & White Par [0087]).
Claim 4 –
Regarding Claim 4, Khan, Rosenberg, Lima, and White disclose the non-transitory computer-readable memory medium of claim 1 in its entirety. Khan further discloses a non-transitory computer-readable memory medium, wherein:
the program instructions are further executable to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
identify at least one care gap based at least in part on the medical history (See Khan Par [0088] which discloses a care gap score determination module that determine a care gap and associated score for the patient based on processing data including medical visit data, lab values, procedures medication, etc.);
automatically display, to the patient on the display, an indication of a treatment based at least in part on the at least one care gap (See Khan Par [0088] which discloses a care gap score determination module that determine a care gap and associated score for the patient based on processing data including medical visit data, lab values, procedures medication, etc.; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc. and/or said care gap).
Claim 5 –
Regarding Claim 5, Khan, Rosenberg, Lima, and White disclose the non-transitory computer-readable memory medium of claim 1 in its entirety. Khan and Rosenberg further disclose a non-transitory computer-readable memory medium, wherein:
the program instructions are further executable to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
display a first health prognosis on the display based on following the intervention proposal (See Rosenberg Par [0210]-[0211] which discloses outputting information associated with or pertaining to desired health outcomes, i.e. prognosis, of the user if the treatment plan is followed; See Rosenberg Par [0488] which discloses the system including an interface/display configured to present information pertaining to the treatment plan, i.e. as specified in Rosenberg Par [0210]-[0211], outputting information associated with or pertaining to desired health outcomes, i.e. prognosis, of the user if the treatment plan is followed); and
display a second health prognosis on the display based on not following the intervention proposal (See Rosenberg Par [0210]-[0211] which also discloses outputting information associated with or pertaining to health outcomes, i.e. prognosis, of the user if the treatment plan is NOT followed; See Rosenberg Par [0488] which discloses the system including an interface/display configured to present information pertaining to the treatment plan, i.e. as specified in Rosenberg Par [0210]-[0211], outputting information associated with or pertaining to health outcomes, i.e. prognosis, of the user if the treatment plan is NOT followed).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the already-combined disclosure of Khan, Rosenberg, Lima, and White which generally discloses displaying health prognosis of the user on a display to further specifically include displaying prognoses for the patient based on following the intervention proposal and not following the intervention proposal, as disclosed by Rosenberg, because this allows a machine learning model to analyze and output a probability that may be used to match to a treatment plan or match to a cohort of users that share characteristics similar to those of the user, such as determining the user’s status after following or not following the treatment plan (See Rosenberg Par [0210]-[0211]).
Claim 6 –
Regarding Claim 6, Khan, Rosenberg, Lima, and White disclose the non-transitory computer-readable memory medium of claim 1 in its entirety. Khan and Rosenberg further disclose a non-transitory computer-readable memory medium, wherein:
the program instructions are further executable to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
receive health information from one or more health software applications operated by the patient (See Khan Par [0097] which discloses utilizing a large language model to generate prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, such that the prompts are responsive to user input and/or existing healthcare data such that the prompts are responsive to user input and/or existing healthcare data and generated/output to a patient via a GUI (as specified in Khan Par [0062]), and therefore would since GUI, i.e. software, receives the inputs, it would be received from a health software; See Khan Par [0066] which disclose that the computing device may receive healthcare data from another device or is co-located with the computing device within the clinical or financial setting, i.e. based on hardware communication via software means for communicating said data to the device) wherein
the intervention proposal is determined further based at least in part on the health information (See Khan Par [0058] which discloses providing the values and/or patient healthcare data as input to a machine learning model trained to predict the PPS, the PPS enabling a more accurate prediction of current and future healthcare needs, i.e. most likely intervention proposals or medical plans, of different patients; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc., and while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing the determination of intervention throughout the disclosure versus merely estimating costs associated with future healthcare needs, which would most likely include intervention proposals and/or medical plans; See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, Rosenberg, Lima, and White which already discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Claim 7 –
Regarding Claim 7, Khan, Rosenberg, Lima, and White disclose the non-transitory computer-readable memory medium of claim 1 in its entirety. Khan, Rosenberg, Lima, and White further disclose a non-transitory computer-readable memory medium, wherein:
conducting the text conversation comprises displaying one or more questions to the patient on the display (See Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the LLM/GUI is not found in the provisional application of Khan and therefore does not constitute as prior art; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient; See Lima Par [0043]-[0044] & [0064]-[0070] which discloses after a user prompt is submitted to the foundation model via a chatbot user interface/website, this text-based information is processed by a large language model, therefore constituting conducting, using a large language model, a text conversation with the patient using a UI), wherein
the one or more questions are related to one or more of the patient’s socioeconomic status, race, sex, gender, ethnicity, living environment, behavioral habits, family status, education level, personality, emotional state, and healthcare access (See Khan Par [0062]-[0063] & [0097] which discloses utilizing a large language model to generate prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, such that the prompts are responsive to user input and/or existing healthcare data, and further specifically mentions that the questions can be used to fill in data gaps for clinically-relevant information and/or patient-specific data; See Khan Par [0011]-[0012] & [0088] which specifically mentions the clinically-relevant information and/or patient specific data being related to demographics, socio-economic data, family history, lifestyle information, behavioral habits, etc.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, Rosenberg, Lima, and White, which already discloses conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined disclosure of Khan, Rosenberg, Lima, and White, which already discloses conducting a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, to further include employing a large language model to perform processing of said text conversation, as disclosed by Lima, because utilizing a large language model, e.g. the foundation model of Lima, allows for analyzing far more medical data than a human counterpart with only minimally guided or self-supervised learning/training (See Lima Par [0044]).
Claim 8 –
Regarding Claim 8, Khan, Rosenberg, Lima, and White disclose the non-transitory computer-readable memory medium of claim 1 in its entirety. Khan and Rosenberg further disclose a non-transitory computer-readable memory medium, wherein:
conducting the text conversation comprises displaying one or more questions to the patient on a display (See Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the GUI is not found in the provisional application of Khan; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient), wherein the one or more questions inquire regarding one or more of:
social determinants of health for the patient (See Khan Par [0056]-[0058] which discloses obtaining and/or determining existing social determinants that rely on socio-economic data, such as by a machine learning model, i.e. a species of an artificial intelligence module; See Khan Par [0068] which specifically mentions receiving social determinant data relating to demographic, socioeconomic data, community data);
a personality of the patient (See Khan Par [0056] which discloses the need for providing and considering patient lifestyle information);
an attitude toward disease for the patient (See Khan Par [0177] which specifically mentions that in determining the patient’s willingness, the answers to one or more surveys may indicate whether the patient agrees or disagrees with the statements provided, i.e. attitude toward disease/health of the patient);
a willingness to modify behavior of the patient (See Khan Par [0062] which specifically states that a large language model can be used to identify and collect clinically-relevant information form patients, including ask for input via a survey to assess patient willingness; See Khan Par [0095]-[0098] which discloses a large language model generating prompts requesting input from the user, i.e. via user interface means, including responses to survey questions relating to the patient’s attitude about taking charge of their own treatment to determine a patient willingness metric, i.e. degree of compliance, and specifically mentions conducting a second or follow-up survey/prompts for obtaining additional information from the user, thereby generating a more comprehensive set of data for determining patient willingness);
a medical history of the patient (See Khan Par [0090] which discloses a risk score determination module being configured to process data including medical visit data, medical history, mental health conditions, medical device use, treatments, etc., all constituting a medical history for a patient); and
an education gap of the patient (While not “education gap” per se, see Khan Par [0068] & [0158] which discloses receiving data relating to education in use of developing a risk score, such that the risk score is used for determining care plans, etc., such that it is understood that an education gap would be present/indicated in receiving said education information, but support for this embodiment is not found in the provisional application of Khan and therefore does not constitute as prior art; however, it is understood by Examiner that this limitation is written in the alternative “one or more of”, and does not necessarily have to be met by Khan to read on this claim in its entirety since the other alternatives are effectively met).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined disclosure of Khan, Rosenberg, Lima, and White, which already conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137).
Claim 9 –
Regarding Claim 9, Khan, Rosenberg, Lima, and White disclose the non-transitory computer-readable memory medium of claim 1 in its entirety. Khan and Rosenberg further disclose a non-transitory computer-readable memory medium, wherein:
in determining the intervention proposal based at least in part on the medical history, the plurality of responses, and the biometric information, the program instructions are executable by the processor to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
determine, from a plurality of risk conditions, a root behavioral cause for a medical issue experienced by the patient based on one or more of the medical history, the plurality of responses, and the biometric information (See Khan Par [0148]-[0149] which discloses applying different weights for an individual based on varying factors that may have a root cause for said medical issue, such that a more significant impact on patient health than a care gap may exist because the patient exercises only twice a week, instead of five times a week, such that a greater weight, i.e. cause/reason for occurrence, may be assigned to the individual score for the negative care gap than for the exercise care gap);
conduct a second text conversation with the patient based at least in part on the root behavioral cause, wherein the second text conversation asks the patient questions to determine a level of awareness and/or a willingness to intervene for the patient in regard to the root behavioral cause (While Applicant may intend this limitation to also be conducted via the large language model, this is not explicitly recited in the limitation, therefore see Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the GUI is not found in the provisional application of Khan; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient); and
determine the intervention proposal based at least in part on the root behavioral cause, the level of awareness, and/or the willingness to improve (See Khan Par [0058] which discloses providing the values and/or patient healthcare data as input to a machine learning model trained to predict the PPS, the PPS enabling a more accurate prediction of current and future healthcare needs, i.e. most likely intervention proposals or medical plans, of different patients; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc., and while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing the determination of intervention throughout the disclosure versus merely estimating costs associated with future healthcare needs, which would most likely include intervention proposals and/or medical plans; See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, Rosenberg, Lima, and White, which already discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Claim 10 –
Regarding Claim 10, Khan, Rosenberg, Lima, and White disclose the non-transitory computer-readable memory medium of claim 9 in its entirety. Khan further discloses a non-transitory computer-readable memory medium, wherein:
the plurality of risk conditions comprise one or more of:
tobacco use (While Khan does mention the need for providing and considering patient lifestyle information, including habits such as smoking at Khan Par [0056], support for this embodiment is not found in the provisional application of Khan and therefore does not constitute as prior art; however, it is understood by Examiner that this limitation is written in the alternative “one or more of”, and does not necessarily have to be met by Khan to read on this claim in its entirety since the other alternatives are effectively met);
alcohol use (While Khan does mention the need for providing and considering patient lifestyle information, including habits such as drinking at Khan Par [0056], support for this embodiment is not found in the provisional application of Khan and therefore does not constitute as prior art; however, it is understood by Examiner that this limitation is written in the alternative “one or more of”, and does not necessarily have to be met by Khan to read on this claim in its entirety since the other alternatives are effectively met);
sleep issues (While Khan does not explicitly mention “sleep issues” per se, Khan does mention receiving and consideration of “lifestyle habits” which would most likely include sleep data, however, it is understood by Examiner that this limitation is written in the alternative “one or more of”, and does not necessarily have to be met by Khan to read on this claim in its entirety since the other alternatives are effectively met; therefore, while not relied upon to read on this claim in its entirety, for the purposes of advancing prosecution, see Rosenberg Par [0110] which discloses the use of quality and/or measure of sleep associated with the user by the machine learning models when developing the treatment plan);
lack of exercise (While not “lack of exercise” per se, Khan Par [0068] discloses receiving data relating to exercise habits, which is understood by Examiner to include or provide indications of a “lack of exercise”);
poor diet and/or obesity (While not “poor diet” per se, Khan Par [0068] discloses receiving data relating to diet, which is understood by Examiner to include or provide indications of a “poor diet”; While not “obesity” per se, see Khan Par [0141] which discloses the obtaining and use of body mass index, i.e. BMI, which would include or provide indications of “obesity”);
hypertension (See Khan Fig. 7A & 7B and Khan Par [0042], [0141], [0144], [0166] which discloses determining a risk score for hypertension, such that blood pressure screening and control are obtained and monitored over time); and
diabetes (See Khan 5A & 5B and Khan Par [0141] & [0144] which discloses the system monitoring various chronic conditions and metrics associated therewith, including diabetes, and glucose screening & control metrics),
wherein the level of awareness comprises one of:
ignorance (While not “ignorance” per se, see Khan Par [0068] & [0158] which discloses receiving data relating to education in use of developing a risk score, such that the risk score is used for determining care plans, etc., but support for this embodiment is not found in the provisional application of Khan and therefore does not constitute as prior art; however, it is understood by Examiner that this limitation is written in the alternative “one of”, and does not necessarily have to be met by Khan to read on this claim in its entirety since the other alternatives are effectively met);
precontemplation (See Khan Par [0177] which specifically mentions that in determining the patient’s willingness, the answers to one or more surveys may indicate whether the patient agrees or disagrees with the statements provided, i.e. understood to constitute precontemplation/contemplation about which factors impact the patient’s health, without further specifying such “precontemplation/contemplation”); and
contemplation (See Khan Par [0177] which specifically mentions that in determining the patient’s willingness, the answers to one or more surveys may indicate whether the patient agrees or disagrees with the statements provided, including “I understand what factors impact my health”, i.e. understood to constitute precontemplation/contemplation about which factors impact the patient’s health, without further specifying such “precontemplation/contemplation”); and
wherein the willingness to intervene comprises one of:
unwillingness (While not “unwillingness” per se, See Khan Par [0060] which discloses receiving obtaining data for each of multiple healthcare factors and storing the data, such that a measure representing patient willingness, i.e. degree of compliance, with the PPS is received/determined; See Khan Par [0062] which specifically states that a large language model can be used to identify and collect clinically-relevant information form patients, including ask for input via a survey to assess patient willingness; See Khan Par [0095]-[0098] which discloses a large language model generating prompts requesting input from the user, i.e. via user interface means, including responses to survey questions relating to the patient’s attitude about taking charge of their own treatment to determine a patient willingness metric, i.e. degree of compliance, which would thereby be an indicator of “unwillingness” as well; See Khan Par [0177] which also specifically mentions that in determining the patient’s willingness, the answers to one or more surveys may indicate whether the patient agrees or disagrees with the statements provided, i.e. understood by Examiner to represent willingness and/or unwillingness, respectively);
preparation (See Khan Par [0177] which also specifically mentions that in determining the patient’s willingness, the answers to one or more surveys may indicate whether the patient agrees or disagrees with the statements provided, including responsiveness towards providers, i.e. preparation for future medical treatments);
action (See Khan Par [0095]-[0098] which discloses generating prompts requesting input from the user, i.e. via user interface means, including responses to survey questions relating to the patient’s attitude, e.g. agreeing or disagreeing, about taking charge of their own treatment, i.e. understood to constitute “action”); and
maintenance (See Khan Par [0177] which specifically mentions that in determining the patient’s willingness, the answers to one or more surveys may indicate whether the patient agrees or disagrees with the statements provided, including maintaining medication dosage schedule, receiving routine medical examinations, receiving preventative care, willingness to visit specialists, which all are understood to constitute “maintenance” of the interventions/plans proposed).
Claim 12 –
Regarding Claim 12, Khan, Rosenberg, Lima, and White disclose the non-transitory computer-readable memory medium of claim 1 in its entirety. Khan and Rosenberg further disclose a non-transitory computer-readable memory medium, wherein:
the program instructions are further executable to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
after displaying the intervention proposal on the display, conduct a second text conversation with the patient using the UI to determine a degree of compliance with the intervention proposal (While Applicant may intend this limitation to also be conducted via the large language model, this is not explicitly recited in the limitation, see Khan Par [0060] which discloses receiving obtaining data for each of multiple healthcare factors and storing the data, such that a measure representing patient willingness, i.e. degree of compliance, with the PPS is received/determined; See Khan Par [0062] which specifically states that a large language model can be used to identify and collect clinically-relevant information form patients, including ask for input via a survey to assess patient willingness; See Khan Par [0095]-[0098] which discloses generating prompts requesting input from the user, i.e. via user interface means, including responses to survey questions relating to the patient’s attitude about taking charge of their own treatment to determine a patient willingness metric, i.e. degree of compliance, and specifically mentions conducting a second or follow-up survey/prompts for obtaining additional information from the user, thereby generating a more comprehensive set of data for determining patient willingness; therefore see Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the GUI is not found in the provisional application of Khan; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient);
modify a behavior profile of the patient based at least in part on the degree of compliance with the intervention proposal (While not a “behavior profile” per se, see Khan Par [0098] which specifically mentions that a patient prioritization score (PPS) can be determined and updated based on the degree of patient willingness; See Khan Par [0104] which discloses the generated GUI identifying treatment, procedures, changes of lifestyle, etc., such that at Khan Par [0196] depending on the PPS, which depends on the degree of patient willingness as discussed above, the GUI may include specific recommendations for interventions, such as lifestyle management, etc., which is understood to represent a “modification” to a “behavior profile” of the patient; See Par [0198]-[0202] & Fig. 14B which discloses the use of a GUI including patient information, scores, measures, etc., including the PPS which is based on the degree of patient willingness, such that this is understood to read on a behavioral profile patient profile);
determine a second intervention proposal based at least in part on the degree of compliance and the modified behavior profile (See Khan Par [0196] which discloses that depending on the PPS, which depends on the degree of patient willingness as discussed above, the GUI may include recommendations for interventions, such as lifestyle management, etc., preventative screenings, monitoring, specialist referrals, etc., which are all plural, indicating at least a first and second intervention; See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received); and
display the second intervention proposal on the display (See Khan Par [0196] which discloses that depending on the PPS, which depends on the degree of patient willingness as discussed above, the GUI may include, i.e. display, recommendations for interventions, such as lifestyle management, etc., preventative screenings, monitoring, specialist referrals, etc., which are all plural, indicating at least a first and second intervention, being determined and recommended by the system of Khan).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, Rosenberg, Lima, and White, which already discloses conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137]). It would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, which also discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Claim 13 –
Regarding Claim 13, Khan, Rosenberg, Lima, and White disclose a method, comprising:
by a computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above):
receiving a medical history for a patient (See Khan Par [0090] which discloses a risk score determination module being configured to process data including medical visit data, medical history, mental health conditions, medical device use, treatments, etc., all constituting a medical history for a patient);
conducting, using a large language model (LLM), a text conversation with the patient using a user interface (UI) to obtain a plurality of responses (See Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the LLM/GUI is not found in the provisional application of Khan and therefore does not constitute as prior art, and is therefore instead met by Rosenberg and Lima, as discussed further in the rejection; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient; See Lima Par [0043]-[0044] & [0064]-[0070] which discloses after a user prompt is submitted to the foundation model via a chatbot user interface/website, this text-based information is processed by a large language model, therefore constituting conducting, using a large language model, a text conversation with the patient using a UI);
determining, using a first artificial intelligence module, one or more social determinants of health (SDOHs) for the patient based on the plurality of responses (See Khan Par [0091] & [0157]-[0158] which discloses a Social Determinants of Health (SDOH) risk score being used by the risk score determinations module; See Khan Par [0086] which discloses that the risk determination module additionally includes a user interface module and a machine learning model training module, i.e. a subsect/species of artificial intelligence);
determining, using a second artificial intelligence module, a personality profile of the patient based on the plurality of responses (See Khan Par [0068] which discloses obtaining various behaviors including exercise habits, shopping habits, patient survey answers, and other lifestyle information, and is therefore understood to constitute a “personality profile” without further specifying a specific embodiment of “personality” and/or “profile”; See Khan Par [0081] which discloses the use of a machine learning model, i.e. a species of an artificial intelligence module, to determine the PPS, care gap score, risk score, change in risk score, patient’s willingness, i.e. behavior, etc.; See Khan Par [0158] which discloses the use of said behaviors, i.e. exercise habits, shopping habits, patient survey answers, and other lifestyle information, for determining a patient’s risk score by a risk score determination module, such that at Khan Par [0161]-[0162], the system identifies care plan considerations for the patient based on the determined risk score, which is based on said behaviors, as discussed above);
receiving biometric information for the patient from at least one biometric device (See Khan Par [0090] which discloses a risk score determination module being configured to process data including medical visit data, medical history, mental health conditions, medical device use, treatments, etc., all constituting a medical history for a patient; See Khan Par [0141] which specifically discloses the use of various monitors for receiving biometric information relating to a patient, including diabetic patients obtaining: glucose screening & control, lipid screening & control, blood pressure screening & control, i.e. measured by biometric devices);
storing the medical history, the plurality of responses, and the biometric information in the non-transitory computer-readable memory medium (See Khan par [0210] which disclose data structures being stored in one or more non-transitory computer-readable storage media in any suitable form that have fields related through location; See Khan Par [0060] which discloses any data received or sourced may be stored, upon obtaining said data, in a manner that enables sufficient processing of such data for determining different healthcare factors, PPS, and/or one or more interventions for one or more patients; See Khan Par [0017] & [0207] which disclose the computer structures for performing storing of various information);
determining a potential atrial fibrillation (AF) diagnosis based at least in part on the medical history and the biometric information (See Rosenberg Par [0056] & [0352]-[0354] which discloses the system utilizing one or more standardized algorithms for determining the probability that the one or more measurements and/or patient information are indicative of atrial fibrillation);
based on determining the potential AF diagnosis:
automatically providing the potential AF diagnosis to a medical call center (See Rosenberg Par [0134]-[0135] which discloses a patient interface and treatment apparatus communicating with a clinic or call center regarding in-home rehabilitation) and
receiving, from the medical call center, a care schedule for the patient that is based at least in part on the potential AF diagnosis (See White Par [0078] which discloses a therapy machine that performs a home treatment; See White Par [0051] which discloses a prescribed therapy or program corresponds to one or more parameters that define how a medical fluid delivery machine is to operate to administer a treatment to a patient, and further specifically mentions at White Par [0087] that one or more prescribed therapies or programs remotely from a clinician server and/or a clinician database, such that the parameters specify how the therapy machine is to administer one or more scheduled treatments to a patient, i.e. a care schedule);
determine, using a machine learning software, an intervention proposal for the patient based on the care schedule, the one or more SDOHs and the personality profile, wherein a behavioral change significance at least in part on a willingness to intervene indicated by the personality profile (See Khan Par [0058] which discloses providing the values and/or patient healthcare data as input to a machine learning model trained to predict the PPS, the PPS enabling a more accurate prediction of current and future healthcare needs, i.e. most likely intervention proposals or medical plans, of different patients; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc., and while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing the determination of intervention throughout the disclosure versus merely estimating costs associated with future healthcare needs, which would most likely include intervention proposals and/or medical plans; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient; See White Par [0087] which further disclose implementing said care schedule to determine appropriate treatment dates and/or total treatment duration and to update any of the prescribed therapy parameters via server implementation, i.e. determining the intervention proposal based on the received care schedule).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, which already discloses conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137]). It would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, which also discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Additionally, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined disclosure of Khan and Rosenberg, which already discloses conducting a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, to further include employing a large language model to perform processing of said text conversation, as disclosed by Lima, because utilizing a large language model, e.g. the foundation model of Lima, allows for analyzing far more medical data than a human counterpart with only minimally guided or self-supervised learning (See Lima Par [0044]).
It would have been additionally obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the already-combined disclosure of Khan, Rosenberg, and Lima which generally discloses notifying a clinic or call center regarding patient diagnostic data, to further include receiving a care schedule from the medical call center to provide to the patient and determining the intervention proposal further based at least in part on the received care schedule, as disclosed by White, because this allows for receiving one or more prescribed therapies or programs remotely from a clinician server and/or a clinician database, such as for utilization of a therapy machine that provides home treatment to a patient. (See White Par [0078] & White Par [0087]).
Claim 16 –
Regarding Claim 16, Khan, Rosenberg, Lima, and White disclose the method of claim 13 in its entirety. Khan further discloses a method, wherein:
identifying at least one care gap based at least in part on the medical history (See Khan Par [0088] which discloses a care gap score determination module that determine a care gap and associated score for the patient based on processing data including medical visit data, lab values, procedures medication, etc.);
automatically displaying, to the patient on the display, an indication of a treatment based at least in part on the at least one care gap (See Khan Par [0088] which discloses a care gap score determination module that determine a care gap and associated score for the patient based on processing data including medical visit data, lab values, procedures medication, etc.; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc. and/or said care gap).
Claim 17 –
Regarding Claim 17, Khan, Rosenberg, Lima, and White disclose the method of claim 13 in its entirety. Khan and Rosenberg further disclose a method, wherein:
determining the intervention proposal based at least in part on the medical history, the plurality of responses, and the biometric information, the machine learning software comprises:
determining, using a first artificial intelligence module, one or more social determinants of health of the patient based on the plurality of responses (See Khan Par [0056]-[0058] which discloses obtaining and/or determining existing social determinants that rely on socio-economic data, such as by a machine learning model, i.e. a species of an artificial intelligence module; See Khan Par [0068] which specifically mentions receiving social determinant data relating to demographic, socioeconomic data, community data; See Khan Par [0091] which discloses the use of risk score models and a risk score determination module that can determine the Social Determinants of Health (SDOH) risk score; See Khan Par [0158] which discloses the use of said demographic, socioeconomic, and/or community data for determining a patient’s risk score by a risk score determination module, such that at Khan Par [0161]-[0162], the system identifies care plan considerations for the patient based on the determined risk score, which is based on said social determining data, as discussed above); and
determining, using a second artificial intelligence module, a personality profile of the patient based on the plurality of responses (See Khan Par [0068] which discloses obtaining various behaviors including exercise habits, shopping habits, patient survey answers, and other lifestyle information, and is therefore understood to constitute a “personality profile” without further specifying a specific embodiment of “personality” and/or “profile”; See Khan Par [0081] which discloses the use of a machine learning model, i.e. a species of an artificial intelligence module, to determine the PPS, care gap score, risk score, change in risk score, patient’s willingness, i.e. behavior, etc.; See Khan Par [0158] which discloses the use of said behaviors, i.e. exercise habits, shopping habits, patient survey answers, and other lifestyle information, for determining a patient’s risk score by a risk score determination module, such that at Khan Par [0161]-[0162], the system identifies care plan considerations for the patient based on the determined risk score, which is based on said behaviors, as discussed above),
wherein the intervention proposal is determined further based on one or both of the social determinants of health and the personality profile (See Khan Par [0158] which discloses the use of said demographic, socioeconomic, and/or community data and the use of said behaviors, i.e. exercise habits, shopping habits, patient survey answers, diet, addiction treatment history, and other lifestyle information for determining a patient’s risk score by a risk score determination module, such that at Khan Par [0161]-[0162], the system identifies care plan considerations for the patient based on the determined risk score, which is based on said social determining and behavior/personality profile data, as discussed above; See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined disclosure of Khan, Rosenberg, Lima, and White, which already discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Claim 18 –
Regarding Claim 18, Khan, Rosenberg, Lima, and White disclose the method of claim 13 in its entirety. Khan and Rosenberg further disclose a method, further comprising:
after displaying the intervention proposal on the display, conducting a second text conversation with the patient using the UI to determine a degree of compliance with the intervention proposal (See Khan Par [0060] which discloses receiving obtaining data for each of multiple healthcare factors and storing the data, such that a measure representing patient willingness, i.e. degree of compliance, with the PPS is received/determined; See Khan Par [0062] which specifically states that a large language model can be used to identify and collect clinically-relevant information form patients, including ask for input via a survey to assess patient willingness; See Khan Par [0095]-[0098] which discloses a large language generating prompts requesting input from the user, including responses to survey questions relating to the patient’s attitude about taking charge of their own treatment to determine a patient willingness metric, i.e. degree of compliance, and specifically mentions conducting a second or follow-up survey/prompts for obtaining additional information from the user, thereby generating a more comprehensive set of data for determining patient willingness; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient; See Lima Par [0043]-[0044] & [0064]-[0070] which discloses after a user prompt is submitted to the foundation model via a chatbot user interface/website, this text-based information is processed by a large language model, therefore constituting conducting, using a large language model, a text conversation with the patient using a UI);
modifying a behavior profile of the patient based at least in part on the degree of compliance with the intervention proposal (While not a “behavior profile” per se, see Khan Par [0098] which specifically mentions that a patient prioritization score (PPS) can be determined and updated based on the degree of patient willingness; See Khan Par [0104] which discloses the generated GUI identifying treatment, procedures, changes of lifestyle, etc., such that at Khan Par [0196] depending on the PPS, which depends on the degree of patient willingness as discussed above, the GUI may include specific recommendations for interventions, such as lifestyle management, etc., which is understood to represent a “modification” to a “behavior profile” of the patient; See Par [0198]-[0202] & Fig. 14B which discloses the use of a GUI including patient information, scores, measures, etc., including the PPS which is based on the degree of patient willingness, such that this is understood to read on a behavioral profile patient profile);
determining a second intervention proposal based at least in part on the degree of compliance and the modified behavior profile (See Khan Par [0196] which discloses that depending on the PPS, which depends on the degree of patient willingness as discussed above, the GUI may include recommendations for interventions, such as lifestyle management, etc., preventative screenings, monitoring, specialist referrals, etc., which are all plural, indicating at least a first and second intervention, being determined and recommended by the system of Khan; ; See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received); and
displaying the second intervention proposal on the display (See Khan Par [0196] which discloses that depending on the PPS, which depends on the degree of patient willingness as discussed above, the GUI may include, i.e. display, recommendations for interventions, such as lifestyle management, etc., preventative screenings, monitoring, specialist referrals, etc., which are all plural, indicating at least a first and second intervention, being determined and recommended by the system of Khan).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan. Rosenberg, Lima, and White which already discloses conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137]). It would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, which also discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Claim 19 –
Regarding Claim 19, Khan, Rosenberg, Lima, and White disclose a computing device, comprising:
one or more processors (See Khan Par [0017] & [0207] which disclose the computer structures claimed above);
a non-transitory computer-readable memory medium coupled to the one or more processors (See Khan Par [0017] & [0207] which disclose the computer structures claimed above); and
a display (See Khan Par [0027] & [0197] which discloses providing a GUI or one or more display implementations on a physical display), wherein
the memory medium stores program instructions that are executable by the one or more processors to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
receive a medical history for a patient (See Khan Par [0090] which discloses a risk score determination module being configured to process data including medical visit data, medical history, mental health conditions, medical device use, treatments, etc., all constituting a medical history for a patient);
conduct, using a large language model (LLM), a text conversation with the patient using a user interface (UI) to obtain a plurality of responses (See Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the LLM/GUI is not found in the provisional application of Khan and therefore does not constitute as prior art, and is therefore instead met by Rosenberg and Lima, as discussed further in the rejection; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient; See Lima Par [0043]-[0044] & [0064]-[0070] which discloses after a user prompt is submitted to the foundation model via a chatbot user interface/website, this text-based information is processed by a large language model, therefore constituting conducting, using a large language model, a text conversation with the patient using a UI);
determine, using a first artificial intelligence module, one or more social determinants of health (SDOHs) for the patient based on the plurality of responses (See Khan Par [0091] & [0157]-[0158] which discloses a Social Determinants of Health (SDOH) risk score being used by the risk score determinations module; See Khan Par [0086] which discloses that the risk determination module additionally includes a user interface module and a machine learning model training module, i.e. a subsect/species of artificial intelligence);
determine, using a second artificial intelligence module, a personality profile of the patient based on the plurality of responses (See Khan Par [0068] which discloses obtaining various behaviors including exercise habits, shopping habits, patient survey answers, and other lifestyle information, and is therefore understood to constitute a “personality profile” without further specifying a specific embodiment of “personality” and/or “profile”; See Khan Par [0081] which discloses the use of a machine learning model, i.e. a species of an artificial intelligence module, to determine the PPS, care gap score, risk score, change in risk score, patient’s willingness, i.e. behavior, etc.; See Khan Par [0158] which discloses the use of said behaviors, i.e. exercise habits, shopping habits, patient survey answers, and other lifestyle information, for determining a patient’s risk score by a risk score determination module, such that at Khan Par [0161]-[0162], the system identifies care plan considerations for the patient based on the determined risk score, which is based on said behaviors, as discussed above);
receive biometric information for the patient from at least one biometric device (See Khan Par [0090] which discloses a risk score determination module being configured to process data including medical visit data, medical history, mental health conditions, medical device use, treatments, etc., all constituting a medical history for a patient; See Khan Par [0141] which specifically discloses the use of various monitors for receiving biometric information relating to a patient, including diabetic patients obtaining: glucose screening & control, lipid screening & control, blood pressure screening & control, i.e. measured by biometric devices);
store the medical history, the plurality of responses, and the biometric information in the non-transitory computer-readable memory medium (See Khan par [0210] which disclose data structures being stored in one or more non-transitory computer-readable storage media in any suitable form that have fields related through location; See Khan Par [0060] which discloses any data received or sourced may be stored, upon obtaining said data, in a manner that enables sufficient processing of such data for determining different healthcare factors, PPS, and/or one or more interventions for one or more patients; See Khan Par [0017] & [0207] which disclose the computer structures for performing storing of various information);
based on determining the potential AF diagnosis:
automatically provide the potential AF diagnosis to a medical call center (See Rosenberg Par [0134]-[0135] which discloses a patient interface and treatment apparatus communicating with a clinic or call center regarding in-home rehabilitation);
receive, from the medical call center, a care schedule for the patient that is based at least in part on the potential AF diagnosis (See White Par [0078] which discloses a therapy machine that performs a home treatment; See White Par [0051] which discloses a prescribed therapy or program corresponds to one or more parameters that define how a medical fluid delivery machine is to operate to administer a treatment to a patient, and further specifically mentions at White Par [0087] that one or more prescribed therapies or programs remotely from a clinician server and/or a clinician database, such that the parameters specify how the therapy machine is to administer one or more scheduled treatments to a patient, i.e. a care schedule);
determine, using a machine learning software, an intervention proposal for the patient based on the care schedule, the one or more SDOHs and the personality profile, wherein a behavioral change significance at least in part on a willingness to intervene indicated by the personality profile (See Khan Par [0058] which discloses providing the values and/or patient healthcare data as input to a machine learning model trained to predict the PPS, the PPS enabling a more accurate prediction of current and future healthcare needs, i.e. most likely intervention proposals or medical plans, of different patients; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc., and while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing the determination of intervention throughout the disclosure versus merely estimating costs associated with future healthcare needs, which would most likely include intervention proposals and/or medical plans; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient; See White Par [0087] which further disclose implementing said care schedule to determine appropriate treatment dates and/or total treatment duration and to update any of the prescribed therapy parameters via server implementation, i.e. determining the intervention proposal based on the received care schedule); and
display the intervention proposal on a display (See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, which already discloses conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137]). It would have been further obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, which also discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Additionally, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined disclosure of Khan and Rosenberg, which already discloses conducting a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, to further include employing a large language model to perform processing of said text conversation, as disclosed by Lima, because utilizing a large language model, e.g. the foundation model of Lima, allows for analyzing far more medical data than a human counterpart with only minimally guided or self-supervised learning (See Lima Par [0044]).
It would have been additionally obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the already-combined disclosure of Khan, Rosenberg, and Lima which generally discloses notifying a clinic or call center regarding patient diagnostic data, to further include receiving a care schedule from the medical call center to provide to the patient and determining the intervention proposal further based at least in part on the received care schedule, as disclosed by White, because this allows for receiving one or more prescribed therapies or programs remotely from a clinician server and/or a clinician database, such as for utilization of a therapy machine that provides home treatment to a patient. (See White Par [0078] & White Par [0087]).
Claim 20 –
Regarding Claim 20, Khan, Rosenberg, Lima, and White disclose the device of claim 19 its entirety. Khan and Rosenberg further disclose a device, wherein:
in determining the intervention proposal based at least in part on the medical history, the plurality of responses, and the biometric information, the program instructions are executable by the one or more processors to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
determine, from a plurality of risk conditions, a root behavioral cause for a medical issue experienced by the patient based on one or more of the medical history, the plurality of responses, and the biometric information (See Khan Par [0148]-[0149] which discloses applying different weights for an individual based on varying factors that may have a root cause for said medical issue, such that a more significant impact on patient health than a care gap may exist because the patient exercises only twice a week, instead of five times a week, such that a greater weight, i.e. cause/reason for occurrence, may be assigned to the individual score for a negative care gap than for the exercise care gap);
conduct a second text conversation with the patient based at least in part on the root behavioral cause, wherein the second text conversation asks the patient questions to determine a level of awareness and/or a willingness to intervene for the patient in regard to the root behavioral cause (While Applicant may intend this limitation to also be conducted via the large language model, this is not explicitly recited in the limitation, therefore see Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the GUI is not found in the provisional application of Khan; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient); and
determine the intervention proposal based at least in part on the root behavioral cause, the level of awareness, and/or the willingness to improve (See Khan Par [0058] which discloses providing the values and/or patient healthcare data as input to a machine learning model trained to predict the PPS, the PPS enabling a more accurate prediction of current and future healthcare needs, i.e. most likely intervention proposals or medical plans, of different patients; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc., and while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing the determination of intervention throughout the disclosure versus merely estimating costs associated with future healthcare needs, which would most likely include intervention proposals and/or medical plans; See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, Rosenberg, Lima, and White, which already discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Claim 21 –
Regarding Claim 21, Khan, Rosenberg, Lima, and White disclose the computing device of claim 19 in its entirety. Khan and Rosenberg further disclose a computing device, wherein:
the program instructions are further executable by the one or more processors to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
display a first health prognosis on the display based on following the intervention proposal (See Rosenberg Par [0210]-[0211] which discloses outputting information associated with or pertaining to desired health outcomes, i.e. prognosis, of the user if the treatment plan is followed; See Rosenberg Par [0488] which discloses the system including an interface/display configured to present information pertaining to the treatment plan, i.e. as specified in Rosenberg Par [0210]-[0211], outputting information associated with or pertaining to desired health outcomes, i.e. prognosis, of the user if the treatment plan is followed); and
display a second health prognosis on the display based on not following the intervention proposal (See Rosenberg Par [0210]-[0211] which also discloses outputting information associated with or pertaining to health outcomes, i.e. prognosis, of the user if the treatment plan is NOT followed; See Rosenberg Par [0488] which discloses the system including an interface/display configured to present information pertaining to the treatment plan, i.e. as specified in Rosenberg Par [0210]-[0211], outputting information associated with or pertaining to health outcomes, i.e. prognosis, of the user if the treatment plan is NOT followed).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the already-combined disclosure of Khan, Rosenberg, Lima, and White which generally discloses displaying health prognosis of the user on a display to further specifically include displaying prognoses for the patient based on following the intervention proposal and not following the intervention proposal, as disclosed by Rosenberg, because this allows a machine learning model to analyze and output a probability that may be used to match to a treatment plan or match to a cohort of users that share characteristics similar to those of the user, such as determining the user’s status after following or not following the treatment plan (See Rosenberg Par [0210]-[0211]).
Claim 22 –
Regarding Claim 22, Khan, Rosenberg, Lima, and White disclose the computing device of claim 19 in its entirety. Khan and Rosenberg further disclose a computing device, wherein:
the program instructions are further executable by the one or more processors to cause the computing device (See Khan Par [0017] & [0207] which disclose the computer structures claimed above) to:
receive health information from one or more health software applications operated by the patient (See Khan Par [0097] which discloses utilizing a large language model to generate prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, such that the prompts are responsive to user input and/or existing healthcare data such that the prompts are responsive to user input and/or existing healthcare data and generated/output to a patient via a GUI (as specified in Khan Par [0062]), and therefore would since GUI, i.e. software, receives the inputs, it would be received from a health software; See Khan Par [0066] which disclose that the computing device may receive healthcare data from another device or is co-located with the computing device within the clinical or financial setting, i.e. based on hardware communication via software means for communicating said data to the device) wherein
the intervention proposal is determined further based at least in part on the health information (See Khan Par [0058] which discloses providing the values and/or patient healthcare data as input to a machine learning model trained to predict the PPS, the PPS enabling a more accurate prediction of current and future healthcare needs, i.e. most likely intervention proposals or medical plans, of different patients; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc., and while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing the determination of intervention throughout the disclosure versus merely estimating costs associated with future healthcare needs, which would most likely include intervention proposals and/or medical plans; See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, Rosenberg, Lima, and White which already discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Claim 23 –
Regarding Claim 23, Khan, Rosenberg, Lima, and White disclose the method of claim 13 in its entirety. Rosenberg further discloses a method, further comprising:
displaying a first health prognosis on the display based on following the intervention proposal (See Rosenberg Par [0210]-[0211] which discloses outputting information associated with or pertaining to desired health outcomes, i.e. prognosis, of the user if the treatment plan is followed; See Rosenberg Par [0488] which discloses the system including an interface/display configured to present information pertaining to the treatment plan, i.e. as specified in Rosenberg Par [0210]-[0211], outputting information associated with or pertaining to desired health outcomes, i.e. prognosis, of the user if the treatment plan is followed); and
displaying a second health prognosis on the display based on not following the intervention proposal (See Rosenberg Par [0210]-[0211] which also discloses outputting information associated with or pertaining to health outcomes, i.e. prognosis, of the user if the treatment plan is NOT followed; See Rosenberg Par [0488] which discloses the system including an interface/display configured to present information pertaining to the treatment plan, i.e. as specified in Rosenberg Par [0210]-[0211], outputting information associated with or pertaining to health outcomes, i.e. prognosis, of the user if the treatment plan is NOT followed).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the already-combined disclosure of Khan, Rosenberg, Lima, and White which generally discloses displaying health prognosis of the user on a display to further specifically include displaying prognoses for the patient based on following the intervention proposal and not following the intervention proposal, as disclosed by Rosenberg, because this allows a machine learning model to analyze and output a probability that may be used to match to a treatment plan or match to a cohort of users that share characteristics similar to those of the user, such as determining the user’s status after following or not following the treatment plan (See Rosenberg Par [0210]-[0211]).
Claim 24 –
Regarding Claim 24, Khan, Rosenberg, Lima, and White disclose the method of claim 13 in its entirety. Khan and Rosenberg further disclose a method, further comprising:
receiving health information from one or more health software applications operated by the patient (See Khan Par [0097] which discloses utilizing a large language model to generate prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, such that the prompts are responsive to user input and/or existing healthcare data such that the prompts are responsive to user input and/or existing healthcare data and generated/output to a patient via a GUI (as specified in Khan Par [0062]), and therefore would since GUI, i.e. software, receives the inputs, it would be received from a health software; See Khan Par [0066] which disclose that the computing device may receive healthcare data from another device or is co-located with the computing device within the clinical or financial setting, i.e. based on hardware communication via software means for communicating said data to the device), wherein
the intervention proposal is determined further based at least in part on the health information (See Khan Par [0058] which discloses providing the values and/or patient healthcare data as input to a machine learning model trained to predict the PPS, the PPS enabling a more accurate prediction of current and future healthcare needs, i.e. most likely intervention proposals or medical plans, of different patients; See Khan Par [0194]-[0196] which discloses a GUI being generated that includes prompt to a healthcare professional to administer a level of care to a patient, based on the PPS determined for the patient, such that the GUI may include, i.e. output/display, one or more recommended actions for treating the patient, and may include recommendations for interventions such as lifestyle management, preventative screenings, etc., and while it is understood by Examiner that the “GUI” itself is not performing said aspects of learning and decision-making because it is recited in Khan Par [0194] that “the updated information may be processed and used to determine a new or updated PPS for the patient. The PPS may be used to generate a GUI that includes a prompt to the Provider to administer a level of care to the patient”, Khan does not seem to explicitly recite machine learning software performing the determination of intervention throughout the disclosure versus merely estimating costs associated with future healthcare needs, which would most likely include intervention proposals and/or medical plans; See Rosenberg Par [0088] & [0107]-[0111] which discloses using trained machine learning models to generate treatment plans using real-time and historical data correlations involving patient cohort-equivalents based on one or more probabilities of the user complying with one or more exercise regimens and/or a respective measure of benefit one or more exercise regimens provide the user, and can use a training data set of a corpus of information associated with treatment data (i.e. medical information), measures of benefits of exercises provide to users, probabilities of users complying with the one or more exercise regimens, etc.), i.e. responses of how the user will comply with the one or more exercise regimens, pertaining to users who performed treatment plans using the treatment apparatus, the details (e.g., treatment protocol including exercises, amount of time to perform the exercises, instructions for the patient to follow, how often to perform the exercises, a schedule of exercises, parameters/configurations/settings of the treatment apparatus throughout each step of the treatment plan, etc.) of the treatment plans performed by the users using the treatment apparatus, and/or the results of the treatment plans performed by the users, etc.; See Rosenberg Par [0056] which discloses that various data relating to a treatment plan, including health data from one or more sensors, i.e. biometric information, can be received).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, Rosenberg, Lima, and White which already discloses determining a patient prioritization score and medical treatment/interventions associated therewith based on received patient data, to further specifically include determinations of said medical intervention by machine learning software, as disclosed by Rosenberg, because this allows for generation and optimization of treatment plans according to sets of parameters that relate to the received data, such as treatment data, measures of benefits of exercises provided to users, probabilities of user compliance associated with the exercises, etc. (see Rosenberg Par [0111]).
Claim 25 –
Regarding Claim 25, Khan, Rosenberg, Lima, and White disclose the method of claim 13 in its entirety. Khan, Rosenberg, Lima, and White further disclose a method, wherein:
conducting the text conversation comprises displaying one or more questions to the patient on the display (See Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the LLM/GUI is not found in the provisional application of Khan and therefore does not constitute as prior art; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient; See Lima Par [0043]-[0044] & [0064]-[0070] which discloses after a user prompt is submitted to the foundation model via a chatbot user interface/website, this text-based information is processed by a large language model, therefore constituting conducting, using a large language model, a text conversation with the patient using a UI), wherein
the one or more questions are related to one or more of the patient's socioeconomic status, race, sex, gender, ethnicity, living environment, behavioral habits, family status, education level, personality, emotional state, and healthcare access (See Khan Par [0062]-[0063] & [0097] which discloses utilizing a large language model to generate prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, such that the prompts are responsive to user input and/or existing healthcare data, and further specifically mentions that the questions can be used to fill in data gaps for clinically-relevant information and/or patient-specific data; See Khan Par [0011]-[0012] & [0088] which specifically mentions the clinically-relevant information and/or patient specific data being related to demographics, socio-economic data, family history, lifestyle information, behavioral habits, etc.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the disclosure of Khan, Rosenberg, Lima, and White which already discloses conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined disclosure of Khan, Rosenberg, Lima, and White which already discloses conducting a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, to further include employing a large language model to perform processing of said text conversation, as disclosed by Lima, because utilizing a large language model, e.g. the foundation model of Lima, allows for analyzing far more medical data than a human counterpart with only minimally guided or self-supervised learning/training (See Lima Par [0044]).
Claim 26 –
Regarding Claim 26, Khan, Rosenberg, Lima, and White disclose the method of claim 13 in its entirety. Khan and Rosenberg further disclose a method, wherein:
conducting the text conversation comprises displaying one or more questions to the patient on a display (See Khan Par [0062] & [0097] which discloses generating prompts requesting input from a user, including responses to survey questions relating to the patient's attitude about taking charge of their own treatments, and while Khan generally discloses the use of a large language model and/or GUI for implementing said text conversation/survey questions, support for the GUI is not found in the provisional application of Khan; See Rosenberg Par [0137] which discloses receiving a pain level from a patent, such that the pain level may be obtained from the patient in response to a solicitation, such as a question, presented upon the patient interface; See Rosenberg Par [0115] & [0144] which discloses presenting information for the assistant to use in assisting the patient, such that the interface may present answers to questions or prompts from the patient and/or present help data to the patient), wherein the one or more questions inquire regarding one or more of:
social determinants of health for the patient (See Khan Par [0056]-[0058] which discloses obtaining and/or determining existing social determinants that rely on socio-economic data, such as by a machine learning model, i.e. a species of an artificial intelligence module; See Khan Par [0068] which specifically mentions receiving social determinant data relating to demographic, socioeconomic data, community data);
a personality of the patient (See Khan Par [0056] which discloses the need for providing and considering patient lifestyle information);
an attitude toward disease for the patient (See Khan Par [0177] which specifically mentions that in determining the patient’s willingness, the answers to one or more surveys may indicate whether the patient agrees or disagrees with the statements provided, i.e. attitude toward disease/health of the patient);
a willingness to modify behavior of the patient (See Khan Par [0062] which specifically states that a large language model can be used to identify and collect clinically-relevant information form patients, including ask for input via a survey to assess patient willingness; See Khan Par [0095]-[0098] which discloses a large language model generating prompts requesting input from the user, i.e. via user interface means, including responses to survey questions relating to the patient’s attitude about taking charge of their own treatment to determine a patient willingness metric, i.e. degree of compliance, and specifically mentions conducting a second or follow-up survey/prompts for obtaining additional information from the user, thereby generating a more comprehensive set of data for determining patient willingness);
a medical history of the patient (See Khan Par [0090] which discloses a risk score determination module being configured to process data including medical visit data, medical history, mental health conditions, medical device use, treatments, etc., all constituting a medical history for a patient); and
an education gap of the patient (While not “education gap” per se, see Khan Par [0068] & [0158] which discloses receiving data relating to education in use of developing a risk score, such that the risk score is used for determining care plans, etc., such that it is understood that an education gap would be present/indicated in receiving said education information, but support for this embodiment is not found in the provisional application of Khan and therefore does not constitute as prior art; however, it is understood by Examiner that this limitation is written in the alternative “one or more of”, and does not necessarily have to be met by Khan to read on this claim in its entirety since the other alternatives are effectively met).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the combined disclosure of Khan, Rosenberg, Lima, and White which already discloses conducting a survey and/or healthcare questionnaire to receive patient information from a patient to further include conduct a text conversation with the patient using a user interface (UI) to obtain a plurality of responses, as disclosed by Rosenberg, because this allows for communicating information to a patient and to receive prompts/feedback information from the patient (see Rosenberg Par [0115] & [0137]).
Response to Arguments
Applicant's arguments filed 01 April 2026 have been fully considered but they are not persuasive:
Regarding 35 U.S.C. 101 rejections of claims 1-20, Applicant argues on p. 11 of Arguments/Remarks that claim 1 is not directed to an abstract idea. More specifically, Applicant argues that the various recited steps in independent claim 1, such as provision, reception and storage of information by a computing device, and determination of various separate quantities by AI modules and machine learning software, which are not abstract ideas and cannot be performed solely in the human mind. Examiner respectfully disagrees with Applicant’s arguments. As established above in the “Claim Rejections – 35 U.S.C. 101” section of this Office Action, Examiner acknowledges steps that fall outside of being reasonably performed in the human mind and are therefore analyzed under later steps of the Alice/Mayo framework as additional elements. However, other steps found in the independent claim can be reasonably performed in the human mind, but recited for generic computer components, and therefore, in view of MPEP 2106.04(a)(2)(III)(C), still constitutes a mental process under broadest reasonable interpretation. Therefore, claims 1-20 and newly pending claims 21-26 remain rejected under 35 U.S.C. 101.
Regarding 35 U.S.C. 101 rejections of claims 1-20, Applicant argues on p. 11-12 of Arguments/Remarks that claim 1 is not directed to an abstract idea. More specifically, Applicant argues that claim 1 taken as a whole includes significantly more than the alleged abstract idea and integrates the claimed subject matter into a practical application. That is, Applicant argues that the claimed method steps are integrated into a practical application of combining different multimodal aspects of patient care and the combination of these separate aspects of patient care further utilizes expertise that is typically exercised by a plurality of types of professionals for diagnosing and treating a complex condition such as atrial fibrillation (AF). Examiner respectfully disagrees with Applicant’s arguments. As established above in the “Claim Rejections – 35 U.S.C. 101” section of this Office Action, each of the steps and claims were analyzed under step 2A, Prong 1 & 2 and step 2B, and each of the limitations represented either insignificant, extra-solution activity and/or well-understood, routine, and conventional activity in prior art systems. Furthermore, the specifically-argued aspects of combining different multimodal aspects of patient care and the combination of these separate aspects of patient care further utilizes expertise that is typically exercised by a plurality of types of professionals for diagnosing and treating a complex condition such as atrial fibrillation (AF) do not represent a technical improvement or significantly more under the Alice/Mayo framework. For instance, combining different multimodal aspects of patient care merely amounts to efforts of data gathering, analysis, and output regarding diagnosing one or more entities, and the aspect of diagnosing entities is an abstract one that can be performed reasonably in the human mind, and improvements to the abstraction alone cannot represent a practical application (See MPEP 2106.04(d)(III)). Therefore, claims 1-20 and newly pending claims 21-26 remain rejected under 35 U.S.C. 101.
Regarding 35 U.S.C. 103 rejections of claims 1-20, Applicant argues on p. 12-14 of Arguments/Remarks that Khan, Rosenberg, and Lima do not disclose the entirety of the newly amended independent claims at least by incorporating the limitations from previously pending dependent claims 2-3, 11, 14-15, & 17 which was met in their entirety by Khan, Rosenberg, Lima, and White. Furthermore, Applicant argues that while Khan generally discloses using a risk score determination module to determine an SDOH risk score, the SDOH risk score is not utilized in combination with a care schedule and a personality profile to determine an intervention profile. Applicant further argues against Rosenberg and Lima do not remedy the deficiencies of Khan, but does not argue over deficiencies of White. Examiner agrees with Applicant’s arguments. Therefore a new ground of rejection has been made under 35 U.S.C. 103 over Khan, Rosenberg, Lima, and White to read on the newly amended limitations incorporated into the independent claims from previously pending dependent claims 2-3, 11, 14-15, & 17. Therefore, while Rosenberg and Lima alone may not remedy the deficiencies of Khan, the combination of Khan, Rosenberg, Lima, and White effectively reads on the newly amended independent claims. Therefore, claims 1-20 and newly pending claims 21-26 remain rejected under 35 U.S.C. 103.
Regarding 35 U.S.C. 103 rejections of claims 1-20, Applicant argues on p. 14 of Arguments/Remarks that claims 13 & 19 which have limitations similar to amended claim should are also purportedly patentably-distinct and non-obvious over the cited art for the same or similar reasons to independent claim 1, and are therefore allowable. Applicant further argues that dependent claims are also allowable for the same or similar reasons, and by virtue of dependency from independent claims 1, 13, & 19. Examiner respectfully disagrees with Applicant’s arguments. As established in the arguments above, a new ground of rejection has been made under 35 U.S.C. 103 over Khan, Rosenberg, Lima, and White to read on the newly amended limitations incorporated into the independent claims from previously pending dependent claims 2-3, 11, 14-15, & 17. As such, Applicant’s arguments regarding independent claim 1 being patentably-distinct and non-obvious over the cited art are rendered moot. Therefore, claims 1-20 and newly pending claims 21-26 remain rejected under 35 U.S.C. 103.
Conclusion
The prior art made of record and not relied upon is considered pertinent to Applicant's disclosure:
Shriberg et al. (U.S. Patent Publication No. 2024/0170109) discloses a system for assessing a mental state of a subject in a single session or over multiple different sessions, using for example an automated module to present one or more target mental states to be assessed and/or performing one or more diagnoses;
Derrick, Jr. et al. (U.S. Patent Publication No. 2021/0319887) discloses a system for automatically diagnosing a medical condition, i.e. diabetes, based on various aspects of the patient including social determinants of health, patterns of life, lifestyle of the person, health of the person, etc.
Applicant's amendment necessitated the new ground of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HUNTER J RASNIC whose telephone number is (571)270-5801. The examiner can normally be reached M-F 8am-5:30pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shahid Merchant can be reached at (571) 270-1360. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/H.R./Examiner, Art Unit 3684
/KENNETH BARTLEY/Primary Examiner, Art Unit 3684
Prosecution Insights