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 .
Status of Claims
This office action for the 18/680586 application is in response to the communications filed February 02, 2026.
Claims 1-4, 7, 10, 11, 16-20, were amended February 02, 2026.
Claims 1-20 are currently pending and considered below.
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 1-20 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.
As per claim 1,
Step 1: The claim recites subject matter within a statutory category as a process.
Step 2A is a two-prong inquiry, in which Prong 1 determines whether a claim recites a judicial exception. Prong 2 determines if the additional limitations of the claim integrates the recited judicial exception into a practical application. If the additional elements of the claim fail to integrate the judicial exception into a practical application, claim is directed to the recited judicial exception, see MPEP 2106.04(II)(A).
Step 2A Prong 1: The claim contains subject matter that recites an abstract idea, with the steps of a method comprising: receiving a transcript representing a clinical encounter between a patient and a clinician; analyzing the transcript to generate a preliminary post patient encounter document that includes patient information and information about the clinical encounter, generated preliminary patient encounter document with a first formatting, wherein the first formatting is based on a confidence score, and in response to a first user input: generated preliminary patient encounter document with a second formatting, generated preliminary patient encounter document with a third formatting; detecting a second user input corresponding to the first portion of the automatically generated preliminary post patient encounter document and in response to detecting the second user input, generating training data based on the second user input and the first portion. These steps, as drafted, under the broadest reasonable interpretation recite:
certain methods of organizing human activity (e.g., fundamental economic principles or practices including: hedging; insurance; mitigating risk; etc., commercial or legal interactions including: agreements in the form of contracts; legal obligations; advertising, marketing or sales activities or behaviors; business relations; etc., managing personal behavior or relationships or interactions between people including: social activities; teaching; following rules or instructions; etc.) 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 being directed to certain methods of organizing human activity. The identified abstract idea, law of nature, or natural phenomenon identified above, in the context of this claim, encompasses a certain method of organizing human activity, namely managing personal behavior or relationships or interactions between people. This is because each of the limitations of the abstract idea recites a list of rules or instructions that a human person can follow in the course of their personal behavior. If a claim limitation, under its broadest reasonable interpretation, covers at least the recited methods of organizing human activity above, but for the recitation of generic computer components, then it falls within the “Certain Methods of Organizing Human Activity” grouping of abstract ideas. Accordingly, the claim recites an abstract idea. See MPEP 2106.04(a).
Step 2A Prong 2: The claim does not recite additional elements that integrate the judicial exception 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, see MPEP 2106.05(f), such as:
“using a generative machine learning model” and “automatically” which corresponds to merely using a computer as a tool to perform an abstract idea. Paragraph [0019] of the as-filed specification describes that the hardware that implements the steps of the abstract idea amounts to a generic computer. Implementing an abstract idea on a generic computer, does not integrate the abstract idea into a practical application in Step 2A Prong Two or add significantly more in Step 2B, similar to how the recitation of the computer in the claim in Alice amounted to mere instructions to apply the abstract idea of intermediated settlement on a generic computer. The Examiner notes that Paragraph [0076] of the as-filed specification describes that “instructions 810 transform the general, non-programmed machine 800 into a particular machine 800 programmed to carry out the described and illustrated functions in the manner described”. This usage of the term “particular machine” is not consistent with how this term is used in the MPEP. All computers use software for its hardware to execute instructions. The definition provided by the as-filed specification would necessarily make all computers a particular machine regardless of the generic nature of the hardware that executes the software. The particularity or generality of the elements of the machine or apparatus, i.e., the degree to which the machine in the claim can be specifically identified (not any and all machines). See MPEP 2106.05(b).
add insignificant extra-solution activity to the abstract idea, see MPEP 2106.05(g), such as:
“generating, for display to the clinician, a graphical user interface (GUI); displaying the GUI, wherein the GUI includes displaying the automatically generated preliminary post patient encounter document.”, “displaying a first portion of the”, “displaying a second portion of the”, “displaying a third portion of the” which corresponds to mere data gathering and/or output.
Accordingly, this claim is directed to an abstract idea.
Step 2B: The claim does not recite additional elements that 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/or generally link the abstract idea to a particular technological environment or field of use. Additionally, the additional limitations, identified as insignificant extra-solution activity to the abstract idea, 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:
computer functions that have been identified by the courts as well‐understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity, see MPEP 2106.05(d)(II), such as:
“generating, for display to the clinician, a graphical user interface (GUI); displaying the GUI, wherein the GUI includes displaying the automatically generated preliminary post patient encounter document.”, “displaying a first portion of the”, “displaying a second portion of the”, “displaying a third portion of the” which corresponds to receiving or transmitting data over a network.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 2,
Claim 2 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 2 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the preliminary post patient encounter document includes a subjective objective assessment plan (SOAP) note, a problem, intervention, and evaluation (PIE) note, a data, assessment, and plan (DAP) note, a behavior, intervention, response, and plan (BIRP) note, a follow-up, outcomes, care, upcoming visits, and symptoms (FOCUS) note, or a chief complaint, history, assessment, treatment, and test results (CHART) note, or an intervention, assessment, and plan (IAP) note.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 3,
Claim 3 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 3 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the clinical encounter includes a virtual office visit, and the clinician includes a physician or therapist.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 4,
Claim 4 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 4 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the patient information includes an electronic health record, past claims information for the patient, patient health information, past medical recommendations, past treatment recommendations, patient demographic information, prior bloodwork results, prior results of non-bloodwork tests, medical history, medical provider notes in the electronic health record, intake forms completed by the patient, patient in-network insurance coverage, patient out-of-network insurance coverage, patient location, or one or more treatment preferences.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 5,
Claim 5 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 5 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“receiving input from the clinician selecting data from the plurality of fields; and populating a final post patient encounter document in response to receiving the input.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“further comprising: presenting in the GUI a plurality of fields of the automatically generated preliminary post patient encounter document;” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to mere data gathering and/or output and receiving or transmitting data over a network.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 6,
Claim 6 depends from claim 5 and inherits all the limitations of the claim from which it depends. Claim 6 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: receiving a selection of an accept option associated with a first field of the plurality of fields; and …transferring data from the first field to a corresponding field of the final post patient encounter document in response to receiving the selection.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“automatically” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 7,
Claim 7 depends from claim 6 and inherits all the limitations of the claim from which it depends. Claim 7 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: receiving a selection of a rejection option associated with a first field of the plurality of fields; identifying a corresponding field of the final post patient encounter document corresponding to the first field in response to receiving the selection; and generating training data including a difference between data in the corresponding field and data in the first field.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 8,
Claim 8 depends from claim 7 and inherits all the limitations of the claim from which it depends. Claim 8 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: generating a tracking report indicating which fields of the plurality of fields have been accepted and which fields of the plurality of fields have been rejected.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 9,
Claim 9 depends from claim 8 and inherits all the limitations of the claim from which it depends. Claim 9 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising updating the generative machine learning model based on the tracking report.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 10,
Claim 10 depends from claim 9 and inherits all the limitations of the claim from which it depends. Claim 10 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the tracking report represents an acceptance rate of the plurality of fields across multiple automatically generated preliminary post patient encounter documents representing multiple clinical encounters, further comprising: measuring an acceptance rate associated with respective fields of the multiple automatically generated preliminary post patient encounter documents; determining that the acceptance rate fails to transgress a threshold;” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“triggering updating the generative machine learning model based on the tracking report in response to determining that the acceptance rate fails to transgress the threshold.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 11,
Claim 11 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 11 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the automatically generated preliminary post patient encounter document includes a JSON file.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 12,
Claim 12 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 12 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“generating an audio recording of the clinical encounter conducted in the established virtual visit; and processing the audio recording by a machine learning model to generate the transcript.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
“further comprising: establishing a virtual visit for conducting the clinical encounter between the clinician and the patient;” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to mere data gathering and/or output and receiving or transmitting data over a network.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 13,
Claim 13 depends from claim 12 and inherits all the limitations of the claim from which it depends. Claim 13 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: generating one or more prompts for generating the preliminary post patient encounter document;” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
“providing the one or more prompts and the transcript to the generative machine learning model to automatically generate the preliminary post patient encounter document.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 14,
Claim 14 depends from claim 13 and inherits all the limitations of the claim from which it depends. Claim 14 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising: receiving permission from the patient approving the generating of the audio recording and the analyzing of the transcript by the generative machine learning model.” further describes the abstract idea. This claim limitation is still directed to “Certain Methods of Organizing Human Activity” and therefore continues to recite an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 15,
Claim 15 depends from claim 13 and inherits all the limitations of the claim from which it depends. Claim 15 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the virtual visit is established by a first server, wherein the transcript is encrypted before being provided to the generative machine learning model, and wherein the generative machine learning model is accessed by a second server after conducting authentication between the first server and the second server.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to mere data gathering and/or output and receiving or transmitting data over a network.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 16,
Claim 16 depends from claim 1 and inherits all the limitations of the claim from which it depends. Claim 16 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“wherein the generative machine learning model includes a large language model (LLM), and wherein the generative machine learning model is trained to establish a relationship between patterns of a plurality of clinical encounter transcripts and patterns of post patient encounter documents.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 17,
Claim 17 depends from claim 16 and inherits all the limitations of the claim from which it depends. Claim 17 merely further defines the abstract idea and/or introduces additional elements that are insufficient to provide a practical application or something significantly more:
“further comprising training the LLM by performing training operations including: obtaining a batch of training data comprising a first set of the patterns of the plurality of clinical encounter transcripts; processing the first set of the patterns of the plurality of clinical encounter transcripts by the LLM to generate an estimated set of post patient encounter documents; computing a loss based on a deviation between the estimated set of post patient encounter documents and the patterns of post patient encounter documents associated with the first set of the patterns of the plurality of clinical encounter transcripts; and updating one or more parameters of the LLM based on the computed loss.” further defines an additional element that was insufficient to provide a practical application and/or significantly more. The claim with this further defining limitation still corresponds to merely using a computer as a tool to perform an abstract idea.
Looking at the limitations of the claim 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 recite an abstract idea and/or provide conventional computer implementation which does not impose a meaningful limit to integrate the abstract idea into a practical application and/or amount to no more than limitations which amount to elements that have been recognized as well-understood, routine, and conventional activity in particular fields.
As per claim 18,
Claim 18 is substantially similar to claim 1. Accordingly, claim 18 is rejected for the same reasons as claim 1.
As per claim 19,
Claim 19 is substantially similar to claim 2. Accordingly, claim 19 is rejected for the same reasons as claim 2.
As per claim 20,
Claim 20 is substantially similar to claim 1. Accordingly, claim 20 is rejected for the same reasons as claim 1.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1-6, 12-14 and 18-20 are rejected under 35 U.S.C. 102(a)(2) as being anticipated by Koll et al. (US 2018/0240538; herein referred to as Koll).
As per claim 1,
Koll discloses a method comprising: receiving a transcript representing a clinical encounter between a patient and a clinician; analyzing the transcript using a generative machine learning model to automatically generate a preliminary post patient encounter document that comprises patient information and information about the clinical encounter; and generating, for display to the clinician, a graphical user interface (GUI); displaying the GUI, wherein displaying the GUI includes displaying the automatically generated preliminary post patient encounter document:
(Paragraphs [0003], [0025]-[0040] and [0113] of Koll. The teaching describes a computerized system processes the speech of a physician and a patient during a patient encounter to automatically produce a draft clinical report which documents the patient encounter. The draft clinical report includes information that has been abstracted from the speech of the physician and patient. The draft report is provided to a scribe or to the physician for review. Producing the draft clinical report automatically, rather than requiring the physician to prepare the draft clinical report manually, significantly reduces the time required by the physician to produce the final version of the clinical report. The abstraction process summarize certain information in the care dialog if that information is relevant to the requirements of the clinical report but not necessary to include in its entirety in the clinical report. For example, consider the following portion of a care dialog: Dr.: Um, so have you had a fever at all? Patient: I don't think so. Sometimes I feel probably a little bit above my regular temperature, but I haven't had things like chills or . . . Dr.: Ok, so no chills, are you taking your temperature at home? Patient: Uh, no I didn't, but I have felt a little tired . . . . Dr.: OK. The abstraction process described herein may summarize the portion of the care dialog above as, for example, “Denies fevers, chills. Does not check temperatures. Feels fatigued.” Documentation alerts may include displaying visible alerts notifying the scribe 302 of documentation guidelines and best practices, information that is missing and/or inconsistent in the draft clinical report 150, and reminders, or, generally, of a portion of the draft clinical report that requires additional modification. The system 300 may display such alerts to the scribe 302, and may display a subset of those alerts (e.g., any alerts that the scribe 302 could not resolve and that are relevant to the physician 102 a) to the physician 102 a when the augmented draft clinical report 350 is displayed to the physician 102 a.)
Koll further discloses displaying a first portion of the automatically generated preliminary patient encounter document with a first formatting, wherein the first formatting is based on a confidence score:
(Paragraphs [0101] and [0102] of Koll. The teaching describes that the statement generation module 304 and the statement modification module 310 may be integrated into a single module. Furthermore, these modules 304 and 310 may perform functions in addition to those disclosed above, such as any one or more of the following, in any combination: (1) template suggestion, (2) predictive typing, and (3) documentation alerts. Template suggestion may, for example, include suggesting that a particular document template or sub-template [first formatting of a first portion of the document] be used for or within the draft clinical report 150. For example, if the physician 102 a begins to discuss a finding, the system 300 may automatically identify and suggest inclusion of a template for that finding in the draft clinical report 150. Sub-templates for documentation of a procedure (e.g., an EKG) may be annotated with the procedure code (e.g., CPT code) identifying the procedure. If the natural language understanding system that processes the partially written report 150 detects an indication that a procedure is likely to be documented [formatting based on confidence score], or that the partial report 150 contains a (partial) free-form text documentation of a procedure for which a template would be available, then the system 300 may suggest the use of the respective template. Similarly, if the care dialog between the physician 102 a and patient 102 b contains an indication of a procedure, then the system 300 may suggest using the template associated with that procedure.)
Koll further discloses in response to receiving a first user input: displaying a second portion of the automatically generated preliminary patient encounter document with a second formatting:
(Paragraphs [0103]-[0105] of Koll. The teaching describes that predictive typing may, for example, include: (1) completing (or suggesting completion of) words and/or sentences in the draft clinical report [first input] 150 based on the textual context in the draft clinical report 150 and the outputs of the signal processing module 114 and dialog mapping module 118; and (2) suggesting alternative text snippet candidates (e.g., sentences and/or paragraphs) from which the scribe 302 can select for inclusion in the draft clinical report [second portion in second formatting], where such suggestions may be made based on the textual context in the draft clinical report 150 and the outputs of the signal processing module 114 and dialog mapping module 118 (3) It may also include autocorrect and spell-checking functionality. Conventional predictive typing may use statistical models of written and/or spoken language to predict the most likely word or word sequences, given a textual left and/or right context of the words to be predicted. Embodiments of the present invention address this limitation of conventional predictive typing by modeling the distribution of medical language conditioned on a representation of the care dialog between the patient 102 a and the physician 102 b. In particular, rather than modeling the likelihood of a word W_n given a word context (typically the preceding words W_n−1, . . . , W_1) and domain D as P(W_n|W_n−1, . . . , W_1, D), embodiments of the present invention model the same conditioned additionally on a representation of the output of the care dialog (e.g., the state of the draft clinical report 150 and/or augmented draft clinical report 350) at any given point in time C(t) as P(W_n|W_n−1, . . . , W_1, D, C(t)).)
Koll further discloses displaying a third portion of the automatically generated preliminary patient encounter document with a third formatting:
(Paragraph [0113] of Koll. The teaching describes that documentation alerts may [third portion in third formatting] include displaying visible alerts notifying the scribe 302 of documentation guidelines and best practices, information that is missing and/or inconsistent in the draft clinical report 150, and reminders, or, generally, of a portion of the draft clinical report that requires additional modification. For example, if the scribe 302 is documenting an EKG procedure, the system 300 may remind the scribe 302 that the documentation for an EKG procedure must minimally contain information on at least any three of the following six elements: (1) the rhythm or rate; (2) axis; (3) intervals; (4) segments; (5) notation of a comparison with a prior EKG if one was available to the physician 102 a; and (6) a summary of the patient 102 b's clinical condition. The system 300 may track the progress of the draft clinical report 150 and remove such a reminder when the system 300 determines that the draft clinical report 150 satisfies the minimum requirements. The system 300 may display such alerts to the scribe 302, and may display a subset of those alerts (e.g., any alerts that the scribe 302 could not resolve and that are relevant to the physician 102 a) to the physician 102 a when the augmented draft clinical report 350 is displayed to the physician 102 a. As a further example of such alerts, the system 300 may display individual reminders or a plurality of reminders, including, for example, a plurality of reminders that form a “to-do” list.)
Koll further discloses detecting a second user input corresponding to the first portion of the automatically generated preliminary post patient encounter document; and in response to detecting the second user input, generating training data based on the second user input and the first portion:
(Paragraphs [0101]-[0105] of Koll. The teaching describes that the statement generation module 304 and the statement modification module 310 may be integrated into a single module. Furthermore, these modules 304 and 310 may perform functions in addition to those disclosed above, such as any one or more of the following, in any combination: (1) template suggestion, (2) predictive typing, and (3) documentation alerts. Template suggestion may, for example, include suggesting that a particular document template or sub-template. predictive typing may, for example, include: (1) completing (or suggesting completion of) words and/or sentences in the draft clinical report 150 based on the textual context in the draft clinical report 150 and the outputs of the signal processing module 114 and dialog mapping module 118; and (2) suggesting alternative text snippet candidates (e.g., sentences and/or paragraphs) from which the scribe 302 can select for inclusion in the draft clinical report, where such suggestions may be made based on the textual context in the draft clinical report 150 and the outputs of the signal processing module 114 and dialog mapping module 118 (3) It may also include autocorrect and spell-checking functionality. Embodiments of the present invention address this limitation of conventional predictive typing by modeling the distribution of medical language conditioned on a representation of the care dialog between the patient 102 a and the physician 102 b. In particular, rather than modeling the likelihood of a word W_n given a word context (typically the preceding words W_n−1, . . . , W_1) and domain D as P(W_n|W_n−1, . . . , W_1, D), embodiments of the present invention model the same conditioned additionally on a representation of the output of the care dialog (e.g., the state of the draft clinical report 150 and/or augmented draft clinical report 350) at any given point in time C(t) as P(W_n|W_n−1, . . . , W_1, D, C(t)). This means that the predictive model for predictive text in the template selected is conditioned based on the inputs that users give.)
As per claim 2,
Koll discloses the limitations of claim 1.
Koll further discloses wherein the preliminary post patient encounter document includes a subjective objective assessment plan (SOAP) note, a problem, intervention, and evaluation (PIE) note, a data, assessment, and plan (DAP) note, a behavior, intervention, response, and plan (BIRP) note, a follow-up, outcomes, care, upcoming visits, and symptoms (FOCUS) note, or a chief complaint, history, assessment, treatment, and test results (CHART) note, or an intervention, assessment, and plan (IAP) note:
(Paragraphs [0011]-[0040] of Koll. The teaching describes that a physician typically discusses, with the patient, the reason for the visit, any changes in the patient's health conditions, medications, etc. e.g. “I'm a little concerned because in a couple weeks I have a wedding and I need to be ready by then.” [subjective client feelings and self reports], examines the patient [objective observable data], discusses the physician’s findings with the patient [assessment with clinical analysis] and creates a clinical report of the patient encounter, containing information such as the care provided to the patient and the physician's treatment plan [plan with a treatment strategy]. Usually the physician would undertake this report manually, though with the provided invention the report generation from the transcript of this encounter would be generated automatically. This means that the preliminary post patient encounter document, the draft, would contain this information amounting to a SOAP note.)
As per claim 3,
Koll discloses the limitations of claim 1.
Koll further discloses wherein the clinical encounter includes a virtual office visit, and the clinician includes a physician or therapist:
(Paragraph [0043] of Koll. The teaching describes that the physician 102 a and patient 102 b may instead, for example, be located remotely from each other (e.g., in different rooms, buildings, cities, or countries) and communicate with each other by telephone/videoconference and/or over the Internet or other network.)
As per claim 4,
Koll discloses the limitations of claim 1.
Koll further discloses wherein the patient information includes an electronic health record, past claims information for the patient, patient health information, past medical recommendations, past treatment recommendations, patient demographic information, prior bloodwork results, prior results of non-bloodwork tests, medical history, medical provider notes in the electronic health record, intake forms completed by the patient, patient in-network insurance coverage, patient out-of-network insurance coverage, patient location, or one or more treatment preferences:
(Paragraph [0044] of Koll. The teaching describes that system 100 also includes an encounter context identification module 110, which identifies and/or generates encounter context data 112 representing properties of the physician-patient encounter (FIG. 2, operation 202). The encounter context identification module 110 may, for example, generate the encounter context data 112 based on information received from the physician 102 a and/or the patient 102 b or an EMR.)
As per claim 5,
Koll discloses the limitations of claim 1.
Koll further discloses further comprising: presenting in the GUI a plurality of fields of the automatically generated preliminary post patient encounter document; receiving input from the clinician selecting data from the plurality of fields; and populating a final post patient encounter document in response to receiving the input:
(Paragraphs [0003], [0085] and [0091]-[0097] of Koll. The teaching describes that the draft report is provided to a scribe or to the physician for review. This means that the tools the scribes use are also the tools physicians are able to use as well. Regarding the draft clinical report incorporating representations of data included in the transcript, and as shown in the example of FIG. 3, the system 300 uses the techniques of FIGS. 2A-B to produce the draft clinical report 150. The statement modification module 310 may generate and proposes, to the scribe 302, based on the draft clinical report 150, one or more modifications 312 to be made to existing statements in the draft clinical report 150 (FIG. 4, operation 410). The scribe 302 may provide, to the statement modification module 310, input 314 indicating approval or rejection of the proposed modifications 312 (FIG. 4, operation 412). Suggested edits to the draft clinical report 150 (e.g. the proposed statements 306 and the proposed modifications 312) may, for example, include: (1) proposed text to be added/modified in the draft clinical report 150; and (2) a location in the draft clinical report 150 where the edit is proposed to be made. Proposed text to be added or modified may include data to be added one or more fields in a database (e.g., in an electronic medical record). Proposed text to be added or modified may include one or more additions or modifications to be made to a user interface element, such as adding a check to a check box or filling a radio button element. Proposed text to be added or modified may include text to be inserted into a document template.)
As per claim 6,
Koll discloses the limitations of claim 5.
Koll further discloses further comprising: receiving a selection of an accept option associated with a first field of the plurality of fields; and automatically transferring data from the first field to a corresponding field of the final post patient encounter document in response to receiving the selection:
(Paragraphs [0003], [0085] and [0091]-[0097] of Koll. The teaching describes that the draft report is provided to a scribe or to the physician for review. This means that the tools the scribes use are also the tools physicians are able to use as well. Regarding the draft clinical report incorporating representations of data included in the transcript, and as shown in the example of FIG. 3, the system 300 uses the techniques of FIGS. 2A-B to produce the draft clinical report 150. The statement modification module 310 may generate and proposes, to the scribe 302, based on the draft clinical report 150, one or more modifications 312 to be made to existing statements in the draft clinical report 150 (FIG. 4, operation 410). The scribe 302 may provide, to the statement modification module 310, input 314 indicating approval or rejection of the proposed modifications 312 (FIG. 4, operation 412). Suggested edits to the draft clinical report 150 (e.g. the proposed statements 306 and the proposed modifications 312) may, for example, include: (1) proposed text to be added/modified in the draft clinical report 150; and (2) a location in the draft clinical report 150 where the edit is proposed to be made. Proposed text to be added or modified may include data to be added one or more fields in a database (e.g., in an electronic medical record). Proposed text to be added or modified may include one or more additions or modifications to be made to a user interface element, such as adding a check to a check box or filling a radio button element. Proposed text to be added or modified may include text to be inserted into a document template.)
As per claim 12,
Koll discloses the limitations of claim 1.
Koll further discloses further comprising: establishing a virtual visit for conducting the clinical encounter between the clinician and the patient; generating an audio recording of the clinical encounter conducted in the established virtual visit; and processing the audio recording by a machine learning model to generate the transcript:
(Paragraphs [0043], [0060]-[0069] and [0079] of Koll. The teaching describes that the physician 102 a and patient 102 b may, but need not, be in the same room as each other or otherwise in physical proximity to each other. The physician 102 a and patient 102 b may instead, for example, be located remotely from each other (e.g., in different rooms, buildings, cities, or countries) and communicate with each other by telephone/videoconference and/or over the Internet or other network. The system 100 includes an audio capture device 106, which captures the physician's speech 104 a and the patient's speech 104 b, thereby producing audio output 108 (FIG. 2, operation 204). The audio capture device 106 may, for example, be one or more microphones, such as distinct microphones spoken into by the physician 102 a and the patient 102 b. The system 100 also includes a dialog mapping module 118 (which may be integrated with the signal processing module 114), which maps segments of the physician and patient speech 116 a and 116 b to appropriate representations in the clinical report 150 (FIG. 2, operation 212). In some embodiments, a statement generation module 304 and a statement modification module 310. The system 100 may also include a draft verification module 152, which may provide the clinical report 150 to the physician 102 a (or to a scribe) for review, verification, and completion (FIG. 2, operation 214). The physician 102 a (or scribe) may then review the report and edit it as desired before submitting it as a complete clinical report. As will be described in greater detail below in connection with FIG. 3, the system may leverage machine translation and/or natural language processing to map a portion of the transcript.)
As per claim 13,
Koll discloses the limitations of claim 12.
Koll further discloses further comprising: generating one or more prompts for generating the preliminary post patient encounter document; and providing the one or more prompts and the transcript to the generative machine learning model to automatically generate the preliminary post patient encounter document:
(Paragraph [0079] of Koll. The teaching describes that the system may leverage machine translation and/or natural language processing to map a portion of the transcript. For example, a statement made by one of the speakers in the encounter may be mapped to a representative form by applying machine learning techniques to a statement (such as “you really should stop smoking”) to identify keywords or concepts (e.g., “stop smoking” or “smoking cessation”) and use those keywords or concepts to identify, in a data structure, a statement mapped to the keywords or concepts or mapped directly to the text of one or more statements as transcribed (e.g., “stop smoking” may be mapped to “I recommended to the patient to stop smoking”). The system may also generate text from discrete coding of information; for example, the system may extract observations from the transcript of captured speech for use in modifying, or proposing a modification to, a “review of systems” section of the draft clinical report 150; for example, the system may identify an observation such as a blood pressure result, a pulse, a weight, a lung examination observation or other observation and determine that a data structure maps the observation to a narrative for use in the draft clinical report 150. The system may also implement natural language generation techniques to generate text representative of information in the transcript, for insertion into the draft clinical report 150.)
As per claim 14,
The method of claim 13.
Koll further discloses further comprising: receiving permission from the patient approving the generating of the audio recording and the analyzing of the transcript by the generative machine learning model:
(Paragraphs [0043], [0060]-[0069] and [0079] of Koll. The teaching describes that the physician 102 a and patient 102 b may, but need not, be in the same room as each other or otherwise in physical proximity to each other. The physician 102 a and patient 102 b may instead, for example, be located remotely from each other (e.g., in different rooms, buildings, cities, or countries) and communicate with each other by telephone/videoconference and/or over the Internet or other network. The system 100 includes an audio capture device 106, which captures the physician's speech 104 a and the patient's speech 104 b, thereby producing audio output 108 (FIG. 2, operation 204). The audio capture device 106 may, for example, be one or more microphones, such as distinct microphones spoken into by the physician 102 a and the patient 102 b. The system 100 also includes a dialog mapping module 118 (which may be integrated with the signal processing module 114), which maps segments of the physician and patient speech 116 a and 116 b to appropriate representations in the clinical report 150 (FIG. 2, operation 212). In some embodiments, a statement generation module 304 and a statement modification module 310. The system 100 may also include a draft verification module 152, which may provide the clinical report 150 to the physician 102 a (or to a scribe) for review, verification, and completion (FIG. 2, operation 214). The physician 102 a (or scribe) may then review the report and edit it as desired before submitting it as a complete clinical report. As will be described in greater detail below in connection with FIG. 3, the system may leverage machine translation and/or natural language processing to map a portion of the transcript. It is construed by the Examiner that the act of being present in a teleconference is an indication of approval for the generation of audio recording and medical report generation methods. This would include the recording of the patient’s audio to transmit back to the physician, otherwise communication would be impossible, and the use of generative methods in a patient summary report as patients generally receive after visit summaries.)
As per claim 18,
Claim 18 is substantially similar to claim 1. Accordingly, claim 18 is rejected for the same reasons as claim 1.
As per claim 19,
Claim 19 is substantially similar to claim 2. Accordingly, claim 19 is rejected for the same reasons as claim 2.
As per claim 20,
Claim 20 is substantially similar to claim 1. Accordingly, claim 20 is rejected for the same reasons as claim 1.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claims 7-10 are rejected under 35 U.S.C. 103 as being unpatentable over Koll in view of Vozila et al. (US 2019/0272895; herein referred to as Vozila).
As per claim 7,
Koll discloses the limitations of claim 6.
Koll further discloses further comprising: receiving a selection of a rejection option associated with a first field of the plurality of fields; identifying a corresponding field of the final post patient encounter document corresponding to the first field in response to receiving the selection:
(Paragraphs [0003], [0085] and [0091]-[0097] of Koll. The teaching describes that the draft report is provided to a scribe or to the physician for review. This means that the tools the scribes use are also the tools physicians are able to use as well. Regarding the draft clinical report incorporating representations of data included in the transcript, and as shown in the example of FIG. 3, the system 300 uses the techniques of FIGS. 2A-B to produce the draft clinical report 150. The statement modification module 310 may generate and proposes, to the scribe 302, based on the draft clinical report 150, one or more modifications 312 to be made to existing statements in the draft clinical report 150 (FIG. 4, operation 410). The scribe 302 may provide, to the statement modification module 310, input 314 indicating approval or rejection of the proposed modifications 312 (FIG. 4, operation 412). Suggested edits to the draft clinical report 150 (e.g. the proposed statements 306 and the proposed modifications 312) may, for example, include: (1) proposed text to be added/modified in the draft clinical report 150; and (2) a location in the draft clinical report 150 where the edit is proposed to be made. Proposed text to be added or modified may include data to be added one or more fields in a database (e.g., in an electronic medical record). Proposed text to be added or modified may include one or more additions or modifications to be made to a user interface element, such as adding a check to a check box or filling a radio button element. Proposed text to be added or modified may include text to be inserted into a document template.)
Koll does not explicitly teach generating training data including a difference between data in the corresponding field and data in the first field.
However, Vozila teaches generating training data including a difference between data in a corresponding field and data in a first field:
(Paragraph [0084] of Vozila. The teaching describes that the automated clinical documentation process 10 may update 410 an output of the user interface based upon, at least in part, one or more modifications made at least one layer of the plurality of layers. For instance, rather than the output being static during the editing process, ACD process 10 may update 410 the output based on the modifications made by the editor so far (e.g., based on the decoder being autoregressive in nature). In particular, the decoder (e.g., sequence to sequence decoder) output may depend on its preceding output. As such, if the scribe (or other user) makes a correction in one part of the draft report, ACD process 10 may update a best guess at the subsequent content. In some implementations, this may be distracting to the user, and so to make it less distracting, it may be optionally limited to a toggle-able mode (e.g., online/synchronous vs. global review mode) and/or limited to only modifying the draft output for subsequent sections of the report. In some implementations, there may be at least four ways that corrections to case-record-persistent system outputs (e.g., medical reports, structured data) may be utilized. For example, pairs of ASR transcripts and corrected reports may be used for offline (sequence to sequence, transcript->report) model training. If in the typing acceleration mode as opposed to draft-report-correction mode, as the user types, the prediction for next sentence may be updated, which may not be model training/adaptation, but rather a reflection of the (auto-regressive) model predicting next output based on report content so far. If in the draft-report-correction mode, as the user makes corrections, prediction of subsequent content (sentences or perhaps less distracting, sections) and thus the draft report content (in this report) may be updated, again utilizing the same auto-regressive nature of the sequence to sequence model (and not some result of model training). Tuples of ASR transcripts (along with ASR confidence information), draft reports and noted user edits (e.g., corrections) may be used for an offline confidence model (e.g., required number of edits) training.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the automated report generation techniques of Koll, the automated report generation techniques of Vozila. Paragraph [0081] of Vozila teaches that for draft reports/sections that ACD process 10 may actually expose to be edited (rather than typed from scratch), ACD process 10 may collect the number of edits made and time required to make them, which may be added to training and improvement of the confidence model over time. One of ordinary skill in the art in possession of Koll would have looked to Vozila because of this incentive in addition to both being in the same field of endeavor. One of ordinary skill in the art would have added to the teaching of Koll, the teaching of Vozila based on this incentive without yielding unexpected results.
As per claim 8,
The combined teaching of Koll and Vozila teaches the limitations of claim 7.
The combined teaching of Koll and Vozila further teaches further comprising: generating a tracking report indicating which fields of the plurality of fields have been accepted and which fields of the plurality of fields have been rejected:
(Paragraphs [0003], [0085] and [0091]-[0097] of Koll. The teaching describes that the draft report is provided to a scribe or to the physician for review. This means that the tools the scribes use are also the tools physicians are able to use as well. Regarding the draft clinical report incorporating representations of data included in the transcript, and as shown in the example of FIG. 3, the system 300 uses the techniques of FIGS. 2A-B to produce the draft clinical report 150. The statement modification module 310 may generate and proposes, to the scribe 302, based on the draft clinical report 150, one or more modifications 312 to be made to existing statements in the draft clinical report 150 (FIG. 4, operation 410). The scribe 302 may provide, to the statement modification module 310, input 314 indicating approval or rejection of the proposed modifications 312 (FIG. 4, operation 412). Suggested edits to the draft clinical report 150 (e.g. the proposed statements 306 and the proposed modifications 312) may, for example, include: (1) proposed text to be added/modified in the draft clinical report 150; and (2) a location in the draft clinical report 150 where the edit is proposed to be made. Proposed text to be added or modified may include data to be added one or more fields in a database (e.g., in an electronic medical record). Proposed text to be added or modified may include one or more additions or modifications to be made to a user interface element, such as adding a check to a check box or filling a radio button element. Proposed text to be added or modified may include text to be inserted into a document template.)
(Paragraph [0084] of Vozila. The teaching describes that the automated clinical documentation process 10 may update 410 an output of the user interface based upon, at least in part, one or more modifications made at least one layer of the plurality of layers. For instance, rather than the output being static during the editing process, ACD process 10 may update 410 the output based on the modifications made by the editor so far (e.g., based on the decoder being autoregressive in nature). In particular, the decoder (e.g., sequence to sequence decoder) output may depend on its preceding output. As such, if the scribe (or other user) makes a correction in one part of the draft report, ACD process 10 may update a best guess at the subsequent content. In some implementations, this may be distracting to the user, and so to make it less distracting, it may be optionally limited to a toggle-able mode (e.g., online/synchronous vs. global review mode) and/or limited to only modifying the draft output for subsequent sections of the report. In some implementations, there may be at least four ways that corrections to case-record-persistent system outputs (e.g., medical reports, structured data) may be utilized. For example, pairs of ASR transcripts and corrected reports may be used for offline (sequence to sequence, transcript->report) model training. If in the typing acceleration mode as opposed to draft-report-correction mode, as the user types, the prediction for next sentence may be updated, which may not be model training/adaptation, but rather a reflection of the (auto-regressive) model predicting next output based on report content so far. If in the draft-report-correction mode, as the user makes corrections, prediction of subsequent content (sentences or perhaps less distracting, sections) and thus the draft report content (in this report) may be updated, again utilizing the same auto-regressive nature of the sequence to sequence model (and not some result of model training). Tuples of ASR transcripts (along with ASR confidence information), draft reports and noted user edits (e.g., corrections) may be used for an offline confidence model (e.g., required number of edits) training.)
Here the tracking report is the determination of the approval or rejection of the proposed modifications which is then used as a basis to update the machine learning model.
As per claim 9,
The combined teaching of Koll and Vozila teaches the limitations of claim 8.
The combined teaching of Koll and Vozila further teaches further comprising updating the generative machine learning model based on the tracking report:
(Paragraphs [0003], [0085] and [0091]-[0097] of Koll. The teaching describes that the draft report is provided to a scribe or to the physician for review. This means that the tools the scribes use are also the tools physicians are able to use as well. Regarding the draft clinical report incorporating representations of data included in the transcript, and as shown in the example of FIG. 3, the system 300 uses the techniques of FIGS. 2A-B to produce the draft clinical report 150. The statement modification module 310 may generate and proposes, to the scribe 302, based on the draft clinical report 150, one or more modifications 312 to be made to existing statements in the draft clinical report 150 (FIG. 4, operation 410). The scribe 302 may provide, to the statement modification module 310, input 314 indicating approval or rejection of the proposed modifications 312 (FIG. 4, operation 412). Suggested edits to the draft clinical report 150 (e.g. the proposed statements 306 and the proposed modifications 312) may, for example, include: (1) proposed text to be added/modified in the draft clinical report 150; and (2) a location in the draft clinical report 150 where the edit is proposed to be made. Proposed text to be added or modified may include data to be added one or more fields in a database (e.g., in an electronic medical record). Proposed text to be added or modified may include one or more additions or modifications to be made to a user interface element, such as adding a check to a check box or filling a radio button element. Proposed text to be added or modified may include text to be inserted into a document template.)
(Paragraph [0084] of Vozila. The teaching describes that the automated clinical documentation process 10 may update 410 an output of the user interface based upon, at least in part, one or more modifications made at least one layer of the plurality of layers. For instance, rather than the output being static during the editing process, ACD process 10 may update 410 the output based on the modifications made by the editor so far (e.g., based on the decoder being autoregressive in nature). In particular, the decoder (e.g., sequence to sequence decoder) output may depend on its preceding output. As such, if the scribe (or other user) makes a correction in one part of the draft report, ACD process 10 may update a best guess at the subsequent content. In some implementations, this may be distracting to the user, and so to make it less distracting, it may be optionally limited to a toggle-able mode (e.g., online/synchronous vs. global review mode) and/or limited to only modifying the draft output for subsequent sections of the report. In some implementations, there may be at least four ways that corrections to case-record-persistent system outputs (e.g., medical reports, structured data) may be utilized. For example, pairs of ASR transcripts and corrected reports may be used for offline (sequence to sequence, transcript->report) model training. If in the typing acceleration mode as opposed to draft-report-correction mode, as the user types, the prediction for next sentence may be updated, which may not be model training/adaptation, but rather a reflection of the (auto-regressive) model predicting next output based on report content so far. If in the draft-report-correction mode, as the user makes corrections, prediction of subsequent content (sentences or perhaps less distracting, sections) and thus the draft report content (in this report) may be updated, again utilizing the same auto-regressive nature of the sequence to sequence model (and not some result of model training). Tuples of ASR transcripts (along with ASR confidence information), draft reports and noted user edits (e.g., corrections) may be used for an offline confidence model (e.g., required number of edits) training.)
Here the tracking report is the determination of the approval or rejection of the proposed modifications which is then used as a basis to update the machine learning model.
As per claim 10,
The combined teaching of Koll and Vozila teaches the limitations of claim 9.
The combined teaching of Koll and Vozila further teaches wherein the tracking report represents an acceptance rate of the plurality of fields across multiple automatically generated preliminary post patient encounter documents representing multiple clinical encounters, further comprising: measuring an acceptance rate associated with respective fields of the multiple automatically generated preliminary post patient encounter documents; determining that the acceptance rate fails to transgress a threshold; and triggering updating the generative machine learning model based on the tracking report in response to determining that the acceptance rate fails to transgress the threshold:
(Paragraphs [0003], [0085] and [0091]-[0097] of Koll. The teaching describes that the draft report is provided to a scribe or to the physician for review. This means that the tools the scribes use are also the tools physicians are able to use as well. Regarding the draft clinical report incorporating representations of data included in the transcript, and as shown in the example of FIG. 3, the system 300 uses the techniques of FIGS. 2A-B to produce the draft clinical report 150. The statement modification module 310 may generate and proposes, to the scribe 302, based on the draft clinical report 150, one or more modifications 312 to be made to existing statements in the draft clinical report 150 (FIG. 4, operation 410). The scribe 302 may provide, to the statement modification module 310, input 314 indicating approval or rejection of the proposed modifications 312 (FIG. 4, operation 412). Suggested edits to the draft clinical report 150 (e.g. the proposed statements 306 and the proposed modifications 312) may, for example, include: (1) proposed text to be added/modified in the draft clinical report 150; and (2) a location in the draft clinical report 150 where the edit is proposed to be made. Proposed text to be added or modified may include data to be added one or more fields in a database (e.g., in an electronic medical record). Proposed text to be added or modified may include one or more additions or modifications to be made to a user interface element, such as adding a check to a check box or filling a radio button element. Proposed text to be added or modified may include text to be inserted into a document template.)
(Paragraph [0084] of Vozila. The teaching describes that the automated clinical documentation process 10 may update 410 an output of the user interface based upon, at least in part, one or more modifications made at least one layer of the plurality of layers. For instance, rather than the output being static during the editing process, ACD process 10 may update 410 the output based on the modifications made by the editor so far (e.g., based on the decoder being autoregressive in nature). In particular, the decoder (e.g., sequence to sequence decoder) output may depend on its preceding output. As such, if the scribe (or other user) makes a correction in one part of the draft report, ACD process 10 may update a best guess at the subsequent content. In some implementations, this may be distracting to the user, and so to make it less distracting, it may be optionally limited to a toggle-able mode (e.g., online/synchronous vs. global review mode) and/or limited to only modifying the draft output for subsequent sections of the report. In some implementations, there may be at least four ways that corrections to case-record-persistent system outputs (e.g., medical reports, structured data) may be utilized. For example, pairs of ASR transcripts and corrected reports may be used for offline (sequence to sequence, transcript->report) model training. If in the typing acceleration mode as opposed to draft-report-correction mode, as the user types, the prediction for next sentence may be updated, which may not be model training/adaptation, but rather a reflection of the (auto-regressive) model predicting next output based on report content so far. If in the draft-report-correction mode, as the user makes corrections, prediction of subsequent content (sentences or perhaps less distracting, sections) and thus the draft report content (in this report) may be updated, again utilizing the same auto-regressive nature of the sequence to sequence model (and not some result of model training). Tuples of ASR transcripts (along with ASR confidence information), draft reports and noted user edits (e.g., corrections) may be used for an offline confidence model (e.g., required number of edits) training.)
Here the tracking report is the determination of the approval or rejection of the proposed modifications which is then used as a basis to update the machine learning model. With a threshold of 1 approval, failing to meet that approval corresponds to a rejection which is used to update the machine learning model.
Claim 11 is rejected under 35 U.S.C. 103 as being unpatentable over Koll in view of Manda et al. (US 2023/0153641; herein referred to as Manda).
As per claim 11,
Koll discloses the limitations of claim 1.
Koll does not explicitly teach wherein the automatically generated preliminary post patient encounter document includes a JSON file.
However, Manda teaches wherein a automatically generated preliminary post patient encounter document includes a JSON file:
(Paragraphs [0047] and [0053] of Manda. The teaching describes text generation operations can be performed using classified data and/or named entities. For example, the extraction engine 150 can receive a medical report that may include form fields denoting basic information about a medical event (e.g., patient name, medical record number, date, provider). The extraction engine 150 can extract named entities from the form fields on the medical report. The extraction engine 150 can classify the document as a medical report based on the detecting a combination of form fields. The extraction engine 150 can extract codified information (e.g., diagnosis code, medication code) from a free-form narrative included in the report by determining text coordinates, applying a bounding box, performing OCR operations on the determined region, tokenizing (parsing) the text returned by the OCR operations, and applying an ontology to tokens in the text to identify a diagnosis, determine a corresponding diagnostic code, identify a medication, and determine a corresponding medication code. The extraction engine 150 can summarize the medical report by generating a sentence via extractive summarization or another suitable technique. The sentence can include the determined codes. After extracting the entities, the extraction engine 150 can convert the entities and/or values to a structured format, such as Excel, JSON or another key-value data store (at 332). At 338-339, the extraction engine 150 can use the extracted entities for form extraction. This establishes that the reports that a generated can be generated in a JSON file format.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the automated report generation techniques of Koll, the automated report generation techniques of Manda. Paragraph [0035] of Manda teaches that the disclosed methods of report generation lead to improving processing and performance metrics. One of ordinary skill in the art in possession of Koll would have looked to Manda because of this incentive in addition to both being in the same field of endeavor. One of ordinary skill in the art would have added to the teaching of Koll, the teaching of Manda based on this incentive without yielding unexpected results.
Claim 15 is rejected under 35 U.S.C. 103 as being unpatentable over Koll in view of Kanagasingam et al. (US 2016/0092721; herein referred to as Kanagasingam).
As per claim 15,
Koll discloses the limitations of claim 13.
Koll does not explicitly teach wherein the virtual visit is established by a first server, wherein the transcript is encrypted before being provided to the generative machine learning model, and wherein the generative machine learning model is accessed by a second server after conducting authentication between the first server and the second server.
However, Kanagasingam teaches a telemedicine conferencing system that uses a plurality of encrypted servers to host the functions of a telemedicine visit:
(Paragraphs [0276]-[0278] and [0280] of Kanagasingam. The teaching describes that telemedicine system 611 consists of three main components as shown in FIG. 6 of the drawings: a cloud based services component 613, an administrative client site component 615 and a group of specialists component 617 each having their own specialised client application. The cloud based services component 613 functions as a host or distributed server architecture to the administrative client site 615 and the specialist client application 617. The server (data) host is built using commercial web-server architecture such as Microsoft SQL Server™ to provide a relational database management system and Microsoft IIS™ to provide information services over the Internet. Clearly information technology can change over time and so the invention is not dependent on the particular architecture of the implementation described in the preferred embodiment. For example, it is possible to use PHP™ with MYSQL™ as a server based technology instead. With the administrative client site 615 and the devices running the specialist client applications 617, standard based web technologies such as web-browser and underlying security (eg: SSL with encryption) are used to communicate with the server host. The server consists of various modules. These modules serve different purposes and are categorised into four main sub-components (engines), comprising an image processing and machine learning engine 619, a decision support engine 61, a data store engine 623 and a billing engine 625.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the machine learning teleconference teachings of Koll, the cloud based machine learning teleconference teachings of Kanagasingam. Paragraph [0271] describes that the machine learning models used in conjunction with cloud based teleconferencing allow for an improvement in the accuracy of detecting medical conditions. Such teachings of Kanagasingam illustrate the implicit teachings of Koll as it pertains to video conferencing with a patient and expands capability but allowing a distributed sever platform that can perform tasks more efficiently than a single host server alone. One of ordinary skill in the art would have added to the teaching of Koll, the teaching of Kanagasingam based on this incentive without yielding unexpected results.
Claims 16 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Koll in view of Tunstall-Pedoe et al. (US 2016/0092721; herein referred to as Kanagasingam Tunstall-Pedoe).
As per claim 16,
Koll discloses the limitations of claim 1.
Koll does not explicitly teach wherein the generative machine learning model inlcudes a large language model (LLM), and wherein the generative machine learning model is trained to establish a relationship between patterns of a plurality of clinical encounter transcripts and patterns of post patient encounter documents.
However, Tunstall-Pedoe teaches a generative machine learning model includes a large language model (LLM), and wherein the generative machine learning model is trained to establish a relationship between patterns of a plurality of clinical encounter transcripts and patterns of post patient encounter documents:
(Paragraphs [0022], [0652], [1955]-[1976] of Tunstall-Pedoe. The teaching describes generate this UL from interacting with the user via conversation and recording their responses in UL. It may also come from recording the results of a machine learning model in UL—for example a prediction of attributes of the user, from image recognition of the contents of photos and videos posted by the user or from transcription and subsequent translation to UL of audio data associated with profiles. UL supports the creation of a horizontal health application able to integrate an extremely broad amount of heterogeneous health data. The system is configured to automatically process the structured representation to analyze the personal health or medical data. In the preferred implementation, the structured, machine-readable representation of data that conforms to a machine-readable language comprises semantic nodes and passages. There is provided a method of interacting with a LLM, including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt. There is provided a method of interacting with a LLM, including the step of generating continuation data by an LLM, by the LLM using the output of a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the LLM is configured to use the output of the processing system as a prompt and to generate a continuation output (e.g. text output) that is an improved version of the output from the processing system.)
It would have been obvious to one of ordinary skill in the art before the time of filing to add to the machine learning models of Koll, the LLM methods of Tunstall-Pedoe. Paragraph [0024] of Tunstall-Pedoe teaches that the usage of LLM with machine learning methods provide an improved output of the machine learning models. One of ordinary skill in the art would have added to the teaching of Koll, the teaching of Tunstall-Pedoe based on this incentive without yielding unexpected results.
As per claim 17,
The combined teaching of Koll and Tunstall-Pedoe teaches the limitations of claim 16.
Tunstall-Pedoe further teaches further comprising training the LLM by performing training operations comprising: obtaining a batch of training data comprising a first set of the patterns of the plurality of clinical encounter transcripts; processing the first set of the patterns of the plurality of clinical encounter transcripts by the LLM to generate an estimated set of post patient encounter documents; computing a loss based on a deviation between the estimated set of post patient encounter documents and the patterns of post patient encounter documents associated with the first set of the patterns of the plurality of clinical encounter transcripts; and updating one or more parameters of the LLM based on the computed loss:
(Paragraphs [0022], [0074]-[0079], [0652], [1955]-[1976] of Tunstall-Pedoe. The teaching describes generate this UL from interacting with the user via conversation and recording their responses in UL. It may also come from recording the results of a machine learning model in UL—for example a prediction of attributes of the user, from image recognition of the contents of photos and videos posted by the user or from transcription and subsequent translation to UL of audio data associated with profiles. UL supports the creation of a horizontal health application able to integrate an extremely broad amount of heterogeneous health data. The system is configured to automatically process the structured representation to analyze the personal health or medical data. In the preferred implementation, the structured, machine-readable representation of data that conforms to a machine-readable language comprises semantic nodes and passages. There is provided a method of interacting with a LLM, including the step of a processing system using a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, to provide new context data for the LLM, in order to improve the output, such as continuation text output, generated by the LLM in response to a prompt. There is provided a method of interacting with a LLM, including the step of generating continuation data by an LLM, by the LLM using the output of a processing system that uses a structured, machine-readable representation of data that conforms to a machine-readable language, such as a universal language, in which the LLM is configured to use the output of the processing system as a prompt and to generate a continuation output (e.g. text output) that is an improved version of the output from the processing system. According to a fourteenth aspect of the invention, there is provided a computer-implemented method of re-training a large language model (LLM), the LLM having been previously trained using a training file, the method including the steps of (i) receiving output from a natural language processing computer process, the output including an answer to a question; (ii) repeating step (i) at least one thousand times using a set of at least one thousand different questions, and storing the answers to the questions in a re-training file; (iii) combining the training file and the re-training file, to generate a combined training file; [computed loss], (iv) using the combined training file to re-train the large language model (LLM); [updating one or more parameters of the LLM based on the computed loss], and (v) storing weights characterizing the re-trained LLM.)
Response to Arguments
Applicant's arguments filed February 02, 2026 have been fully considered.
Applicants arguments pertaining to rejections made under 35 U.S.C. 101 are not persuasive.
The Applicant argues that the production of training data increases the accuracy of the machine learning model over time. This establishes a technical improvement and therefore a practical application of the any alleged abstract idea.
The Examiner respectfully disagrees. The use of training data in machine learning models are the basis of all machine learning models. There is no technical description of how the training is being done or what is even included in the training data itself. This high level of generality that the claims invoke are nothing more than merely applying the abstract idea to the technical field of machine learning. There is no rational basis to conclude that the manner in which the training data is being generated would improve any machine learning model. A technical improvement needs to be specific in how the machine learning model is being improved in such a way that one of ordinary skill in the art would have readily recognized. Further, this is all under-minded by the fact that, as claimed, the training data is merely being generated. The training data is not actually being trained into the machine learning model. Even if it could be established that the specific training data could improve technology, a point which the Examiner does not concede, the claims as written do not even implement the training data being generated. Accordingly, these arguments are not persuasive.
Applicants arguments pertaining to rejections made under 35 U.S.C. 102 and 103 are not persuasive for the reasons indicated in the updated rejection above.
Conclusion
THIS ACTION IS MADE FINAL. 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 CHAD A NEWTON whose telephone number is (313)446-6604. The examiner can normally be reached M-F 8:00AM-4:00PM (EST).
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, PETER H. CHOI can be reached at (469) 295-9171. 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.
/CHAD A NEWTON/Primary Examiner, Art Unit 3681
Prosecution Insights