DETAILED ACTION
The present office action represents a final action on the merits.
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 .
Priority
This application claims the priority date of provisional application 63/583,224 of September 15, 2023.
Status of Claims
Claims 1, 11, 21, are amended and Claims 1-30 are pending.
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 1-30 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.
Claims 1-10 are drawn to a method for automated SOAP note evaluation using machine learning, which is within the four statutory categories (i.e., process). Claims 11-20 are drawn to a system for automated SOAP note evaluation using machine learning, which is within the four statutory categories (i.e., machine). Claims 21-30 are drawn to one or more non-transitory computer-readable media storing instructions for automated SOAP note evaluation using machine learning, which is within the four statutory categories (i.e., machine).
Claims 1-10 recite computer-implemented method comprising:
accessing a Subjective, Objective, Assessment and Plan (SOAP) note and a checklist that includes checklist facts, wherein the checklist is an itemized reference of the checklist facts discussed during a conversation between a provider and a patient;
using a first machine-learning model prompt to extract SOAP note facts from the SOAP note;
using one or more second machine-learning model prompts to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts within the checklist are supported by at least one of the SOAP note facts, and whether individual SOAP note facts are supported by at least one of the checklist facts within the checklist; and
generating a score for the SOAP note based on the feedback.
Claim 11 recites a system comprising:
one or more processing systems; and one or more computer-readable media storing instructions which, when executed by the one or more processing systems, cause the system to perform operations comprising:
accessing a Subjective, Objective, Assessment and Plan (SOAP) note and a checklist that includes checklist facts, wherein the checklist is an itemized reference of the checklist facts discussed during a conversation between a provider and a patient;
using a first machine-learning model prompt to extract SOAP note facts from the SOAP note;
using one or more second machine-learning model prompts to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts are supported by at least one SOAP note fact, and whether individual SOAP note facts are supported by at least one fact in the checklist facts; and
generating a score for the SOAP note based on the feedback.
Claim 21 recites one or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause a system to perform operations, comprising:
accessing a Subjective, Objective, Assessment and Plan (SOAP) note and a checklist that includes checklist facts, wherein the checklist is an itemized reference of the checklist facts discussed during a conversation between a provider and a patient;
using a first machine-learning model prompt to extract SOAP note facts from the SOAP note;
using a one or more second machine-learning model prompts to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts are supported by at least one SOAP note fact, and whether individual SOAP note facts are supported by at least one checklist fact; and
generating a score for the SOAP note based on the feedback.
The bolded limitations, given the broadest reasonable interpretation, cover a certain method of organizing human activity and mathematic concepts, but for the recitation of generic computer components (e.g., in this case a system, one or more processors.). The underlined limitations are not part of the identified abstract idea (the method of organizing human activity and mathematic concepts) and are deemed “additional elements,” and will be discussed in further detail below.
Dependent claims 2-10, 12-20, and 22-30 are similarly rejected because they either further define/narrow the abstract idea and/or do not further limit the claim to a practical application or provide as inventive concept such that the claims are subject matter eligible even when considered individually or as an ordered combination. These limitations only serve to further limit the abstract idea (or contain the same additional elements found in the independent claim), and hence are nonetheless directed towards fundamentally the same abstract idea as independent claims 1, 11, and 21.
The dependent claims recite additional limitations but these only serve to further limit the abstract idea, and hence are nonetheless directed towards fundamentally the same abstract idea as independent claims 1, 11, and 21.
The additional elements from claim 11 include:
a system (apply it, MPEP 2106.05(f)).
The additional elements from claim 21 include:
one or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause a system to perform operations (apply it, MPEP 2106.05(f)).
These additional elements, in the independent claims are not integrated into a practical application because the additional elements (i.e., the limitations not identified as part of the abstract idea) amount to no more than limitations which:
amount to mere instructions to apply an exception – for example, a system and one or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause a system to perform operations, See Specification paragraphs [0044], [0091], [0119], and [0177]-[0178] (See MPEP 2106.05(f)).
Furthermore, the claims do not include additional elements that are sufficient to amount to “significantly more” than the judicial exception because, the additional elements (i.e., the elements other than 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, as demonstrated by:
The Specification discloses that the additional elements are well-understood, routine, and conventional in nature (i.e., the Specification, paragraphs [0044], [0091], [0119], and [0177]-[0178], discloses that the additional elements (i.e., a system and one or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause a system to perform operations.);
Relevant court decisions: The following example of court decision demonstrating well understood, routine and conventional activities, e.g., see MPEP 2106.05(d)(II): Extract SOAP note, e.g., see Intellectual Ventures v. Symantec – similarly, the current invention receives input data.
Thus, taken alone, the additional elements do not amount to “significantly more” than the above identified abstract idea. Furthermore, looking at the limitations as an ordered combination adds nothing that is not already present when looking at the elements taken individually, and there is no indication that the combination of elements improves any other technology, and their collective functions merely provide conventional computer implementation.
The application, is an attempt to organize human activity and mathematic concepts, using a personalized assistance system to receive and transmit patient data. The inventive concept is the automated SOAP note evaluation using machine learning models, which is not patentable. Therefore, whether taken individually or as an ordered combination, claims 1-30 are nonetheless rejected under 35 U.S.C. 101 as being directed to non-statutory subject matter.
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 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.
Claims 1-2, 5-12, 15-22, and 25-30 are rejected under 35 U.S.C. 103 as being unpatentable over Lipton (U.S. Pub. No. 2022/0375605 A1) in view of Kartoun (U.S. Pub. No. 2020/0321085 A1).
Regarding claim 1, Lipton discloses a computer-implemented method comprising:
accessing a Subjective, Objective, Assessment and Plan (SOAP) note and a checklist that includes checklist facts, wherein the checklist is an itemized reference of the checklist facts discussed during a conversation between a provider and a patient (Paragraphs [0008], [0037], [0040], [0045], [0050]-[0055], and FIG. 9 discuss accessing a digital resource that includes a plurality of sections and generating content for at least one of the sections by: parsing, by the data processing system, one or more fields in one or more of the received data items; and receives conversation data from client device, transcribes the conversation data, extracts clinically relevant information, and makes clinical inferences to assist both physicians and patients with organizing medical information and generating SOAP notes; the data processing system maps or links each noteworthy utterance to a piece of evidence; FIG. 9 details a table with subsections that list various items that can be extracted from the conversation data, i.e., Prescriptions and Therapeutics, Review of Systems, Past Medical History, Medications, Assessment, Review of Systems, Chief Complaint, etc. (Examiner is interpreting the Subsections as a checklist and the noteworthy utterances that are clustered into the subsections as the checklist facts.); each section of SOAP is further divided into subsections giving it a finer substructure. For example, the subjective section S includes multiple subsections such as a chief complaint section (e.g., a primary reason for a patient's visit), an allergies section, a past medical history section, and so forth. Generally, a particular visit may not have information relevant to each subsection. The extraction-centric scenario localizes the precise sentences upon which each SOAP note sentence depends, enabling physicians to (i) verify the correctness of each sentence and (ii) to improve the draft by highlighting sentences, in contrast with revising the text directly.);
using a first machine-learning model prompt to extract SOAP note facts from the SOAP note (Paragraphs [0038] and [0040]–[0041] discuss data processing system extracts the noteworthy utterances using multi-label classification. The data processing system assigns the extracted noteworthy utterances to summary section(s) and uses a neural network or other trained machine learning model to analyze the physician-patient sessions and update the model using feedback data from the physician provided after one or more encounters, the system stores historical data including of thousands of recorded clinical conversations with associated SOAP notes created by a work force trained in the official style of SOAP note documentation. The historical data includes automatic speech recognition (ASR) transcriptions of these conversations and machine learning optimized SOAP notes based on the human generated transcripts.);
using one or more second machine-learning model prompts (Examiner notes that the prior art does not explicitly state “first” or “second” and is interpreting it to include iteratively training and improving the model.) to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts within the checklist are supported by at least one of the SOAP note facts, and whether individual SOAP note facts are supported by at least one of the checklist facts within the checklist (Paragraphs [0037]-[0041], [0043], and FIG. 9 discuss various and multiple machine learning networks and methodologies can be used to train a model for use in automatically generating a SOAP note, a unique dataset of patient visit records, including of transcripts, paired SOAP notes, and annotations marking noteworthy utterances that support each summary sentence can be generated and can be stored in a database and noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections from a live physician-patient session. The data processing system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note; FIG. 9 details a table with subsections that list various items that are extracted from the conversation data, i.e., Prescriptions and Therapeutics, Review of Systems, Past Medical History, Medications, Assessment, Review of Systems, Chief Complaint, etc. and the system clusters the noteworthy utterances on a per-section basis into the subsection of the SOAP note.).
Lipton does not explicitly disclose:
generating a score for the SOAP note based on the feedback.
Kartoun teaches:
generating a score for the SOAP note based on the feedback (Paragraphs [0006] and [0043] discuss generate a classifier using a machine learning process, use supervised or unsupervised learning to develop classifiers for scoring narrative notes and the scoring the clinical narrative note.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Lipton to include, generating a score for the SOAP note based on the feedback, as taught by Kartoun, in order to provide sufficient information to enable one to accurately determine the patient's health status from the record. (Kartoun Paragraph [0005]).
Regarding claims 2, 12, and 22, Lipton discloses wherein using the one or more second machine-learning model prompts to generate the feedback for the SOAP note comprises using a first prompt of the one or more second machine-learning model prompts to determine whether each checklist fact is included the SOAP note facts (Paragraphs [0039]-[0040] and [0043] discuss data processing system uses a neural network or other trained machine learning model to analyze the physician-patient sessions and update the model using feedback data from the physician provided after one or more encounters and select noteworthy utterances to generate a SOAP note, noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections. The data processing system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note.).
Regarding claims 5, 15, and 25, Lipton discloses wherein the SOAP note is generated using one or more machine learning models based at least in-part on a text transcript corresponding to an interaction between a healthcare provider and a patient of the healthcare provider (Paragraphs [0005], [0039]-[0040] and [0043] discuss data processing system uses a neural network or other trained machine learning model to analyze the physician-patient sessions and update the model using feedback data from the physician provided after one or more encounters and select noteworthy utterances to generate a SOAP note, noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections. The data processing system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note.).
Regarding claims 6, 16, and 26, Lipton discloses wherein the checklist facts are extracted from the text transcript, and wherein each of the checklist facts is expressed as a sentence (Paragraphs [0005], [0039]-[0040] and [0043] discuss data processing system uses a neural network or other trained machine learning model to analyze the physician-patient sessions and update the model using feedback data from the physician provided after one or more encounters and select phrases or collections of sentences called noteworthy utterances to generate a SOAP note, noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections. The data processing system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note.).
Regarding claims 7, 17, and 27, Lipton discloses wherein each SOAP note fact in the SOAP note facts is an atomic sentence, and wherein using the first machine-learning model prompt to extract the SOAP note facts comprises using the first machine-learning model prompt to generate atomic sentences from the SOAP note (Paragraphs [0038], [0042], [0089], [0101], and FIG. 9 discuss the system using a machine learning model and the generation of formatted annotations to create the SOAP note and the system creates clusters of supporting utterances which are related to each other and summarizes each cluster separately to produce a one-sentence summary for each cluster, three example processes are described for deciding if a sentence is noteworthy. A first process is called UMLS-noteworthy in which the data processing system designates a sentence as noteworthy if the medical tagger finds an entity relevant to the task (e.g., a diagnosis or symptom) as defined in the medical-entity-matching baseline. The second process is called all-noteworthy in which the data processing system deems a sentence in the conversation noteworthy if it was used as evidence for any line in the annotated SOAP note, the classifier is trained to predict the noteworthy sentences given a conversation. The third process is called diagnosis/RoS-noteworthy in which the data processing system defines noteworthy sentences as being only those sentences are deemed noteworthy in the second process that were used as evidence for an entry including the ground truth tags (e.g., diagnosis/RoS abnormality) that are being predicted.).
Regarding claims 8, 18, and 28, Lipton discloses wherein the feedback provides an indication of which checklist facts are not included in the SOAP note facts and which SOAP note facts are not included in the checklist facts (Paragraphs [0037]-[0039] and [0120] discuss each section of SOAP is further divided into subsections giving it a finer substructure. For example, the subjective section S includes multiple subsections such as a chief complaint section (e.g., a primary reason for a patient's visit), an allergies section, a past medical history section, and so forth. Generally, a particular visit may not have information relevant to each subsection. As a result, some of the subsections may be empty. The fraction of times a subsection is populated varies widely. For example, an allergies section is generally a sparsest populated overall (present in about 4% of notes), while a chief complaint section is generally the most frequently observed (generally present in every record) and noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections and the system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note; also the system uses beam search to make sure that all the SOAP note sections are generated in proper order by feeding the header of the first section (chief complaint). Whenever the model predicts a section header as next word and it shows up in a beam, the data processing system determines whether the header is the next section to be generated. If not, the data processing system replaces the header with the header of the correct next section.).
Regarding claims 9, 19, and 29, Lipton does not explicitly disclose wherein generating the score for the SOAP note based on the feedback comprises calculating a SOAP note score based on the feedback.
Kartoun teaches:
wherein generating the score for the SOAP note based on the feedback comprises calculating a SOAP note score based on the feedback (Paragraphs [0006] and [0043] discuss generate a classifier using a machine learning process, use supervised or unsupervised learning to develop classifiers for scoring narrative notes and the scoring the clinical narrative note.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Lipton to include, wherein generating the score for the SOAP note based on the feedback comprises calculating a SOAP note score based on the feedback, as taught by Kartoun, in order to provide sufficient information to enable one to accurately determine the patient's health status from the record. (Kartoun Paragraph [0005]).
Regarding claims 10, 20, and 30, Lipton discloses wherein using the one or more second machine-learning model prompts to generate the feedback for the SOAP note comprises using a prompt of the one or more second machine-learning model prompts to determine that a SOAP note fact, indicated to support a checklist fact, contradicts the checklist fact (Paragraphs [0038]-[0041], [0043]-[0046], and [0120] discuss various and multiple machine learning networks and methodologies can be used to train a model for use in automatically generating a SOAP note, a unique dataset of patient visit records, including of transcripts, paired SOAP notes, and annotations marking noteworthy utterances that support each summary sentence can be generated and can be stored in a database and noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections. The data processing system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note; a qualitative evaluation of the produced SOAP notes, characterizing the errors that both models make, and the impact of per-section conditioning; also a model classifies each utterance as noteworthy or not for each specific subsection of the SOAP note; also the system uses beam search to make sure that all the SOAP note sections are generated in proper order by feeding the header of the first section (chief complaint). Whenever the model predicts a section header as next word and it shows up in a beam, the data processing system determines whether the header is the next section to be generated. If not, the data processing system replaces the header with the header of the correct next section.).
Regarding claim 11, Lipton discloses a system comprising (Paragraph [0032] discloses a system.):
one or more processing systems (Paragraph [0033] discloses a data processing system.); and
one or more computer-readable media storing instructions which, when executed by the one or more processing systems, cause the system to perform operations comprising (Claim 21 discloses or more non-transitory computer-readable media storing instructions that, when executed by at least one processing device, cause the at least one processing device to perform operations.):
accessing a Subjective, Objective, Assessment and Plan (SOAP) note and a checklist that includes checklist facts, wherein the checklist is an itemized reference of the checklist facts discussed during a conversation between a provider and a patient (Paragraphs [0008], [0037], [0040], [0045], [0050]-[0055], and FIG. 9 discuss accessing a digital resource that includes a plurality of sections and generating content for at least one of the sections by: parsing, by the data processing system, one or more fields in one or more of the received data items; and receives conversation data from client device, transcribes the conversation data, extracts clinically relevant information, and makes clinical inferences to assist both physicians and patients with organizing medical information and generating SOAP notes; the data processing system maps or links each noteworthy utterance to a piece of evidence; FIG. 9 details a table with subsections that list various items that can be extracted from the conversation data, i.e., Prescriptions and Therapeutics, Review of Systems, Past Medical History, Medications, Assessment, Review of Systems, Chief Complaint, etc.; each section of SOAP is further divided into subsections giving it a finer substructure. For example, the subjective section S includes multiple subsections such as a chief complaint section (e.g., a primary reason for a patient's visit), an allergies section, a past medical history section, and so forth. Generally, a particular visit may not have information relevant to each subsection. The extraction-centric scenario localizes the precise sentences upon which each SOAP note sentence depends, enabling physicians to (i) verify the correctness of each sentence and (ii) to improve the draft by highlighting sentences, in contrast with revising the text directly.);
using a first machine-learning model prompt to extract SOAP note facts from the SOAP note (Paragraphs [0038] and [0040]–[0041] discuss data processing system extracts the noteworthy utterances using multi-label classification. The data processing system assigns the extracted noteworthy utterances to summary section(s) and uses a neural network or other trained machine learning model to analyze the physician-patient sessions and update the model using feedback data from the physician provided after one or more encounters, the system stores historical data including of thousands of recorded clinical conversations with associated SOAP notes created by a work force trained in the official style of SOAP note documentation. The historical data includes automatic speech recognition (ASR) transcriptions of these conversations and machine learning optimized SOAP notes based on the human generated transcripts.);
using one or more second machine-learning model prompts to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts are supported by at least one SOAP note fact, and whether individual SOAP note facts are supported by at least one fact in the checklist facts (Paragraphs [0037]-[0041], [0043], and FIG. 9 discuss various and multiple machine learning networks and methodologies can be used to train a model for use in automatically generating a SOAP note, a unique dataset of patient visit records, including of transcripts, paired SOAP notes, and annotations marking noteworthy utterances that support each summary sentence can be generated and can be stored in a database and noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections from a live physician-patient session. The data processing system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note; FIG. 9 details a table with subsections that list various items that are extracted from the conversation data, i.e., Prescriptions and Therapeutics, Review of Systems, Past Medical History, Medications, Assessment, Review of Systems, Chief Complaint, etc. and the system clusters the noteworthy utterances on a per-section basis into the subsection of the SOAP note.).
Lipton does not explicitly disclose:
generating a score for the SOAP note based on the feedback.
Kartoun teaches:
generating a score for the SOAP note based on the feedback (Paragraphs [0006] and [0043] discuss generate a classifier using a machine learning process, use supervised or unsupervised learning to develop classifiers for scoring narrative notes and the scoring the clinical narrative note.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Lipton to include, generating a score for the SOAP note based on the feedback, as taught by Kartoun, in order to provide sufficient information to enable one to accurately determine the patient's health status from the record. (Kartoun Paragraph [0005]).
Regarding claim 21, Lipton discloses one or more non-transitory computer-readable media storing instructions which, when executed by one or more processors, cause a system to perform operations comprising (Claim 21 discloses or more non-transitory computer-readable media storing instructions that, when executed by at least one processing device, cause the at least one processing device to perform operations.):
accessing a Subjective, Objective, Assessment and Plan (SOAP) note and a checklist that includes checklist facts, wherein the checklist is an itemized reference of the checklist facts discussed during a conversation between a provider and a patient (Paragraphs [0008], [0037], [0040], [0045], [0050]-[0055], and FIG. 9 discuss accessing a digital resource that includes a plurality of sections and generating content for at least one of the sections by: parsing, by the data processing system, one or more fields in one or more of the received data items; and receives conversation data from client device, transcribes the conversation data, extracts clinically relevant information, and makes clinical inferences to assist both physicians and patients with organizing medical information and generating SOAP notes; the data processing system maps or links each noteworthy utterance to a piece of evidence; FIG. 9 details a table with subsections that list various items that can be extracted from the conversation data, i.e., Prescriptions and Therapeutics, Review of Systems, Past Medical History, Medications, Assessment, Review of Systems, Chief Complaint, etc.; each section of SOAP is further divided into subsections giving it a finer substructure. For example, the subjective section S includes multiple subsections such as a chief complaint section (e.g., a primary reason for a patient's visit), an allergies section, a past medical history section, and so forth. Generally, a particular visit may not have information relevant to each subsection. The extraction-centric scenario localizes the precise sentences upon which each SOAP note sentence depends, enabling physicians to (i) verify the correctness of each sentence and (ii) to improve the draft by highlighting sentences, in contrast with revising the text directly.);
using a first machine-learning model prompt to extract SOAP note facts from the SOAP note (Paragraphs [0038] and [0040]–[0041] discuss data processing system extracts the noteworthy utterances using multi-label classification. The data processing system assigns the extracted noteworthy utterances to summary section(s) and uses a neural network or other trained machine learning model to analyze the physician-patient sessions and update the model using feedback data from the physician provided after one or more encounters, the system stores historical data including of thousands of recorded clinical conversations with associated SOAP notes created by a work force trained in the official style of SOAP note documentation. The historical data includes automatic speech recognition (ASR) transcriptions of these conversations and machine learning optimized SOAP notes based on the human generated transcripts.);
using a one or more second machine-learning model prompts to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts are supported by at least one SOAP note fact, and whether individual SOAP note facts are supported by at least one checklist fact using one or more second machine-learning model prompts (Examiner notes that the prior art does not explicitly state “first” or “second” and is interpreting it to include iteratively training and improving the model.) to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts within the checklist are supported by at least one of the SOAP note facts, and whether individual SOAP note facts are supported by at least one of the checklist facts within the checklist (Paragraphs [0037]-[0041], [0043], and FIG. 9 discuss various and multiple machine learning networks and methodologies can be used to train a model for use in automatically generating a SOAP note, a unique dataset of patient visit records, including of transcripts, paired SOAP notes, and annotations marking noteworthy utterances that support each summary sentence can be generated and can be stored in a database and noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections from a live physician-patient session. The data processing system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note; FIG. 9 details a table with subsections that list various items that are extracted from the conversation data, i.e., Prescriptions and Therapeutics, Review of Systems, Past Medical History, Medications, Assessment, Review of Systems, Chief Complaint, etc. and the system clusters the noteworthy utterances on a per-section basis into the subsection of the SOAP note.).
Lipton does not explicitly disclose:
generating a score for the SOAP note based on the feedback.
Kartoun teaches:
generating a score for the SOAP note based on the feedback (Paragraphs [0006] and [0043] discuss generate a classifier using a machine learning process, use supervised or unsupervised learning to develop classifiers for scoring narrative notes and the scoring the clinical narrative note.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Lipton to include, generating a score for the SOAP note based on the feedback, as taught by Kartoun, in order to provide sufficient information to enable one to accurately determine the patient's health status from the record. (Kartoun Paragraph [0005]).
Claims 3-4, 13-14, and 23-24 are rejected under 35 U.S.C. 103 as being unpatentable over Lipton in view of Kartoun and in further view of Zimmerman (U.S. Pub. No. 2022/0068482 A1).
Regarding claims 3, 13, and 23, Lipton discloses wherein using the one or more second machine-learning model prompts to generate the feedback for the SOAP note comprises using the first prompt (Paragraphs [0007] and [0040]-[0041] discuss the generation of SOAP notes and the system uses a neural network or other trained machine learning model to analyze the physician-patient sessions and update the model using feedback data from the physician provided after one or more encounters to create the SOAP notes.).
Lipton does not explicitly disclose:
wherein using the one or more second machine-learning model prompts to generate the feedback for the SOAP note comprises using the first prompt to determine an importance level of each of the checklist facts.
Zimmerman teaches:
wherein using the one or more second machine-learning model prompts to generate the feedback for the SOAP note comprises using the first prompt to determine an importance level of each of the checklist facts (Paragraphs [0044]-[0045] discuss the provider collects patient data and puts the patient data into a triage interface that is configured to automatically suggest relevant care pathways by using this triage information to automate the search and return a ranked list of pathways based on the patient data; physicians rely on the triage keywords assigned to patients (Examiner is interpreting the triage keywords as the checklist facts, which based on the triage keywords importance determine the care pathway.).
Therefore, it would have been obvious to one of ordinary skill in the art to modify Lipton to include, wherein using the one or more second machine-learning model prompts to generate the feedback for the SOAP note comprises using the first prompt to determine an importance level of each of the checklist facts, as taught by Zimmerman, in order to determine which features matter most when modeling a more personalized set of diagnosis or treatment alternatives, and to help clinicians more efficiently author more accurate and detailed clinical notes. (Zimmerman Paragraph [0069]).
Regarding claims 4, 14, and 24, Lipton discloses wherein using the one or more second machine-learning model prompts to generate the feedback for the SOAP note comprises using a second prompt to determine whether each SOAP note fact corresponds to at least one checklist fact in the checklist facts (Paragraphs [0005], [0039]-[0040] and [0043] discuss data processing system uses a neural network or other trained machine learning model to analyze the physician-patient sessions and update the model using feedback data from the physician provided after one or more encounters and select noteworthy utterances to generate a SOAP note, noteworthy utterances include relevant keywords with respect to one or more of the four (S, O, A, P) sections. The data processing system automatically identifies and classifies transcript data and associated metadata in a physician-patient session based on that data's relevance to different parts of the SOAP note.).
Response to Arguments
Applicant’s arguments filed 12/22/2025 have been fully considered.
Rejections under 35 U.S.C. 101:
With respect to claim 1 and the 35 U.S.C. 101 rejection, Applicant’s amendment fails to overcome the previous rejection. Claim 1 as amended recites an abstract idea, a method of organizing human activity. See MPEP 2106.04(a)(2)(II)(C) Managing Personal Behavior or Relationships or Interactions Between People. Applicant states, “The Claims are Directed to a Technical Improvement in Computer Capabilities. As discussed and tentatively agreed to by the Examiner during the interview, the claims are not directed to an abstract idea such as "organizing human activity." Rather, the claims are directed to a specific improvement in the functioning of computers, specifically in the field of Natural Language Processing (NLP), and automated text generation using machine learning. The problem addressed by the present invention is one specific to machine learning models.” (Remarks, page 9). Applicant further states, “models often have input window token limits, are inconsistent in performance, do not follow SOAP note structure, and are error prone (e.g., hallucinate, use incorrect terminology, and overlook important facts, numerical information, important entities, and other important details, and the like). The claims address this problem not by generic "organization," but by a specific technical architecture that includes both "using a first machine-learning model prompt to extract SOAP note facts from the SOAP note" and then "using one or more second machine-learning model prompts to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts are supported by at least one of the SOAP note facts, and whether individual SOAP note facts are supported by at least one of the checklist facts".” (Remarks, page 9). Applicant further states, “This architecture defined by the recitations of claim 1 improves the computer's ability to evaluate its own output. As held in Enfish, LLC v. Microsoft Corp., 822 F.3d 1327 (Fed. Cir. 2016), claims directed to a specific improvement to the way computers operate are not directed to an abstract idea. The present claims recite a specific technique for automated verification of text generated by a machine learning model that improves the reliability of the computer system itself.” (Remarks, page 10). Examiner respectfully disagrees. Here, the prompts used by the machine-learning models, the claims recite, “extract SOAP note facts from the SOAP note; using one or more second machine-learning model prompts to generate feedback for the SOAP note, the feedback indicating whether individual checklist facts within the checklist are supported by at least one of the SOAP note facts, and whether individual SOAP note facts are supported by at least one of the checklist facts within the checklist;” and the amendment at a high level attempts to resolve the problem where the second model checks data generated by the first model, confirming that what the first model generated is based on facts found in the patient/doctor notes and the automated prompt manager keeps refining to get the best prompt. The amendments fall short of resulting in an improvement or claiming the specific improvement to the way the computer operates, and are only an improvement to the abstract idea.
Rejections under 35 U.S.C. 102 and 35 U.S.C. 103:
With respect to claim 1 and the 35 U.S.C. 103 rejection, Applicant’s amendment overcomes the previous 35 U.S.C. 103 rejection. Applicant states, “Lipton and Kartoun Fail to Teach of Suggest Verification of "SOAP Note Facts" Against "Checklist Facts"” (Remarks, page 11). Examiner notes that Lipton discloses, each section of SOAP is further divided into subsections giving it a finer substructure. For example, the subjective section S includes multiple subsections such as a chief complaint section (e.g., a primary reason for a patient's visit), an allergies section, a past medical history section, and so forth. Generally, a particular visit may not have information relevant to each subsection. As a result, some of the subsections may be empty, the conversation data collected during the physician-patient session is extracted and put into the appropriate field and verify the correctness of each sentence. Paragraphs [0037], [0040], and [0045]. Applicant’s arguments with respect to claim 1 have been considered and the Examiner’s rejection has been updated to address Applicant’s claim amendments. Similarly, Examiner’s rejection related to claims 11 and 21 has been amended.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DAWN TRINAH HAYNES whose telephone number is (571)270-5994. The examiner can normally be reached M-F 7:30-5:15PM.
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, Jason Dunham can be reached on (571)272-8109. 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.
/DAWN T. HAYNES/
Art Unit 3686
/RACHELLE L REICHERT/Primary Examiner, Art Unit 3686