DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 15 April 2026 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the IDS is being considered by the Examiner in this Office Action.
Response to Amendment
Claims 1-13 & 15-21 were previously pending in this application. The amendment filed 15 April 2026 has been entered and the following has occurred: Claims 1, 15, 17, & 19 have been amended. Claim 16 & 21 have been cancelled. Claim 22 & 23 has been added.
Claims 1-13, 15, 17-20, & 22-23 remain pending in the application
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 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 1-13, 15, 17-20, & 22-23 are rejected under 35 U.S.C. 103 as being unpatentable over Khaleghi et al. (U.S. Patent Publication No. 2020/0084595), hereinafter “Khaleghi”, in view of Godbole et al. (U.S. Patent Publication No. 2022/0351868), hereinafter “Godbole”, further in view of Thomson et al. (U.S. Patent Publication No. 2020/0175961), hereinafter “Thomson”.
Claim 1 –
Regarding Claim 1, Khaleghi discloses a method implemented via a computing device (See Khaleghi Abstract for a computing device; See Khaleghi Par [0119] for a computerized method implemented via computing device), the method comprising:
receiving, by a processor of the computing device, behavioral treatment data associated with a subject, the behavioral treatment data associated with the subject comprising data collected during delivery of applied behavior analysis (ABA) a behavior therapy intervention and indicative of behavior of the subject, mood of the subject, emotions of the subject, treatment goals for the subject, instruction given to the subject, or combinations thereof (See Khaleghi Par [0022] which discloses receiving or extraction of patient-related data including sound and/or video recordings, scans, test results, contact information, calendaring information, biographical data, patient-related team data, etc.; See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment, i.e. data collected during delivery of a behavior therapy intervention; See Khaleghi Par [0092] which discloses receiving new or updated biographical, medical, clinical, therapeutic, and/or diary data, i.e. treatment data; See Khaleghi Par [0094] which discloses the check-in user interface possibly enabling a user to provide updates on how a patient or the user is doing, i.e. emotions of the subject; See Khaleghi Par [0084] which discloses a medication record including fields that may be populated including the goal of the medication, i.e. treatment goal; See Khaleghi Par [0053] which discloses recording follow-up information indicating whether the patient is taking the medication, following other instructions provided by the doctor/specialist (i.e. instructions given to the subject), the patient's physical condition and health, etc.; See Khaleghi Par [0088]-[0089] which discloses said virtual diary being updated during each new appointment, intervention, etc., the interventions including those listed in Khaleghi Par [0053] & [0110] which discloses example forms of prescribed therapies for a patient, including physical therapy, speech therapy, counseling sessions, etc.), wherein
a therapy notes (TN) model is associated with the computing device (See Khaleghi Par [0053]-[0054] which discloses the electronic notebook including a record control, that enables video and/or audio to be recorded, such that the spoken voice captured may be converted to text using a voice-to-text module), wherein
the TN model is a natural language processing (NLP)/machine-learning (ML) model (See Khaleghi Par [0053]-[0054] & [0111] which discloses the voice-to-text module including neural networks for trainable brain-like computer models that can reliably recognize patterns, such as word sounds, after training), wherein
a non-transitory computer-readable medium of the computing device causes the processor to implement the TN model (See Khaleghi Par [0054] which discloses a software module, i.e. stored computerized instructions that embodies the neural networks for trainable brain-like computer models that can reliably recognize patterns, such as word sounds, after training), wherein
the TN model has been trained on training data associated with a plurality of subjects (See Khaleghi Par [0053]-[0054] & [0111] which discloses the voice-to-text module including neural networks for trainable brain-like computer models that can reliably recognize patterns, such as word sounds, after training), wherein
at least a portion of the subject are individuals characterized as having a neurodevelopmental disorder (NDD) (See Khaleghi Par [0031]-[0035] which discloses generate a new electronic notebook, the electronic notebook application may provide a user interface listing various medically-related conditions or categories. By way of non-limiting example, the conditions may include one or more of the following: Autistic Spectrum Disorder, Developmental Disorders, Learning Disorders, Emotional or Psychiatric Disorders), wherein
the training data comprises free text fields from ABA therapy notes (See Khaleghi Par [0040] & [0096] which discloses receiving free-form text such that NLP or keyword processing may be utilized, i.e. the NLP or keyword processing algorithms are trained to be able to process said free-form text); while not ABA therapy notes per se, Khaleghi Par [0110] which disclose various types of therapy and data generated therefrom or therefor), and wherein
the TN model has been trained via a method comprising (See Khaleghi Par [0053]-[0054] & [0111] which discloses the voice-to-text module including neural networks for trainable brain-like computer models that can reliably recognize patterns, such as word sounds, after training):
preprocessing the behavioral treatment data and generating one or more vectorized therapy note features to form a therapy note feature matrix (See Khaleghi Par [0022] which discloses receiving or extraction of patient-related data including sound and/or video recordings, scans, test results, contact information, calendaring information, biographical data, patient-related team data, etc.; See Khaleghi Par [0053] & [0055] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment; See Khaleghi Par [0089] which discloses an example health timeline generated by the system using collected data, including receipt of new or updated diagnosis and/or treatment data for a subject; See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, such that the system can recognize various words, phrases, sentences, or series of sentences),
the TN model comprises a large language model and an ML model selected from the group consisting of a deep learning model, a generative adversarial network model, a computational neural network model, a recurrent neural network model, a perceptron model, a classical tree-based machine-learning model, a decision tree type model, a regression type model, a classification model, a reinforcement learning model, and combinations thereof (See Khaleghi Par [0054] & [0111] which discloses the use of a voice-to-text module, using language modeling and statistical analysis, and can possibly make use of neural networks (trainable brain-like computer models that reliably recognize patterns) and/or pattern matching, pattern and feature analysis, language modeling and statistical analysis, etc.).
As disclosed above, Khaleghi discloses language modeling and statistical analysis, and can possibly make use of neural networks (trainable brain-like computer models that reliably recognize patterns) and/or pattern matching, pattern and feature analysis, language modeling and statistical analysis, etc. However, Khaleghi does not explicitly disclose the full list of models recited in the limitation “the TN model is a machine-learning model selected from the group consisting of a deep learning model, a generative adversarial network model, a computational neural network model, a recurrent neural network model, a perceptron model, a classical tree-based machine-learning model, a decision tree type model, a regression type model, a classification model, a reinforcement learning model, and combinations thereof” and/or being applied during “behavior treatment” session per se. However, because Khaleghi Par [0022]; [0053]; & [0092] identify the need for automated transcription of medical sessions, such as via a learning algorithm, and while not explicitly during “ behavioral treatment” sessions per se, Khaleghi further suggests at Par [0054] & [0111] that the use of one of the species found amongst the machine learning models found in the list above can accomplish said task of automated transcription of medical sessions, it is understood that the list of other machine learning models are mere alternatives to the one Khaleghi discloses and would also have the same reasonable expectation of success, i.e. transcription of therapy notes during a therapy session. As a result, it would have been obvious to try one of the identified, predictable solutions, i.e. machine learning algorithms, with a reasonable expectation of success by one of ordinary skill in the art before the effective filing date of the claimed invention. Furthermore, while it is understood that Khaleghi renders the claim above obvious and therefore not being relied upon, Examiner also points to Co et al. and Roh et al. for additional teachings regarding viable, known alternative machine learning algorithms for accomplishing the same or similar results as Khaleghi to further demonstrate said obviousness to try.
While Khaleghi generally discloses the use of a machine learning model in the form of a neural network for purposes of note generation and/or text extraction, and said models being capable of being trained, Khaleghi is not explicit on how this training is performed as given by:
preprocessing the training data by one or more of removing punctuations, removing symbols, removing stop words, lowering text case, tokenizing, stemming, lemmatization, or combinations thereof
extracting vectorized features from the preprocessed training data into a training feature matrix; and
fine tuning a pretrained model on the training feature matrix to yield the TN model.
However, Godbole discloses preprocessing the training data by one or more of removing punctuations, removing symbols, removing stop words, lowering text case, tokenizing, stemming, lemmatization, or combinations thereof (See Godbole Par [0051] which discloses pre-processing steps, including tokenizing text into sentences, taking place for generation of a dataset for training one or more learning models, as seen in Godbole Par [0064] & [0073], and further includes medical diction being processed by one or more word to vector models to create vectors from words recognized); extracting vectorized features from the preprocessed training data into a training feature matrix (See Godbole Par [0051] which discloses pre-processing steps, including tokenizing text into sentences, taking place for generation of a dataset for training one or more learning models, as seen in Godbole Par [0064] & [0073], and further includes medical diction being processed by one or more word to vector models to create vectors from words recognized; it is understood by Examiner that a vector is a matrix of a singular row or column, so creation of a vector for training purposes would effectively constitute developing a training feature matrix); and fine tuning a pretrained model on the training feature matrix to yield the TN model (See Godbole Par [0051] which discloses pre-processing steps, including tokenizing text into sentences, taking place for generation of a dataset for training one or more learning models, as seen in Godbole Par [0064] & [0073], and further includes medical diction being processed by one or more word to vector models to create vectors from words recognized; it is understood by Examiner that a vector is a matrix of a singular row or column, so creation of a vector for training purposes would effectively constitute developing a training feature matrix). The disclosure of Godbole is directly applicable to the disclosure of Khaleghi, because both disclosures share limitations and capabilities, such as being directed towards machine learning efforts for automatically extracting content from medical literature.
It would have been obvious to one of ordinary skill in the effective filing date of the claimed invention to modify the disclosure of Khaleghi, which already discloses the use of a machine learning model in the form of a neural network for purposes of note generation and/or text extraction, and said models being capable of being trained, to further include aspects of preprocessing said training data by performing various actions, extracting vectorized features from the preprocessed training data into a training feature matrix, and fine tuning a pretrained model on the training feature matrix to yield the TN model, as disclosed by Godbole, because
While Khaleghi and Godbole, specifically Godbole Par [0066], discloses outputting probability for each category of a training dataset, and further includes determining the effectiveness of the training phase, these references are relatively silent on:
evaluating, by the TN model associated with the computing device, the behavioral treatment data associated with the subject, wherein evaluating the behavioral treatment data comprises:
generating a therapy note quality score by using the therapy note feature matrix; wherein
the therapy note quality score is compared to a threshold to classify the behavioral treatment data as adequate or as requiring revisions.
However, Thomson discloses generating a therapy note quality score by using the therapy note feature matrix (See Thomson Table 5 which discloses estimating a feature, including an estimated transcription quality metric, such as the number or percentage of correctly aligned words, number or percentage of incorrectly aligned tokens, etc.); wherein the therapy note quality score is compared to a threshold to classify the behavioral treatment data as adequate or as requiring revisions (See Thomson Table 5 which discloses estimating a feature, including an estimated transcription quality metric, such as the number or percentage of correctly aligned words, number or percentage of incorrectly aligned tokens, etc. and further describes that the number or percentage of transcribed words with confidence, as reported by a recognizer, are compared to a certain threshold, and can contain an indicator of whether a decision to use non-revoiced ASR systems to generate a transcription of communication session segments or revision via from a revoiced ASR system or from a revoiced ASR system). The disclosure of Thomson is directly applicable to the disclosure of Khaleghi and Godbole, such as being directed towards performing transcription of one or more records or audio sessions, etc.
It would have been obvious to one of ordinary skill in the effective filing date of the claimed invention to modify the disclosure of Khaleghi and Godbole, which already discloses outputting probability for each category of a training dataset, and further includes determining the effectiveness of the training phase, to further include generating a therapy note quality score by using the therapy note feature matrix and the therapy note quality score is compared to a threshold to classify the behavioral treatment data as adequate or as requiring revisions, as disclosed by Thomson, because this allows for developing and/or outputting an indicator of whether additional or modified transcription of the session should be employed for accuracy purposes (See Thomson Table 5).
Claim 2 –
Regarding Claim 2, Khaleghi, Godbole, and Thomson disclose the method of claim 1 in its entirety. Khaleghi further discloses a method, wherein:
the one or more therapy note features comprise a dropdown menu, a checkbox, a structured text field, a free text section, a therapy session narrative, a content thereof, or combinations thereof (See Khaleghi Par [0123] which discloses a user selecting a control, menu selection, or the like, and other user input modalities, including include voice commands, text entry, gestures, text fields, menu selection, drop down menu, check box, selectable icons, etc.; See Khaleghi Par [0040] which discloses the use of free form text fields being used as user input; Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), constituting therapy session narrative, the electronic notebook generating and/or provide user interfaces textually providing information about the treatment).
Claim 3 –
Regarding Claim 3, Khaleghi, Godbole, and Thomson disclose the method of claim 1 in its entirety. Khaleghi further discloses a method, wherein:
the behavioral treatment data is recorded into a TN application in communication with the computing device (See Khaleghi Par [0014] which discloses some or all of the information communicated between a user terminal app and a remote system are transmitted securely, i.e. an application is in communication with a remote computing system/device; See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment).
Claim 4 –
Regarding Claim 4, Khaleghi, Godbole, and Thomson disclose the method of claim 3 in its entirety. Khaleghi further discloses a method, wherein:
the behavioral treatment data is directly recorded into the TN application by a user (See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment; See Khaleghi Par [0092] which discloses receiving new or updated biographical, medical, clinical, therapeutic, and/or diary data, i.e. treatment data; See Khaleghi Par [0094] which discloses the check-in user interface possibly enabling a user to provide updates on how a patient or the user is doing).
Claim 5 –
Regarding Claim 5, Khaleghi, Godbole, and Thomson disclose the method of claim 4 in its entirety. Khaleghi further discloses a method, wherein:
the user, responsive to the one or more therapy note features generated by the TN model, modifies the behavioral treatment data recorded into the TN application to yield a therapy note (See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment; See Khaleghi Par [0092] which discloses receiving new or updated biographical, medical, clinical, therapeutic, and/or diary data, i.e. treatment data; See Khaleghi Par [0094] which discloses the check-in user interface possibly enabling a user to provide updates on how a patient or the user is doing; See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, such that the system can recognize various words, phrases, sentences, or series of sentences).
Claim 6 –
Regarding Claim 6, Khaleghi, Godbole, and Thomson disclose the method of claim 5 in its entirety. Khaleghi further discloses a method, wherein:
the TN application submits the therapy note for approval (See Khaleghi Par [0096] which discloses a percentage likelihood of identifying phrases used in information provided during a check-in, and in some instances of slurred speech or unintelligible speech, an alert, i.e. notification, can be provided to a treating professional that the check-in information, i.e. in the note, needs to be urgently reviewed, i.e. revised), wherein
the therapy note is approved or requires revisions (See Khaleghi Par [0096] which discloses a percentage likelihood of identifying phrases used in information provided during a check-in, and in some instances of slurred speech or unintelligible speech, an alert, i.e. notification, can be provided to a treating professional that the check-in information, i.e. in the note, needs to be urgently reviewed, i.e. revised).
Claim 7 –
Regarding Claim 7, Khaleghi, Godbole, and Thomson disclose the method of claim 6 in its entirety. Khaleghi further discloses a method, wherein:
when the therapy note requires revisions, the TN application sends a notification to the user (See Khaleghi Par [0096] which discloses a percentage likelihood of identifying phrases used in information provided during a check-in, and in some instances of slurred speech or unintelligible speech, an alert, i.e. notification, can be provided to a treating professional that the check-in information, i.e. in the note, needs to be urgently reviewed, i.e. revised).
Claim 8 –
Regarding Claim 8, Khaleghi, Godbole, and Thomson disclose the method of claim 3 in its entirety. Khaleghi further discloses a method, wherein:
the behavioral treatment data is received via an audio sensor, a video device, or both (See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment).
Claim 9 –
Regarding Claim 9, Khaleghi, Godbole, and Thomson disclose the method of claim 8 in its entirety. Khaleghi further discloses a method, wherein:
the audio sensor conveys a dictation from a user to the TN application (See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, and in some instances, the complete speech-to-text file for a given recording may be inserted/accessible for each past and future appointment, an indication as to whether there are one or more appointment recordings and any associated other files for the treatment (e.g. drug tests, blood test, psychiatric reports, orthopedic reports, prescriptions, imaging reports, etc.), wherein
the dictation comprises at least one word of portion thereof (See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, such that the system can recognize various words, phrases, sentences, or series of sentences), and wherein
the TN model converts the dictation into the one or more therapy note features (See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, such that the system can recognize various words, phrases, sentences, or series of sentences).
Claim 10 –
Regarding Claim 10, Khaleghi, Godbole, and Thomson disclose the method of claim 8 in its entirety. Khaleghi further discloses a method, wherein:
the behavioral treatment data acquired via the audio sensor comprises audio data (See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment; See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, such that the system can recognize various words, phrases, sentences, or series of sentences), wherein
the audio data comprises vocal sounds produced by the subject, vocal sounds produced by a caregiver, ambient sounds, or combinations thereof (See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, such that the system can recognize various words, phrases, sentences, or series of sentences), wherein
the vocal sounds comprise onomatopoeic sounds, words, sentences, sentence portions, phrases, phrase portions, conversations, humming, singing, whispering, yelling, sound pattern data, pattern of vocal sounds produced by the subject, pattern of vocal sounds produced by a caregiver, sound volume fluctuations, or combinations thereof (See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, such that the system can recognize various words, phrases, sentences, or series of sentences), and wherein
the TN model converts the audio data into the one or more therapy note features (See Khaleghi Par [0055] which discloses a voice recording or text file generated by the voice-to-text module allowing for convenient and organized viewing of content vocalized in the electronic notebook, i.e. as a note or file, such that the system can recognize various words, phrases, sentences, or series of sentences).
Claim 11 –
Regarding Claim 11, Khaleghi, Godbole, and Thomson disclose the method of claim 8 in its entirety. Khaleghi further discloses a method, wherein:
the behavioral treatment data acquired via the video device comprises video data and optionally audio data (See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment), wherein
the video data comprises visually observable elements of the subject, the subject's spatial position, visually observable elements of a caregiver, the caregiver's spatial position, a body feature thereof, a movement thereof, visually observable elements of the subject's environment, or combinations thereof (See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment; See Khaleghi Par [0100] which discloses real-time or recorded videos or images (optionally with an associated voice track) of the patient and/or significant other, caregiver, family member, etc., to be transmitted, such that the visual content may provide significant or critical information in making mental and/or physical health assessments, such as detecting if someone has suffered a stroke or heart attack), and wherein
the TN model converts the video data and optionally the audio data, respectively, into the one or more therapy note features (See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment; Ss Khaleghi Par [0018] & [0053] which discloses an electronic notebook automatically or upon activation by a user, recording, processing, and reproducing video recordings and associated audio track,, and/or other treatment information in an electronic notebook for future access by varying entities with access, without requiring that the user, patient, and/or other medical professional(s) manually write or type in notes during the appointment).
Claim 12 –
Regarding Claim 12, Khaleghi, Godbole, and Thomson disclose the method of claim 8 in its entirety. Khaleghi further discloses a method, wherein:
the one or more therapy note features are recorded into the TN application to yield the therapy notes (See Khaleghi Par [0053] which discloses recording control which enables video and/or audio of a given appointment, i.e. treatment (e.g. medication, exercise physical therapy, etc.), the electronic notebook generating and/or provide user interfaces textually providing information about the treatment; See Khaleghi Par [0018] & [0053] which discloses an electronic notebook automatically or upon activation by a user, recording, processing, and reproducing video recordings and associated audio track, and/or other treatment information in an electronic notebook for future access by varying entities with access, without requiring that the user, patient, and/or other medical professional(s) manually write or type in notes during the appointment); wherein
a user assesses, in the TN application, the therapy notes (See Khaleghi Par [0096] which discloses a percentage likelihood of identifying phrases used in information provided during a check-in, and in some instances of slurred speech or unintelligible speech, an alert can be provided to a treating professional that the check-in information, i.e. in the note, needs to be urgently reviewed, i.e. revised), wherein
the user revises the therapy notes and/or signals the TN application to submit the therapy notes for approval (See Khaleghi Par [0096] which discloses a percentage likelihood of identifying phrases used in information provided during a check-in, and in some instances of slurred speech or unintelligible speech, an alert can be provided to a treating professional that the check-in information, i.e. in the note, needs to be urgently reviewed, i.e. revised), and wherein
the therapy notes are approved or require revisions (See Khaleghi Par [0096] which discloses a percentage likelihood of identifying phrases used in information provided during a check-in, and in some instances of slurred speech or unintelligible speech, an alert can be provided to a treating professional that the check-in information, i.e. in the note, needs to be urgently reviewed, i.e. revised).
Claim 13 –
Regarding Claim 13, Khaleghi, Godbole, and Thomson disclose the method of claim 12 in its entirety. Khaleghi further discloses a method, wherein:
when the therapy notes require revisions, the TN application sends a notification to the user (See Khaleghi Par [0096] which discloses a percentage likelihood of identifying phrases used in information provided during a check-in, and in some instances of slurred speech or unintelligible speech, an alert, i.e. notification, can be provided to a treating professional that the check-in information, i.e. in the note, needs to be urgently reviewed, i.e. revised).
Claim 15 –
Regarding Claim 15, Khaleghi, Godbole, and Thomson disclose the method of claim 1 in its entirety. Khaleghi further discloses a method, wherein:
the NDD comprises disorders on the autism spectrum or autism spectrum disorder (ASD); attention deficit hyperactivity disorder (ADHD), other specified ADHD, unspecified ADHD; motor disorders, developmental coordination disorder, stereotypic movement disorder, tic disorders, Tourette's disorder or syndrome, persistent or chronic motor or vocal tic disorder, provisional tic disorder, other specified tic disorder, unspecified tic disorder; cerebral palsy; Rett syndrome; intellectual disabilities, intellectual developmental disorder, global developmental delay, unspecified intellectual disability, unspecified intellectual developmental disorder, communication disorders, language disorder, speech sound disorder or phonological disorder, childhood-onset fluency disorder or stuttering; social or pragmatic communication disorder, unspecified communication disorder; specific learning disorder; other NDDs, other specified NDD, unspecified NDD; or combinations thereof (See Khaleghi Par [0045] which discloses a patient category that can be populated, including the patient having Autism Spectrum Disorder; See Khaleghi Par [0046]-[0047] which discloses a patient category for characterizing the patient, including developmental disorders, learning disorders, emotional disorder, psychiatric disorder, chemical dependency, comorbid substance abuse problem, mental illness, etc.; See Khaleghi Par [0077] which discloses diagnoses and conditions for characterizing a patient, including drug addiction, aging, dementia, special needs, seizure disorder, Parkinson’s, cancer, hyperactivity, i.e. ADHD, and/or by treatment side effect associated with various medications, e.g. sleeplessness, nausea, anxiety, etc.).
Claim 17 –
Regarding Claim 17, Khaleghi, Godbole, and Thomson disclose the method implemented via a computing device of claim 1 in its entirety. Furthermore, claim 17 is recited for a system comprising a computing device, the computing device comprising a processor and a non-transitory computer-readable medium includes instructions configured to cause the processor to implement a TN model, which is disclosed by Khaleghi Par [0120]. Therefore, claim 17 is rejected for the same or substantially similar logic/reasonings found in the analysis for claim 1 above, but recited for a computing device comprising a processor and a non-transitory computer-readable medium includes instructions. As such, claim 17 is rejected under 35 U.S.C. 103 in view of Khaleghi, Godbole, and Thomson.
Claim 18 –
Regarding Claim 18, Khaleghi, Godbole, and Thomson disclose the system of claim 17 in its entirety. Khaleghi discloses a system, further comprising:
a mobile device (See Khaleghi Par [0024] & [0124] which discloses the use of a mobile communication device, e.g. a cellphone, laptop, tablet, personal computer, wearables, networked watch, etc.); wherein
the mobile device is selected from the group consisting of a smartphone, a smartwatch, a tablet, a laptop, a personal computer, and combinations thereof; and wherein the application is installed on the mobile device (See Khaleghi Par [0024] & [0124] which discloses the use of a mobile communication device, e.g. a cellphone, laptop, tablet, personal computer, wearables, networked watch, etc.).
Claim 19 –
Regarding Claim 19, Khaleghi, Godbole, and Thomson disclose the method implemented via a computing device of claim 1 in its entirety. The method and steps recited in claim 19 are substantially similar to the methods recited in claim 1. Therefore, claim 19 is rejected for the same or substantially similar logic/reasonings found in the analysis for claim 1 above. As such, claim 19 is rejected under 35 U.S.C. 103 in view of Khaleghi, Godbole, and Thomson.
Claim 20 –
Regarding Claim 20, Khaleghi, Godbole, and Thomson disclose the method of claim 19 in its entirety. Khaleghi discloses a method, wherein:
processing the training behavioral data associated with the plurality of subjects comprises natural language processing, computer vision or combinations thereof (See Khaleghi Par [0054] & [0111] which discloses the use of a voice-to-text module, using language modeling and statistical analysis, and can possibly make use of neural networks (trainable brain-like computer models that reliably recognize patterns) and/or pattern matching, pattern and feature analysis, language modeling and statistical analysis, etc.).
Claim 22 –
Regarding Claim 22, Khaleghi, Godbole, and Thomson disclose the system of claim 17 in its entirety. Khaleghi further discloses a system, wherein:
the application is configured to detect a therapy session audio, record a therapy session audio, detect a therapy session video, record a therapy session video, or a combination thereof via an audio sensor, an audio device, a video sensor, a video device, or combinations thereof (See Khaleghi Par [0018] & [0024] which discloses one or more user terminals recording, processing, and reproducing video data, such as via a camera or a variety of other sensors).
Claim 23 –
Regarding Claim 23, Khaleghi, Godbole, and Thomson disclose the system of claim 22 in its entirety. Khaleghi further discloses a system, wherein:
the audio sensors, the video sensor, or both provide for time-series data (See Khaleghi Par [0018], [0021]-[0022], & [0024] which discloses one or more user terminals recording, processing, and reproducing video data, such as via a camera or a variety of other sensor, including biographical, medical, and clinical information/data; See Khaleghi Par [0043]-[0044] which discloses said biographical, medical, and clinical information/data being used to generate a health timeline, i.e. time-series data), wherein
the time-series data comprises physiological data (See Khaleghi Par [0043]-[0044] which discloses said biographical, medical, and clinical information/data, i.e. physiological data under BRI, being used to generate a health timeline).
Response to Arguments
Applicant's arguments filed 15 April 2026 have been fully considered but they are not persuasive:
Regarding 35 U.S.C. 101 rejections of claims 1-13 & 15-21, Applicant argues on p. 13-16 of Arguments/Remarks that the claims overcome 35 U.S.C. 101 in view of the Memo issued regarding claim limitations encompassing AI in a way that cannot be practically performed in the human mind do not fall within the mental processes grouping of abstract ideas. Applicant further argues in view of the claims amounting to a practical application, at least by a technical improvement to behavioral health documentation systems, for example, from the NLP/ML models being substantially optimized and/or improved. Examiner agrees with Applicant’s arguments. More specifically, Examiner agrees with Applicant in view of newly issued Desjardins memo, that the improvement to the technological components can stem from the machine learning algorithm itself. That is, claims to a method of training a machine learning model can be directed to improvements in the machine learning technology itself. In the instant application, the inventive concept is directed towards a feature extraction model that allows for extraction of content from therapy notes and positively recites “fine tuning a pretrained model on the training feature to yield the TN model” in the independent claims. As such, similarities between the instant application and the newly issued Desjardins memo point towards the TN model found in the instant application and optimization thereof amounts to a practical application in the form of a technological improvement. Therefore the 35 U.SC. 101 rejections for claims 1-13 & 15-23 have been withdrawn.
Regarding 35 U.S.C. 103 rejections of claims 1-13 & 15-21, Applicant argues on p. 16-20 of Arguments/Remarks that independent claims 1, 17, & 19 overcome previous 35 U.S.C. 103 rejections made in view of Khaleghi. More specifically, Applicant argues substantially similar arguments from previous responses regarding the methods being applied to behavior therapy or ABA and that the newly amended limitations overcome previous 35 U.S.C. 103 rejections at least by newly amended limitations regarding specific training aspects of the TN model, preprocessing efforts for said training data, vectorizing the training data, etc. Examiner agrees with Applicant’s arguments. Therefore the previous 35 U.S.C. 103 rejections have been withdrawn for independent claims 1, 17, & 19 and claims dependent therefrom. However, upon further consideration, a new ground of rejection has been made under 35 U.S.C. 103 for independent claims 1, 17, & 19. This new ground of rejection depends on newly cited portions of Khaleghi to read on a TN model, generally training said TN model and applying to NDD patients. However, specific training aspects of the TN model, preprocessing efforts for said training data, vectorizing the training data, etc., met instead by Godbole and Thomson. Therefore, claims 1, 17, & 19 and claims dependent therefrom remain rejected under 35 U.S.C. 103.
Regarding 35 U.S.C. 103 rejections of claims 1-13 & 15-21, Applicant argues on p. 20 of Arguments/Remarks that claims 22-23 are new and depend from claim 17 which is purportedly allowable over the prior art, and therefore claims 22-23 should also be allowable by virtue of dependency. Examiner respectfully disagrees with Applicant’s arguments. As established above, claim 17 remains rejected under 35 U.S.C. 103 and is not allowable over the prior art. Therefore, Applicant’s arguments regarding claim 17 being purportedly allowable over the prior art are rendered moot. As such, claims 22-23 are not allowable over the prior art and remain rejected under 35 U.S.C. 103. Therefore, claims 1, 17, & 19 and claims dependent therefrom remain rejected under 35 U.S.C. 103.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Castine et al. (U.S. Patent Publication No. 2020/0143913) discloses a system wherein unstructured text items are processed to identify elements of the unstructured text items relevant to classification rules of quality metrics applicable to services provided by a healthcare provider with respect to diseases, conditions, or interventions of patients
Bernard et al. (U.S. Patent No. 10,140,421) discloses a system for selecting a medical scan for transmission, such that annotation data can be automatically generated.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HUNTER J RASNIC whose telephone number is (571)270-5801. The examiner can normally be reached M-F 8am-5:30pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Shahid Merchant can be reached at (571) 270-1360. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/H.R./Examiner, Art Unit 3684
/Shahid Merchant/Supervisory Patent Examiner, Art Unit 3684
Prosecution Insights