# US 2023/0053429 A1 · System and method for automatic analysis of texts in psychotherapy, counseling, and other mental health management activities

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0053429 A1
- Document ID: US20230053429A1
- Status: Published application
- Kind: A1
- Application number: 17/889,415
- Filed: 2022-08-17
- Published: 2023-02-23
- Earliest claimed: 2021-08-18
- Assignees: Mind Medicine, Inc.
- Applicants: Mind Medicine, Inc.
- Inventors: Adam KOLAR; Martin MAJERNIK; Miguel Amavel dos Santos PINHEIRO; Daniel R. KARLIN; Robert BARROW
- Web page: https://patentgrep.com/patent/US20230053429A1

## CPC

- A61B 5/16: Devices for psychotechnics (using teaching or educational appliances G09B1/00 - G09B7/00); Testing reaction times {; Devices for evaluating the psychological state}
- A61B 5/7267: {involving training the classification device}
- A61B 5/165: {Evaluating the state of mind, e.g. depression, anxiety}
- A61B 5/4803: {Speech analysis specially adapted for diagnostic purposes}
- G06F 40/279: Recognition of textual entities
- G06F 40/30: Semantic analysis
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 20/70: relating to mental therapies, e.g. psychological therapy or autogenous training
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/50: for simulation or modelling of medical disorders
- A61B 5/0077: {Devices for viewing the surface of the body, e.g. camera, magnifying lens}
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

A method of analyzing a patient's mental state, by automatically processing, integrating, and analyzing text-based and audio-based sources from the patient and clinical staff, and generating real-time outcomes and predictions. A system for processing, analyzing, and managing a patient's input including a data pool, model HUB, search service, topic modeling service, mental health related prediction service, and analytics all in electronic communication. A method of analyzing a patient, by processing, analyzing, and managing a patient's and clinical staff's text and audio input, and informing and augmenting diagnostic and prognostic processes, identifying improvement and deterioration of a patient's mental state, and identifying adverse events in psychotherapy, counseling, and other mental health management activities. A system for processing, analyzing, and managing clinical and diagnostic texts, and audio transcripts.

## Claims

### Claim 1

A method of analyzing a patient's mental state, including the steps of:
automatically processing, integrating, and analyzing text-based and audio-based sources from the patient and clinical staff; and
generating real-time outcomes and predictions.

### Claim 2 (depends on 1)

The method of claim 1, wherein the sources are chosen from the group consisting of analysis of free-text and structured text responses to diagnostic assignments/tasks, patient's diaries, journals, worry script, transcripts of patient-clinical staff discussions, written/transcribed answers to structured set of questions, and audio recordings.

### Claim 3 (depends on 1)

The method of claim 1, further providing an assessment of pathological and non-pathological mental states from patient generated text and audio.

### Claim 4 (depends on 1)

The method of claim 1, wherein said generating step further includes presenting results in a visual interface for a user.

### Claim 5 (depends on 1)

The method of claim 1, further providing an assessment of specific mental disorder severity and progression from patient generated text and audio.

### Claim 6 (depends on 1)

The method of claim 1, further including the step of highlighting parts of text with high mental disorder severity.

### Claim 7 (depends on 1)

The method of claim 1, further including the step of providing topical analysis of psychotherapeutic texts, audio transcripts, and patient's reports.

### Claim 8 (depends on 1)

The method of claim 1, further including the step of projecting psychotherapeutic session content into a topic map of relations.

### Claim 9 (depends on 1)

The method of claim 1, further including the step of predicting topics' and keywords' occurrence in a next therapeutic session, based on their presence in previous sessions.

### Claim 10 (depends on 1)

The method of claim 1, further providing patient generated text-search for patients reporting similar behavioral, psychological or emotional symptoms, disorder indications or mental states.

### Claim 11 (depends on 1)

The method of claim 1, further providing the step of summarizing of a volume of patient generated texts into a shorter abstracts with clinical and diagnostic relevance.

### Claim 12 (depends on 1)

The method of claim 1, further including the step of question answering on the patient generated text.

### Claim 13 (depends on 1)

The method of claim 1, further including the step of text searching over the patient generated text and transcripts based on text model embeddings, restricted by clinically relevant topics, symptoms, or indications.

### Claim 14 (depends on 1)

The method of claim 1, further including the step of pairing critical psychological events with concrete entities in the patient generated text identified via entity recognition model.

### Claim 15

A system for processing, analyzing, and managing a patient's input comprising a data pool, model HUB, search service, topic modeling service, mental health related prediction service, and analytics all in electronic communication.

### Claim 16 (depends on 15)

The system of claim 15, wherein said search service uses said data pool content to retreat query and generate a search result.

### Claim 17 (depends on 15)

The system of claim 15, wherein said topic modeling service uses said data pool to define topics for topic extraction.

### Claim 18 (depends on 17)

The system of claim 17, wherein said topic modeling service receives video stream data and diaries from said analytics and sends back topic modeling related data.

### Claim 19 (depends on 15)

The system of claim 15, wherein said model HUB provides retrained models for client facing features and services.

### Claim 20 (depends on 15)

The system of claim 15, wherein said search service receives queries, text, and metadata from said analytics and sends back most relevant existing content data pool, and transforms query and text metadata from analytics via model version coming from said model HUB and uses a new representation of current text to search said data pool.

### Claim 21 (depends on 15)

The system of claim 15, wherein said mental health related prediction service receives video stream data, clinician notes, and diaries from said analytics and sends back assessments and highlights in text.

### Claim 22 (depends on 15)

The system of claim 15, wherein said analytics includes user-facing metrics including visualizations, notifications, lists, counters, and charts and receives input from and provides feedback to said search service, said topic modeling service, and said mental health related prediction service.

### Claim 23

A method of analyzing a patient, including the steps of:
processing, analyzing, and managing a patient's and clinical staff's text and audio input;
informing and augmenting diagnostic and prognostic processes, identifying improvement and deterioration of a patient's mental state; and
identifying adverse events in psychotherapy, counseling, and mental health management activities.

### Claim 24

A system for processing, analyzing, and managing clinical and diagnostic texts and audio transcripts comprising a data pool, model HUB, search service, topic modeling service, mental health related prediction service, and analytics all in electronic communication, wherein said system is able to identify and highlight recurrent topics, critical moments, and clinically valuable moments in clinical staff's feetext notes, to manage content/information load for clinical professionals, and to offer a retrospective view or an overview of a patient's treatment progress.

### Claim 25

A method of analyzing clinical and diagnostic texts, including the steps of:
processing, analyzing, and managing clinical and diagnostic texts;
identifying and highlighting recurrent topics, critical moments, and clinically valuable moments in clinical staff's feetext notes;
managing content/information load for clinical professionals; and
offering a retrospective view or an overview of a patient's treatment progress.

### Claim 26 (depends on 25)

The method of claim 25, wherein sources of input are chosen from the group consisting of clinical staff's clinical notes from patient's treatment and therapy, initial assessments notes, progress notes, non-clinical notes from patient's treatment and therapy, drug administration notes, clinical and research staff notes, treatment plans, prescriptions, audio recordings, release documentation, and combinations thereof.

### Claim 27 (depends on 25)

The method of claim 25, further including the step of assessing pathological and non-pathological mental states from clinical and diagnostic texts and audio.

### Claim 28 (depends on 25)

The method of claim 25, further including the step of assessing specific mental disorder severity and progression from clinical and diagnostic texts and audio.

### Claim 29 (depends on 25)

The method of claim 25, further including the step of highlighting parts of clinical and diagnostic texts with high mental disorder severity.

### Claim 30 (depends on 25)

The method of claim 25, further including the step of providing topical analysis of clinical and diagnostic texts, audio transcripts, and clinical staff notes and reports.

### Claim 31 (depends on 25)

The method of claim 25, further including the step of projecting clinical and diagnostic texts and audio generated at psychotherapeutic sessions into a topic map of relations.

### Claim 32 (depends on 25)

The method of claim 25, further including the step of predicting topics' and keywords' occurrence in the next therapeutic session, based on their presence in previous sessions.

### Claim 33 (depends on 25)

The method of claim 25, further including the step of providing clinical and diagnostic text-search for patients reporting similar behavioral, psychological or emotional symptoms, disorder indications or mental states.

### Claim 34 (depends on 25)

The method of claim 25, further including the step of summarizing of a volume of clinical and diagnostic texts into a shorter abstracts with clinical and diagnostic relevance.

### Claim 35 (depends on 25)

The method of claim 25, further including the step of question answering on the clinical and diagnostic texts.

### Claim 36 (depends on 25)

The method of claim 25, further including the step of text searching over the clinical and diagnostic text and transcripts based on text model embeddings, restricted by clinically relevant topics, symptoms, or indications.

### Claim 37 (depends on 25)

The method of claim 25, further including the step of pairing critical psychological events with concrete entities in the clinical and diagnostic texts identified via entity recognition model.

### Claim 38 (depends on 25)

The method of claim 25, wherein said generating step further includes presenting results in a visual interface for a user.
