# US 2026/0253700 A1 · System and Method for Conversational Personalization of Therapeutic Outputs Using Biomarker-Driven Retrieval-Augmented Generation

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

- Number: US 2026/0253700 A1
- Document ID: US20260253700A1
- Status: Published application
- Kind: A1
- Application number: 19/548,019
- Filed: 2026-02-24
- Published: 2026-08-27
- Earliest claimed: 2025-02-25
- Inventors: Médéric Degoy
- Web page: https://patentgrep.com/patent/US20260253700A1

## CPC

- G16H 20/70: relating to mental therapies, e.g. psychological therapy or autogenous training
- A61B 5/0205: Simultaneously evaluating both cardiovascular conditions and different types of body conditions, e.g. heart and respiratory condition
- A61B 5/165: {Evaluating the state of mind, e.g. depression, anxiety}
- A61B 5/375: using biofeedback
- A61B 5/4836: {Diagnosis combined with treatment in closed-loop systems or methods (A61B5/0036 takes precedence)}
- A61B 5/486: {Biofeedback (using electroencephalography [EEG] A61B5/375)}
- A61B 5/7257: {using Fourier transforms}
- G01S 7/356: {involving particularities of FFT processing}
- G01V 1/307: {for determining seismic attributes, e.g. amplitude, instantaneous phase or frequency, reflection strength or polarity}
- G16H 10/20: for electronic clinical trials or questionnaires
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 20/00: ICT specially adapted for therapies or health-improving plans, e.g. for handling prescriptions, for steering therapy or for monitoring patient compliance
- G16H 20/30: relating to physical therapies or activities, e.g. physiotherapy, acupressure or exercising
- G16H 40/63: for local operation
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/30: for calculating health indices; for individual health risk assessment
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- G06F 2218/08: Feature extraction
- G06F 2218/10: by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
- G06V 10/62: relating to a temporal dimension, e.g. time-based feature extraction; Pattern tracking
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01V: GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; DETECTING MASSES OR OBJECTS; TAGS (means for indicating the location of accidentally buried, e.g. snow-buried, persons A63B29/02)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A computer-implemented method enables conversational personalization of therapeutic outputs using biomarker-specific retrieval-augmented generation. Physiological biomarkers and their relational mapping, integral coherence scores, and causal chains are provided as context to a large language model or specialized AI assistants. The system generates tailored explanations, asks clarifying questions, and iteratively refines suggestions based on user responses and updated biomarker data. Specialized assistants, each focused on a subset of biomarkers or categories, interact with the user to modify therapeutic protocols in real time. Live biofeedback can be triggered during dialogue to re-compute features and adapt outputs, achieving highly individualized coherence restoration and health and wellness guidance.

## Claims

### Claim 1

A computer-implemented method for conversational personalization of therapeutic outputs, comprising:
obtaining a current set of physiological biomarkers associated with a user, together with their relational mapping, integral coherence scores, and causal chains;
providing said biomarkers, scores, and chains as context to a retrieval-augmented generation system or large language model;
generating, via the model, personalized therapeutic suggestions, explanations, or clarifying questions;
receiving one or more user responses to the questions;
updating the context with the user responses and, if necessary, re-computing or retrieving updated biomarker data;
iteratively refining the model's output in a multi-turn conversational loop; and
modifying at least one therapeutic output parameter in real time based on the refined output.

### Claim 2 (depends on 1)

The method of claim 1, wherein multiple specialized AI assistants are employed, each assistant configured to receive and process a subset of biomarkers, relational mapping, or coherence scores corresponding to a specific physiological, energetic, or psychological category.

### Claim 3 (depends on 2)

The method of claim 2, wherein the specialized assistants interact with the user in parallel or sequence to refine understanding, ask category-specific clarifying questions, or propose targeted modifications to the therapeutic protocol.

### Claim 4 (depends on 1)

The method of claim 1, further comprising triggering real-time biofeedback measurement during the conversation, re-computing one or more biomarkers or relational features based on the measurement, and updating the model context accordingly.

### Claim 5 (depends on 1)

The method of claim 1, wherein the therapeutic output modification includes at least one of: adjusting the selection or weighting of audio frequencies in a harmonic boost mode, re-prioritizing resources and priorities in a protocol, modifying guided session content, or altering micro-current delivery parameters in a connected device.

### Claim 6

A system for conversational personalization of therapeutic outputs, comprising:
a processor;
memory storing instructions that, when executed, cause the processor to obtain physiological biomarkers, relational mapping, coherence scores, and causal chains;
provide said data as context to a retrieval-augmented generation system or large language model;
generate personalized suggestions or questions;
receive user responses;
update context iteratively; and
modify therapeutic output parameters in real time based on the conversational loop.

### Claim 7 (depends on 6)

The system of claim 6, further comprising a plurality of specialized AI assistants, each configured to handle a subset of biomarker categories or relational aspects.

### Claim 8 (depends on 6)

The system of claim 6, further comprising a biofeedback interface configured to trigger live physiological measurements during the conversation and update biomarker data in the model context.

### Claim 9 (depends on 1)

The method of claim 1, wherein the model generates explanations of biomarker states, coherence scores, relational influences, or therapeutic implications in natural language tailored to the user's current context and knowledge level.

### Claim 10 (depends on 1)

The method of claim 1, wherein the conversational loop continues until the therapeutic protocol achieves a target coherence level or user-defined goal, as determined by updated integral coherence scores or user feedback.
