# US 2026/0310975 A1 · Training and Using a Neuromodulation Large Language Model for Neuromodulation

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

- Number: US 2026/0310975 A1
- Document ID: US20260310975A1
- Status: Published application
- Kind: A1
- Application number: 19/637,214
- Filed: 2026-04-02
- Published: 2026-10-08
- Earliest claimed: 2025-04-07
- Assignees: Reach Neuro, Inc.
- Applicants: Reach Neuro, Inc.
- Inventors: Marc Philip Powell; Marco Capogrosso; Douglas Weber; Amir Barati Farimani
- Web page: https://patentgrep.com/patent/US20260310975A1

## CPC

- G06N 3/0895: Weakly supervised learning, e.g. semi-supervised or self-supervised learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The disclosure includes a system and method for obtaining, at a stimulator, a set of kinematic parameters at least one kinematic parameter determined specifically for a subject, at least in part, by a first machine learning algorithm neuromodulation large language model (LLM); and delivering, by the stimulator, electrical stimulation via an electrode array, the electrical stimulation defined by the set of kinematic parameters, wherein the electrode array comprises a plurality of electrodes, the electrode array is functionally coupled to a nervous system of the subject by electrical stimulation, and, subsequent to delivering the electrical stimulation defined by the set of kinematic parameters to the subject, the subject achieves a physiological function with reduced motor impairment.

## Claims

### Claim 1

A system comprising:
an electrode array comprising a plurality of electrodes, the electrode array being functionally coupled to a nervous system of a subject by electrical stimulation, the electrical stimulation reducing motor impairment in the subject so that the subject may perform a physiological function; and
a stimulator delivering the electrical stimulation via the electrode array, the electrical stimulation defined by a set of kinematic parameters, wherein:
at least one kinematic parameter in the set of kinematic parameters is:
determined, at least in part, by a neuromodulation large language model (LLM), specifically for the subject; and
responsive to a prompt and based on subject-specific context data; and
when the set of kinematic parameters are delivered to the subject, the subject achieves a physiological function with reduced motor impairment.

### Claim 2 (depends on 1)

The system according to claim 1, wherein the subject-specific context data comprises one or more of:
a neuromuscular map specific to the subject;
a kinematic model specific to the subject; and
a patient history representing a subject’s prior interactions with the neuromodulation LLM.

### Claim 3 (depends on 1)

The system according to claim 1 comprising:
a processor; and
a memory, the memory storing instructions that, when executed by the processor, cause the system to:
obtain a base large language model LLM;
obtain domain knowledge data;
train a first intermediary LLM by pretraining the base LLM using the domain knowledge data;
tune the first intermediary LLM based on a plurality of prompt-response pairs;
perform preference optimization; and
output the neuromodulation LLM.

### Claim 4 (depends on 3)

The system according to claim 3, wherein one or more of the base LLM and the neuromodulation LLM are an open weight model.

### Claim 5 (depends on 3)

The system according to claim 3, wherein the base LLM is a self-hosted model selected from one or more of: Large Language Model Meta Artificial Intelligence (Llama), Mistral, Gemma, Qwen, Deepseek, and Command R+.

### Claim 6 (depends on 3)

The system according to claim 3, wherein the domain knowledge data comprises one or more of:
curated scientific or clinical literature related to one or more of: neuromuscular rehabilitation, implantable stimulation systems, muscle activation dynamics, and biomechanical motor control;
publications or technical reports describing one or more of: stimulation strategies, rehabilitation protocols, and observed physiological responses;
medical or anatomy texts describing a neuromuscular system;
scientific journals;
textbooks; and
text describing clinical trials.

### Claim 7 (depends on 3)

The system according to claim 3, wherein the plurality of prompt-response pairs, include a subset of prompt-response pairs based on the domain knowledge data.

### Claim 8 (depends on 3)

The system according to claim 3, wherein the plurality of prompt-response pairs, include a subset of prompt-response pairs based on patient history, the patient history associated with prior prompts associated with one or more patients and prior responses output by one or more of a clinician and a prior version of the neuromodulation LLM.

### Claim 9 (depends on 3)

The system according to claim 3, wherein one or more of the tuning and the preference optimization comprise: one or more of supervised fine-tuning, full fine-tuning, parameter-efficient fine-tuning, reinforcement learning from human feedback, direct preference optimization, proximal policy optimization, and odds ratio preference optimization.

### Claim 10 (depends on 1)

The system according to claim 1 comprising:
a controller comprising:
a processor; and
a memory, the memory storing instructions that, when executed by the processor, cause the system to:
present, to a user, a user interface;
receive a user prompt via the user interface, wherein the user prompt is a natural language prompt regarding one or more of the subject’s physiological function and the set of kinematic parameters delivered to the subject;
receive a response including the at least one kinematic parameter in the set of kinematic parameters, the at least one kinematic parameter determined, at least in part, by the neuromodulation LLM and modifying a prior value; and
cause the stimulator to deliver the set of kinematic parameters to the subject.

### Claim 11

A method comprising:
obtaining, at a stimulator, a set of kinematic parameters at least one kinematic parameter determined specifically for a subject, at least in part, by a first machine learning algorithm neuromodulation large language model (LLM) responsive to a prompt and based on subject-specific context data; and
delivering, by the stimulator, electrical stimulation via an electrode array, the electrical stimulation defined by the set of kinematic parameters, wherein the electrode array comprises a plurality of electrodes, the electrode array is functionally coupled to a nervous system of the subject by electrical stimulation, and, subsequent to delivering the electrical stimulation defined by the set of kinematic parameters to the subject, the subject achieves a physiological function with reduced motor impairment.

### Claim 12 (depends on 11)

The method according to claim 11, wherein the subject-specific context data comprises one or more of:
a neuromuscular map specific to the subject;
a kinematic model specific to the subject; and
a patient history representing a subject’s prior interactions with the neuromodulation LLM.

### Claim 13 (depends on 11)

The method according to claim 11 comprising:
obtaining a base large language model LLM;
obtaining domain knowledge data;
training a first intermediary LLM by pretraining the base LLM using the domain knowledge data;
tuning the first intermediary LLM based on a plurality of prompt-response pairs;
performing preference optimization; and
outputting the neuromodulation LLM.

### Claim 14 (depends on 13)

The method according to claim 13, wherein one or more of the base LLM and the neuromodulation LLM are an open weight model.

### Claim 15 (depends on 13)

The method according to claim 13, wherein the base LLM is a self-hosted model selected from one or more of: Large Language Model Meta Artificial Intelligence (Llama), Mistral, Gemma, Qwen, Deepseek, and Command R+.

### Claim 16 (depends on 13)

The method according to claim 13, wherein the domain knowledge data comprises one or more of:
curated scientific or clinical literature related to one or more of: neuromuscular rehabilitation, implantable stimulation systems, muscle activation dynamics, and biomechanical motor control;
publications or technical reports describing one or more of: stimulation strategies, rehabilitation protocols, and observed physiological responses;
medical or anatomy texts describing a neuromuscular system;
scientific journals;
textbooks; and
text describing clinical trials.

### Claim 17 (depends on 13)

The method according to claim 13, wherein the plurality of prompt-response pairs, include a subset of prompt-response pairs based on the domain knowledge data.

### Claim 18 (depends on 13)

The method according to claim 13, wherein the plurality of prompt-response pairs, includes on a subset of prompt-response pairs based on patient history, the patient history associated with prior prompts associated with one or more patients and prior responses output by one or more of a clinician and a prior version of the neuromodulation LLM.

### Claim 19 (depends on 13)

The method according to claim 13, wherein one or more of the tuning and the preference optimization comprise: one or more of supervised fine-tuning, full fine-tuning, parameter-efficient fine-tuning, reinforcement learning from human feedback, direct preference optimization, proximal policy optimization, and odds ratio preference optimization.

### Claim 20 (depends on 11)

The method according to claim 11 comprising:
presenting, to a user, a user interface;
receiving a user prompt via the user interface, wherein the user prompt is a natural language prompt regarding one or more of the subject’s physiological function and the set of kinematic parameters delivered to the subject;
receiving a response including the at least one kinematic parameter in the set of kinematic parameters, the at least one kinematic parameter determined, at least in part, by the neuromodulation LLM and modifying a prior value; and
causing the stimulator to deliver the set of kinematic parameters to the subject.
