# US 2026/0066066 A1 · Generating Clinical Documentation Using Large Language Models and Artificial Intelligence

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

- Number: US 2026/0066066 A1
- Document ID: US20260066066A1
- Status: Published application
- Kind: A1
- Application number: 18/967,365
- Filed: 2024-12-03
- Published: 2026-03-05
- Earliest claimed: 2024-08-28
- Assignees: Orchid Exchange Inc.
- Applicants: Orchid Exchange Inc.
- Inventors: Yipeng Peng; Joseph Pomianowski; Soo Yeon Lee
- Web page: https://patentgrep.com/patent/US20260066066A1

## CPC

- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G06F 40/186: Templates
- G10L 15/183: using context dependencies, e.g. language models
- G16H 15/00: ICT specially adapted for medical reports, e.g. generation or transmission thereof
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 80/00: ICT specially adapted for facilitating communication between medical practitioners or patients, e.g. for collaborative diagnosis, therapy or health monitoring
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

Systems and methods generate clinical documentation using large language models and artificial intelligence (AI). A template management module is provided to create customizable templates. A processing unit can receive input data from various sources and use AI to generate transcripts, summarize sessions, and produce clinical documentation such as clinical notes. The processing unit may also generate Current Procedural Terminology (CPT) and diagnosis codes, generate after-visit summaries, and generate referral letters. The AI may be trained on past clinical notes and can adapt to the clinician's style over time, with a feedback loop for continuous improvement. Additional features include cohort-based training, real-time language translation, predictive text, and analytics for documentation trends. The system supports customization of note length, style, and keywords, as well as integration with external medical databases and patient portals.

## Claims

### Claim 1

A system for generating clinical documentation using large language models or artificial intelligence (AI), comprising:
a data acquisition module configured to receive clinical data from at least one of dictation, telehealth session audio recordings, telehealth session video recordings, uploaded audio files, uploaded video files, and clinician-supplied data streams;
a processing unit configured to execute at least one machine learning algorithm to:
(i) generate a transcription of the clinical data;
(ii) receive a clinician-supplied data stream;
(iii) when the clinician-supplied data stream comprises at least one of the telehealth session audio recordings, the telehealth session video recordings, the uploaded audio files, or the uploaded video files, generate an AI-generated summary of at least a portion of the clinical data in accordance with configuration data;
(iv) when the clinician-supplied data stream comprises the dictation, receive a user-provided synopsis corresponding to the clinical data;
(v) generate, using a large language model engine, a draft clinical note using at least one of the transcription, an automatically generated summarization of the transcription, and a user-inputted summarization; and
(vi) generate, responsive to the configuration data, at least one structured clinical documentation derived from the draft clinical note;
a template management module configured to enable a selection, at any stage of a clinical documentation workflow, of a customizable template and to apply the customizable template, at any stage of the clinical documentation workflow, to at least one of the transcription, the AI-generated summary, a clinician-provided synopsis, and the draft clinical note, wherein the clinical documentation workflow comprises the stages (i)-(vi); and
a clinician interface configured to:
display the draft clinical note and any of the at least one structured clinical documentation, and
capture feedback for iterative refinement of subsequent clinical documentation.

### Claim 2 (depends on 1)

The system of claim 1, wherein the data acquisition module comprises a real-time transcription feature configured to transcribe both audio data and video data and to provide adaptability across a plurality of clinical environments.

### Claim 3 (depends on 1)

The system of claim 1, wherein the data acquisition module is adaptable to a plurality of data formats.

### Claim 4 (depends on 1)

The system of claim 1, wherein the processing unit is further configured to execute natural language processing (NLP) techniques trained on clinical notes across a plurality of medical specialties to provide specialized interpretation.

### Claim 5 (depends on 4)

The system of claim 4, wherein the plurality of medical specialties includes behavioral health.

### Claim 6 (depends on 1)

The system of claim 1, further comprising a coding module configured to automatically generate Current Procedural Terminology (CPT) and International Classification of Diseases (ICD) codes using a content and a structure of an AI-generated clinical documentation, and configured to comply with healthcare regulatory standards.

### Claim at position 7

7-30. (canceled)

### Claim 31 (depends on 1)

The system of claim 1, wherein the at least one structured clinical documentation comprises at least one of a Current Procedural Terminology (CPT) code or an International Classification of Diseases (ICD) code.

### Claim 32 (depends on 31)

The system of claim 31, wherein generation of the CPT code or the ICD code is performed only when a clinician-selectable coding mode is enabled.

### Claim 33 (depends on 1)

The system of claim 1, wherein the at least one structured clinical documentation comprises a treatment plan derived from the draft clinical note.

### Claim 34 (depends on 1)

The system of claim 1, wherein the template management module is configured to apply the customizable template to the draft clinical note before the structured clinical documentation is generated.

### Claim 35 (depends on 1)

The system of claim 1, wherein the clinician interface is configured to capture feedback in a structured format that is used to retrain at least one machine learning model in the processing unit.

### Claim 36 (depends on 1)

The system of claim 1, wherein the data acquisition module is further configured to receive at least one of physiological-sensor data, data originating from a virtual-reality platform, and data originating from an augmented-reality platform.
