# US 2026/0253715 A1 · Leveraging large language models for standardizing clinical data

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

- Number: US 2026/0253715 A1
- Document ID: US20260253715A1
- Status: Published application
- Kind: A1
- Application number: 19/682,725
- Filed: 2026-05-20
- Published: 2026-08-27
- Earliest claimed: 2023-12-01
- Assignees: Genentech, Inc.; Hoffmann-La Roche Inc.
- Applicants: Genentech, Inc.; Hoffmann-la Roche Inc.
- Inventors: Yogesh P. Pandit; Arindam Sett; Mrunal Shriram Yadav; Somaye Sadat Hashemifar; Seyed Mohammadmoshen Hejrati
- Web page: https://patentgrep.com/patent/US20260253715A1

## CPC

- G06F 16/84: Mapping; Conversion
- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- G06F 16/3347: {using vector based model}
- G06F 16/90332: {Natural language query formulation or dialogue systems}
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- 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

## Abstract

Disclosed are various embodiments for leveraging large language models (LLMs) and retrieval-augmented generation (RAG) for data standardization of clinical AI data. A query comprising a target dataset that needs to be standardized and a dataset dictionary can be obtained. Augmented data can be extracted from an external source. A prompt including the query and the augmented data can be generated and applied to a large language model configured to output a response to the query. The response can include the target dataset standardized according to a standard format.

## Claims

### Claim 1

A system, comprising:
a computing device comprising a processor and a memory; and
machine-readable instructions stored in the memory that, when executed by the processor, cause the computing device to at least:
obtain a query comprising a target dataset and a dataset dictionary;
generate a plurality of vector embeddings based at least in part on the dataset dictionary and the target dataset;
obtain augmented data from an external source based at least in part on the plurality of vector embeddings;
generate a prompt comprising the query and the augmented data;
apply the prompt to a large language model configured to output a response to the query based at least in part on the prompt; and
transmit the response to the query to a computing device.

### Claim 2 (depends on 1)

The system of claim 1, wherein the target dataset comprises clinical data.

### Claim 3 (depends on 1)

The system of claim 1, wherein the external source comprises a vector database comprising a plurality of documents formatted according to a standardized format.

### Claim 4 (depends on 3)

The system of claim 3, wherein the response comprises the target dataset formatted according to the standardized format.

### Claim 5 (depends on 4)

The system of claim 4, wherein the standardized format comprises Fast Healthcare Interoperability Resources (FHIR) format.

### Claim 6 (depends on 1)

The system of claim 1, wherein the prompt is generated based at least in part on Retrieval-Augmented Generation (RAG).

### Claim 7

A method, comprising:
obtaining, via at least one computing device, a query comprising a target dataset and a dataset dictionary;
generating, via the at least one computing device, a plurality of vector embeddings based at least in part on the dataset dictionary and the target dataset;
obtaining, via the at least one computing device, augmented data from an external source based at least in part on the plurality of vector embeddings;
generating, via the at least one computing device, a prompt comprising the query and the augmented data;
applying, via the at least one computing device, the prompt to a large language model configured to output a response to the query based at least in part on the prompt; and
transmitting, via the at least one computing device, the response to the query to a computing device.

### Claim 8 (depends on 7)

The method of claim 7, wherein the target dataset comprises clinical data.

### Claim 9 (depends on 7)

The method of claim 7, wherein the external source comprises a vector database comprising a plurality of documents formatted according to a standardized format.

### Claim 10 (depends on 9)

The method of claim 9, wherein the response comprises the target dataset formatted according to the standardized format.

### Claim 11 (depends on 10)

The method of claim 10, wherein the standardized format comprises Fast Healthcare Interoperability Resources (FHIR) format.

### Claim 12 (depends on 7)

The method of claim 7, wherein the prompt is generated based at least in part on Retrieval-Augmented Generation (RAG).

### Claim 13

A non-transitory, computer-readable medium, comprising machine-readable instructions that, when executed by a processor of a computing device, cause the computing device to at least:
obtain a query comprising a target dataset and a dataset dictionary;
generate a plurality of vector embeddings based at least in part on the dataset dictionary and the target dataset;
obtain augmented data from an external source based at least in part on the plurality of vector embeddings;
generate a prompt comprising the query and the augmented data;
apply the prompt to a large language model configured to output a response to the query based at least in part on the prompt; and
transmit the response to the query to a computing device.

### Claim 14 (depends on 13)

The non-transitory, computer-readable medium of claim 13, wherein the target dataset comprises clinical data.

### Claim 15 (depends on 13)

The non-transitory, computer-readable medium of claim 13, wherein the external source comprises a vector database comprising a plurality of documents formatted according to a standardized format.

### Claim 16 (depends on 15)

The non-transitory, computer-readable medium of claim 15, wherein the response comprises the target dataset formatted according to the standardized format.

### Claim 17 (depends on 13)

The non-transitory, computer-readable medium of claim 13, wherein the standardized format comprises Fast Healthcare Interoperability Resources (FHIR) format.

### Claim 18 (depends on 13)

The non-transitory, computer-readable medium of claim 13, wherein the prompt is generated based at least in part on Retrieval-Augmented Generation (RAG).
