# US 12,001,464 B1 · System and method for medical data governance using large language models

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

- Number: US 12,001,464 B1
- Document ID: US12001464B1
- Status: Granted
- Kind: B1
- Application number: 18/417,511
- Filed: 2024-01-19
- Granted: 2024-06-04
- Earliest claimed: 2024-01-19
- Assignees: OneSource Solutions International, Inc.
- Applicants: OneSource Solutions International, INC
- Inventors: Harold Arkoff; Vedran Jukic
- Web page: https://patentgrep.com/patent/US12001464B1

## CPC

- G06F 16/3334: {Selection or weighting of terms from queries, including natural language queries}
- G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes}
- G06F 40/40: Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30)
- G16H 10/60: for patient-specific data, e.g. for electronic patient records
- G16H 40/20: for the management or administration of healthcare resources or facilities, e.g. managing hospital staff or surgery rooms
- G16H 50/20: for computer-aided diagnosis, e.g. based on medical expert systems
- G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients
- 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

A system for medical data governance using large language models is disclosed. The system receives a user input including at least one search query to retrieve first medical data from one or more medical data governance (MDG) databases. The system applies one or more large language models (LLMs) on the received at least one search query, wherein the one or more LLMs are pre-trained models. The system determines metadata associated with the at least one search query based on the application of the one or more LLMs on the received search query. The system queries a first MDG database of the one or more MDG databases based on the determined metadata to retrieve the first medical data. The system outputs the retrieved first medical data.

## Claims

### Claim 1

A system using large language models to process medical data comprising:
circuitry configured to receive a user input including at least one search query to retrieve first medical data from one or more medical data governance (MDG) databases;
apply one or more large language models (LLMs) on the received at least one search query, wherein the one or more LLMs are pre-trained models;
determine metadata associated with the at least one search query based on the application of the one or more LLMs on the received search query;
query a first MDG database of the one or more MDG databases based on the determined metadata to retrieve the first medical data;
extract, from the first MDG database, raw data associated with the determined metadata based on the querying the first MDG database;
generate one or more constructs associated with the one or more LLMs to be applied on the extracted raw data, wherein the one or more constructs are associated with the determined metadata;
retrieve the first medical data based on the application of the generated one or more constructs on the extracted raw data; and
output the retrieved first medical data.

### Claim 2 (depends on 1)

The system according to claim 1, wherein the circuitry is further configured to:
receive real-time medical data associated with at least one user from one or more medical devices associated with the at least one user;
determine at least one upcoming event associated with a medical condition of the at least one user based on the received real-time medical data and the one or more MDG databases; and
output the determined at least one upcoming event.

### Claim 3 (depends on 1)

The system according to claim 1, wherein the circuitry is further configured to:
determine at least one keyword from the determined metadata, wherein the at least one keyword is associated with the at least one search query;
select the first MDG database of the one or more MDG databases based on the determined at least one keyword; and
query the selected first MDG database of the one or more MDG databases.

### Claim 4

A method of using large language models to process medical data comprising:
receiving a user input including at least one search query to retrieve first medical data from one or more medical data governance (MDG) databases;
applying one or more large language models (LLMs) on the received at least one search query, wherein the one or more LLMs are pre-trained models;
determining metadata associated with the at least one search query based on the application of the one or more LLMs on the received search query;
querying a first MDG database of the one or more MDG databases based on the determined metadata to retrieve the first medical data; and,
extracting, from the first MDG database, raw data associated with the determined metadata based on the querying the first MDG database;
generating one or more constructs associated with the one or more LLMs to be applied on the extracted raw data, wherein the one or more constructs are associated with the determined metadata;
retrieving the first medical data based on the application of the generated one or more constructs on the extracted raw data; and
outputting the retrieved first medical data.

### Claim 5 (depends on 4)

The method according to claim 4, further comprising:
receiving real-time medical data associated with at least one user from one or more medical devices associated with the at least one user;
determining at least one upcoming event associated with a medical condition of the at least one user based on the received real-time medical data and the one or more MDG databases; and
outputting the determined at least one upcoming event.

### Claim 6 (depends on 4)

The method according to claim 4, further comprising:
determining at least one keyword from the determined metadata, wherein the at least one keyword is associated with the at least one search query;
selecting the first MDG database of the one or more MDG databases based on the determined at least one keyword; and
querying the selected first MDG database of the one or more MDG databases.

### Claim 7

A non-transitory computer-readable medium including computer program instructions, which when executed by a system, cause the system to perform one or more operations comprising:
receiving a user input including at least one search query to retrieve first medical data from one or more medical data governance (MDG) databases;
applying one or more large language models (LLMs) on the received at least one search query, wherein the one or more LLMs are pre-trained models;
determining metadata associated with the at least one search query based on the application of the one or more LLMs on the received search query;
querying a first MDG database of the one or more MDG databases based on the determined metadata to retrieve the first medical data;
extracting, from the first MDG database, raw data associated with the determined metadata based on the querying the first MDG database;
generating one or more constructs associated with the one or more LLMs to be applied on the extracted raw data, wherein the one or more constructs are associated with the determined metadata;
retrieving the first medical data based on the application of the generated one or more constructs on the extracted raw data; and
outputting the retrieved first medical data.