US 12,243,646 B1
Systems and methods for improving retrieval- augmented generation in clinical decision support
Dereck William Paul, Jr., Tiburon, CA (US); and Graham Ramsey, San Francisco, CA (US)
Assigned to Glass Health Inc., San Francisco, CA (US)
Filed by Glass Health Inc., San Francisco, CA (US)
Filed on May 9, 2024, as Appl. No. 18/659,846.
Claims priority of provisional application 63/554,881, filed on Feb. 16, 2024.
Int. Cl. G06N 20/00 (2019.01); G10L 15/26 (2006.01); G16H 15/00 (2018.01); G16H 20/00 (2018.01); G16H 50/20 (2018.01)
CPC G16H 50/20 (2018.01) [G10L 15/26 (2013.01); G16H 15/00 (2018.01); G16H 20/00 (2018.01)] 21 Claims
OG exemplary drawing
 
1. An artificial intelligence (AI)-based clinical decision support platform for treating a patient with a health condition, the platform comprising:
a user input processing module configured to receive a clinical problem representation (CPR) based at least in part on an input provided by a healthcare provider (HCP) or a patient, wherein the CPR comprises a list of one or more symptoms presented or determined in real time during a patient encounter;
a context matching module comprising a first large language model (LLM) generally trained using general or historical data, wherein the first LLM is configured to determine a clinical diagnosis of the health condition by (1) iteratively processing a first set of prompts using a plurality of healthcare context topics generated from a physician-validated context library and (2) determining, using the first set of prompts, a context match from the plurality of healthcare context topics, wherein the context match associates the health condition with at least one of the plurality of healthcare context topics with a confidence level;
a retrieval-augmented generation (RAG) module comprising the physician-validated context library, wherein the RAG module is configured to: (1) generate the plurality of healthcare context topics for use by the context matching module and (2) identify physician-validated schemas and clinical guidelines for treating the health condition; and
an output generation module comprising a second LLM trained using the physician-validated context library, wherein the second LLM is configured to determine a plurality of treatment plans for treating the health condition by (1) iteratively processing a second set of prompts using the context match and the physician-validated schemas and clinical guidelines and (2) determining, using the second set of prompts, at least one treatment plan of the plurality of treatment plans,
wherein the at least one treatment plan is used to treat the patient having or suspected of having the health condition based at least on a confidence level of the clinical diagnosis.