Providing accurate, complete, and contextful information from medical notes with llms.

A system for providing medical information analysis, comprising:

• a processor;
• and
• a memory storing instructions that, when executed by the processor, cause the system to:
• receive medical documentation from patient medical files;
• process the medical documentation to extract medical entities using a large language model;
• access biomedical knowledge graphs to obtain contextual information related to the extracted medical entities;
• generate a summary of medical information by combining the extracted medical entities with the contextual information from the knowledge graphs;
• and
• provide the summary to assist physician preparation for patient visits.

A computer-readable medium comprising instructions that, when executed by a processor, cause the processor to perform a method for analyzing medical notes using knowledge graph enhanced language models, the method comprising:

• receiving a medical note containing medical information;
• processing the medical note with a large language model to identify medical entities within the medical note;
• determining a type of medical entity from the identified medical entities;
• accessing a knowledge graph corresponding to the determined type of medical entity, wherein the knowledge graph contains structured medical knowledge relevant to the type of medical entity;
• generating an augmented context by retrieving relevant information from the knowledge graph based on the identified medical entities;
• and
• reprocessing the medical note with the large language model using the augmented context to generate enhanced medical analysis results.