Structured Extraction of Real World Medical Knowledge using LLMs for Summarization and Search

TL;DR

This paper introduces a method using large language models to extract and construct patient-specific medical knowledge graphs from unstructured data, enhancing disease discovery and patient search capabilities beyond traditional ontologies.

Contribution

The paper presents a novel approach for creating patient knowledge graphs with LLMs that maps extracted entities to existing ontologies, enabling more nuanced and flexible disease analysis.

Findings

Successful extraction of patient data related to Dravet syndrome

Demonstrated identification of BPAN patients without prior ground truth

Improved disease discovery through natural language-based knowledge graphs

Abstract

Creation and curation of knowledge graphs can accelerate disease discovery and analysis in real-world data. While disease ontologies aid in biological data annotation, codified categories (SNOMED-CT, ICD10, CPT) may not capture patient condition nuances or rare diseases. Multiple disease definitions across data sources complicate ontology mapping and disease clustering. We propose creating patient knowledge graphs using large language model extraction techniques, allowing data extraction via natural language rather than rigid ontological hierarchies. Our method maps to existing ontologies (MeSH, SNOMED-CT, RxNORM, HPO) to ground extracted entities. Using a large ambulatory care EHR database with 33.6M patients, we demonstrate our method through the patient search for Dravet syndrome, which received ICD10 recognition in October 2020. We describe our construction of patient-specific knowledge graphs and symptom-based patient searches. Using confirmed Dravet syndrome ICD10 codes as ground truth, we employ LLM-based entity extraction to characterize patients in grounded ontologies. We then apply this method to identify Beta-propeller protein-associated neurodegeneration (BPAN) patients, demonstrating real-world discovery where no ground truth exists.