<ul><li>Creation and curation of knowledge graphs can accelerate disease discovery and analysis in real-world data.</li><li>Proposes creating patient knowledge graphs using large language model extraction techniques, allowing data extraction via natural language rather than rigid ontological hierarchies.</li><li>Demonstrates the method through patient search for Dravet syndrome using a large ambulatory care EHR database.</li><li>Applies the method to identify Beta-propeller protein-associated neurodegeneration (BPAN) patients, showing real-world discovery where no ground truth exists.</li></ul>

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

Discover more