A Hybrid Framework with Large Language Models for Rare Disease Phenotyping

TL;DR

This paper presents a hybrid NLP framework combining ontologies and large language models to improve rare disease detection from clinical notes, outperforming traditional methods and uncovering unrecognized cases.

Contribution

It introduces a novel hybrid approach integrating ORDO, UMLS, and LLMs for enhanced rare disease phenotyping from unstructured clinical data.

Findings

Superior performance over traditional NLP and standalone LLMs

Uncovered many potential rare disease cases not documented in records

Effective identification of previously unrecognized patients

Abstract

Rare diseases pose significant challenges in diagnosis and treatment due to their low prevalence and heterogeneous clinical presentations. Unstructured clinical notes contain valuable information for identifying rare diseases, but manual curation is time-consuming and prone to subjectivity. This study aims to develop a hybrid approach combining dictionary-based natural language processing (NLP) tools with large language models (LLMs) to improve rare disease identification from unstructured clinical reports. We propose a novel hybrid framework that integrates the Orphanet Rare Disease Ontology (ORDO) and the Unified Medical Language System (UMLS) to create a comprehensive rare disease vocabulary. The proposed hybrid approach demonstrates superior performance compared to traditional NLP systems and standalone LLMs. Notably, the approach uncovers a significant number of potential rare disease cases not documented in structured diagnostic records, highlighting its ability to identify previously unrecognized patients.