A Hybrid Framework with Large Language Models for Rare Disease Phenotyping
This work addresses the challenge of rare disease diagnosis for clinicians and researchers by improving phenotyping from clinical notes, though it is incremental as it builds on existing NLP and LLM techniques.
The study tackled the problem of identifying rare diseases from unstructured clinical notes by developing a hybrid framework combining dictionary-based NLP tools with large language models, resulting in superior performance over traditional methods and uncovering many potential cases not in structured records.
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.