Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2405.10440 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912112614309888 |
|---|---|
| author | Wu, Jinge Dong, Hang Li, Zexi Wang, Haowei Li, Runci Patra, Arijit Dai, Chengliang Ali, Waqar Scordis, Phil Wu, Honghan |
| author_facet | Wu, Jinge Dong, Hang Li, Zexi Wang, Haowei Li, Runci Patra, Arijit Dai, Chengliang Ali, Waqar Scordis, Phil Wu, Honghan |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_10440 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Hybrid Framework with Large Language Models for Rare Disease Phenotyping Wu, Jinge Dong, Hang Li, Zexi Wang, Haowei Li, Runci Patra, Arijit Dai, Chengliang Ali, Waqar Scordis, Phil Wu, Honghan Computation and Language 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. |
| title | A Hybrid Framework with Large Language Models for Rare Disease Phenotyping |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2405.10440 |