Identifying symptom etiologies using syntactic patterns and large language models
Authors:
Open Access
- 13 July 2024
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-15
Abstract
Differential diagnosis is a crucial aspect of medical practice, as it guides clinicians to accurate diagnoses and effective treatment plans. Traditional resources, such as medical books and services like UpToDate, are constrained by manual curation, potentially missing out on novel or less common findings. This paper introduces and analyzes two novel methods to mine etiologies from scientific literature. The first method employs a traditional Natural Language Processing (NLP) approach based on syntactic patterns. By using a novel application of human-guided pattern bootstrapping patterns are derived quickly, and symptom etiologies are extracted with significant coverage. The second method utilizes generative models, specifically GPT-4, coupled with a fact verification pipeline, marking a pioneering application of generative techniques in etiology extraction. Analyzing this second method shows that while it is highly precise, it offers lesser coverage compared to the syntactic approach. Importantly, combining both methodologies yields synergistic outcomes, enhancing the depth and reliability of etiology mining.Keywords
Funding Information
- Israeli Science Foundation (901/19)
- H2020 European Research Council (802774)
This publication has 25 references indexed in Scilit:
- SEED: Symptom Extraction from English Social Media Posts using Deep Learning and Transfer LearningmedRxiv, 2021
- Recent advances in biomedical literature miningBriefings in Bioinformatics, 2020
- Task definition, annotated dataset, and supervised natural language processing models for symptom extraction from unstructured clinical notesJournal of Biomedical Informatics, 2020
- DiseaSE: A biomedical text analytics system for disease symptom extraction and characterizationJournal of Biomedical Informatics, 2019
- Disease networks and their contribution to disease understanding: A review of their evolution, techniques and data sourcesJournal of Biomedical Informatics, 2019
- BioCreative V CDR task corpus: a resource for chemical disease relation extractionDatabase: The Journal of Biological Databases and Curation, 2016
- Community challenges in biomedical text mining over 10 years: success, failure and the futureBriefings in Bioinformatics, 2015
- Human symptoms–disease networkNature Communications, 2014
- NCBI disease corpus: A resource for disease name recognition and concept normalizationJournal of Biomedical Informatics, 2014
- MEDIC: a practical disease vocabulary used at the Comparative Toxicogenomics DatabaseDatabase: The Journal of Biological Databases and Curation, 2012