Repository logo
 
Publication

Zero-shot learning for clinical phenotyping: comparing LLMs and rule-based methods

2025-06-01Research article Open access
Simple item page
dc.contributor.authorNeves, Bernardo
dc.contributor.authorMoreira, José Maria
dc.contributor.authorGonçalves, Simão
dc.contributor.authorCerejo, Jorge
dc.contributor.authorSilva, Nuno A. da
dc.contributor.authorLeite, Francisca
dc.contributor.authorSilva, Mário J.
dc.date.accessioned2025-08-13T14:42:21Z
dc.date.available2025-08-13T14:42:21Z
dc.date.issued2025-06-01
dc.description.abstractBackground: Phenotyping, the process of systematically identifying and classifying conditions within clinical data, is a crucial first step in any data science work involving Electronic Health Records (EHRs). Traditional approaches require extensive manual annotation efforts and face challenges with scalability. Methods: We investigated the use of Large Language Models (LLMs) for zero-shot phenotyping of 20 prevalent chronic conditions based on synthetic patient summaries generated from real structured EHRs codes. We evaluated the performance of multiple LLMs, including GPT-4o, GPT-3.5, and LLaMA 3 models with 8-billion, 70-billion, and 405-billion parameters, comparing them against traditional rule-based methods. For the analysis we used a dataset of 1,000 patients from Hospital da Luz Lisboa. Results: GPT-4o outperformed both traditional rule-based methods and alternative LLMs, achieving superior recall (0.97) and macro-F1 score (0.92). Rule-based phenotyping, while highly precise (0.92), showed lower recall (0.36). The integration of rule-based methods with LLMs optimized phenotyping accuracy by targeting manual annotation efforts on discordant cases. Conclusion: Zero-shot learning with LLMs, particularly GPT-4o, offers a powerful and efficient approach for phenotyping chronic conditions from EHRs, significantly reducing the need for extensive labeled datasets while maintaining high accuracy and interpretability.eng
dc.identifier.citationNeves, B., Moreira, J. M., Gonçalves, S., & Cerejo, J. et al. (2025). Zero-shot learning for clinical phenotyping: comparing LLMs and rule-based methods. Computers in Biology and Medicine, 192, Article 110181. https://doi.org/10.1016/j.compbiomed.2025.110181
dc.identifier.doi10.1016/j.compbiomed.2025.110181
dc.identifier.eid105003218284
dc.identifier.issn0010-4825
dc.identifier.other1903ac83-59bd-4d5e-98e0-cd0ae07e7fe4
dc.identifier.pmid40273817
dc.identifier.urihttp://hdl.handle.net/10400.14/54550
dc.language.isoeng
dc.peerreviewedyes
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subjectLarge language models
dc.subjectMultimorbidity
dc.subjectPhenotyping
dc.subjectZero-shot learning
dc.titleZero-shot learning for clinical phenotyping: comparing LLMs and rule-based methodseng
dc.typeresearch article
dspace.entity.typePublication
oaire.citation.titleComputers in Biology and Medicine
oaire.citation.volume192
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
118221386.pdf
Size:
5.17 MB
Format:
Adobe Portable Document Format
Download

Collections

CIIS - Contribuições em Revistas Científicas / Contribution to Journals