EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Integrating Large Language Models and Machine Learning for Enhanced Catatonia Phenotyping: A Study on Clinical Data from Electronic Health Records

Yubo Feng, Ruiyan Ma, Xinmeng Zhang, You Chen

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250915 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Yubo Feng und 3 weiteren Autor:innen. Beteiligte Einrichtung: Vanderbilt University, Nashville, TN, USA. Hauptthemen laut MEDLINE: Electronic Health Records, Machine Learning, Catatonia, Natural Language Processing. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Catatonia, a complex syndrome with diagnostic challenges, was studied using a novel approach combining LightGBM and GPT-4 to enhance phenotyping from electronic health record (EHR) data. LightGBM, trained on structured data, achieved superior performance (AUROC 0.713) compared to GPT-4 (best AUROC 0.709 with retrieval-augmented generation (RAG) few-shot and ML predictions). While LightGBM excelled in raw metrics, GPT-4 added value through enhanced interpretability, effectively analyzing contextual information like the Bush-Francis Catatonia Rating Scale from clinical notes. This integration demonstrates the potential of combining ML and GPT-4 to improve catatonia identification and phenotyping accuracy.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Electronic Health RecordsMachine LearningCatatoniaNatural Language ProcessingHumansPhenotypeLarge Language Models

Stichwörter der Autor:innen

CatatoniaEHRGPT-4LightGBMPhenotyping

Autor:innen und Institutionen

  • Vanderbilt University, Nashville, TN, USA.
  • Vanderbilt University Medical Center, Nashville, TN, USA.

Zitieren

APA

Feng, Y., Ma, R., Zhang, X., & Chen, Y. (2025). Integrating Large Language Models and Machine Learning for Enhanced Catatonia Phenotyping: A Study on Clinical Data from Electronic Health Records. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250915

Vancouver

Feng Y, Ma R, Zhang X, Chen Y. Integrating Large Language Models and Machine Learning for Enhanced Catatonia Phenotyping: A Study on Clinical Data from Electronic Health Records. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250915

BibTeX
@article{Feng2025,
  author = {Feng, Yubo and Ma, Ruiyan and Zhang, Xinmeng and Chen, You},
  title = {Integrating Large Language Models and Machine Learning for Enhanced Catatonia Phenotyping: A Study on Clinical Data from Electronic Health Records},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250915}
}
Kostenlos starten →