EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Evaluation over Generalist Large Language Models and Specialised Models for Clinical Risk Prediction

Zou Lai, Guodao Zhang, Winfried Post, Fried-Michael Dahlweid, Hong Sun

Studies in Health Technology and Informatics · 21.05.2026

DOI: 10.3233/shti260338 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, erschienen am 21.05.2026. Verfasst von Zou Lai und 4 weiteren Autor:innen. Beteiligte Einrichtung: Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing University, Jiaxing 314000, China. Hauptthemen laut MEDLINE: Large Language Models, Myocardial Infarction. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large language models (LLMs) show promise in clinical applications but face accuracy limitations in disease risk prediction, especially for rare conditions. We evaluated ChatGPT and DeepSeek against task-specific models for cholangiocarcinoma (rare) and myocardial infarction (common) prediction. Standalone LLMs underperformed specialized models, whereas collaborative prediction improved performance. Our findings suggest hybrid architectures leveraging complementary strengths of both approaches represent a promising direction for clinical AI deployment.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsMyocardial InfarctionHumansPredictive Learning ModelsRisk AssessmentPrediction AlgorithmsMachine LearningBile Duct Neoplasms

Stichwörter der Autor:innen

Clinical risk predictionEHRLLMmachine learning

Autor:innen und Institutionen

  • Provincial Key Laboratory of Multimodal Perceiving and Intelligent Systems, Jiaxing University, Jiaxing 314000, China.
  • Sino-European Joint Lab for Health Information Processing and Applications, Jiaxing University, Jiaxing 314000, China.
  • Institute of Intelligent Media Computing, Hangzhou Dianzi University, Hangzhou 310018, China.
  • Dedalus Healthcare, Bonn, Germany.

Zitieren

APA

Lai, Z., Zhang, G., Post, W., Dahlweid, F. M., & Sun, H. (2026). Evaluation over Generalist Large Language Models and Specialised Models for Clinical Risk Prediction. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti260338

Vancouver

Lai Z, Zhang G, Post W, Dahlweid FM, Sun H. Evaluation over Generalist Large Language Models and Specialised Models for Clinical Risk Prediction. Studies in Health Technology and Informatics. 2026. doi:10.3233/shti260338

BibTeX
@article{Lai2026,
  author = {Lai, Zou and Zhang, Guodao and Post, Winfried and Dahlweid, Fried-Michael and Sun, Hong},
  title = {Evaluation over Generalist Large Language Models and Specialised Models for Clinical Risk Prediction},
  journal = {Studies in Health Technology and Informatics},
  year = {2026},
  doi = {10.3233/shti260338}
}
Kostenlos starten →