EUVIMEDEUVIMED entdecken
Open Access

Leveraging Large Language Models for Predicting Postoperative Acute Kidney Injury in Elderly Patients

Hanfei Zhu, Ruojiang Wang, Jiajie Qian, Yuhao Wu, Zhuqing Jin, Xishen Shan, Fuhai Ji, Zixuan Yuan, Tingrui Pan iD

BME Frontiers · 2025-01 · 6

DOI: 10.34133/bmef.0111 ↗

Kurz gefasst

Fachartikel in der Zeitschrift BME Frontiers, online erschienen am 11.03.2025. Verfasst von Hanfei Zhu und 8 weiteren Autor:innen. Beteiligte Einrichtung: Center for Intelligent Medical Equipment and Devices, Institute for innovative Medical Devices, School of Biomedical Engineering, Division of Life Sc…. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: National Key Research and Development Program, Suzhou Medical Innovation Applied Research, Jiangsu Province Medical Research General Project.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

The objective of this work is to develop a framework based on large language models (LLMs) to predict postoperative acute kidney injury (AKI) outcomes in elderly patients. Impact Statement: Our study demonstrates that LLMs have the potential to address the issues of poor generalization and weak interpretability commonly encountered in disease prediction using traditional machine learning (ML) models.

Introduction

AKI is a severe postoperative complication, especially in elderly patients with declining renal function. Current AKI prediction models rely on ML, but their lack of interpretability and generalizability limits clinical use. LLMs, with extensive pretraining and text generation capabilities, offer a new solution.

Methods

We applied prompt engineering and knowledge distillation based on instruction fine-tuning to optimize LLMs for AKI prediction. The framework was tested on 2,649 samples from 2 private Chinese hospitals and one public South Korean dataset, which were divided into internal and external datasets.

Results

The LLM framework showed robust external performance, with accuracy rates: commercial LLMs (internal: 63.73%, external: 68.73%), open-source LLMs (internal: 63.70%, external: 64.24%), and ML models (internal: 63.93%, external: 58.27%). LLMs also provided human-readable explanations for better clinical understanding.

Conclusion

The proposed framework showcases the potential of LLMs to enhance generalization and interpretability in postoperative AKI prediction, paving the way for more robust and transparent predictive solutions in clinical settings.

Autor:innen und Institutionen

  • Center for Intelligent Medical Equipment and Devices, Institute for innovative Medical Devices, School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, He…
  • Suzhou Institute for Advanced Research, University of Science and Technology of China, Suzhou, Jiangsu, P. R. China.
  • Department of Anesthesiology, The First Affiliated Hospital of Soochow University, Suzhou, Jiangsu, P. R. China.
  • Department of Nephrology, The Second Affiliated Hospital of Anhui Medical University, Hefei, P. R. China.
  • Thrust of Financial Technology, The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, P. R. China.
  • Department of Precision Machinery and Precision Instrumentation, School of Engineering Science, University of Science and Technology of China, Hefei, Anhui, P. R. China.

ORCID-Profile: Tingrui Pan

Förderung

  • National Key Research and Development Program
  • Suzhou Medical Innovation Applied Research
  • Jiangsu Province Medical Research General Project

Zitieren

APA

Zhu, H., Wang, R., Qian, J., Wu, Y., Jin, Z., Shan, X., Ji, F., Yuan, Z., & Pan, T. (2025). Leveraging Large Language Models for Predicting Postoperative Acute Kidney Injury in Elderly Patients. BME Frontiers, 6. https://doi.org/10.34133/bmef.0111

Vancouver

Zhu H, Wang R, Qian J, Wu Y, Jin Z, Shan X, et al. Leveraging Large Language Models for Predicting Postoperative Acute Kidney Injury in Elderly Patients. BME Frontiers. 2025;6. doi:10.34133/bmef.0111

BibTeX
@article{Zhu2025,
  author = {Zhu, Hanfei and Wang, Ruojiang and Qian, Jiajie and Wu, Yuhao and Jin, Zhuqing and Shan, Xishen and Ji, Fuhai and Yuan, Zixuan and Pan, Tingrui},
  title = {Leveraging Large Language Models for Predicting Postoperative Acute Kidney Injury in Elderly Patients},
  journal = {BME Frontiers},
  year = {2025},
  volume = {6},
  doi = {10.34133/bmef.0111}
}
Kostenlos starten →