EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Harnessing the Potential of LLMs in Hospital Management: Insights Into Medical Data Inquiry

Jiaxi Li, Yu Zhang, Jing Zhao, Shengyang He, Danni Li

The International Journal of Health Planning and Management · 2026-12 · 41 (6) · 1136-1145

DOI: 10.1002/hpm.70106 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The International Journal of Health Planning and Management, online erschienen am 31.07.2026. Verfasst von Jiaxi Li und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Clinical Laboratory Medicine, Jinniu Maternity and Child Health Hospital of Chengdu, Chengdu, China. Hauptthemen laut MEDLINE: Large Language Models, Hospital Administration. Die Arbeit nennt 48 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Chengdu Science and Technology Bureau under the Chengdu Municipal Finance and Technology Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Considering the rapid expansion of hospital operations and the increasing digitisation of medical data, there is a pressing need for efficient and intelligent methods to process and analyse large‐scale medical data.

Methods

We integrated the QLoRA algorithm with ChatGLM2‐6b, Llama2‐7b, and Llama2‐13b models, fine‐tuning them on a local SQL dataset to optimise query performance. Prompt‐Engineering with ChatGPT was further applied for effective SQL execution.

Results

Original open‐source models showed almost no SQL generation capability (overall EX ≈ 0 for ChatGLM2‐6B and Llama2‐7B; 0.04 for Llama2‐13B). QLoRA fine‐tuning substantially improved performance, with QLoRA‐Llama2‐13B achieving the best results among open‐source models (overall EX 0.41 ± 0.030). Proprietary models demonstrated significantly stronger performance. Zero‐shot ChatGPT‐3.5 achieved moderate accuracy (EX 0.44 ± 0.007), which improved to 0.94 ± 0.017 with few‐shot prompting. GPT‐4.1 further improved performance, reaching 0.78 ± 0.038 in the zero‐shot setting and 0.96 ± 0.011 with few‐shot prompting. The few‐shot GPT‐4.1 results were comparable to those of database engineers (EX 0.97 ± 0.017), with no significant difference ( p = 0.42).

Conclusion

Fine‐tuned LLMs and few‐shot GPT‐4.1 demonstrate substantial improvements in SQL query execution, providing a robust framework for efficient medical data analysis and informed hospital decision‐making.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsHospital AdministrationAlgorithmsHumans

Stichwörter der Autor:innen

GPTLLMNL2SQLhospital managementprompt‐engineering

Autor:innen und Institutionen

  • Department of Clinical Laboratory Medicine, Jinniu Maternity and Child Health Hospital of Chengdu, Chengdu, China.
  • School of Medicine, University of Electronic Science and Technology of China, Chengdu, China.
  • Information Center, West China Hospital, Sichuan University, Chengdu, China.
  • State Key Laboratory of Oral Diseases & National Center for Stomatology & National Clinical Research Center for Oral Diseases & Department of Information Management, West China Hospital of Stomatology, Sichuan Universit…

Förderung

  • Chengdu Science and Technology Bureau under the Chengdu Municipal Finance and Technology Project

Zitieren

APA

Li, J., Zhang, Y., Zhao, J., He, S., & Li, D. (2026). Harnessing the Potential of LLMs in Hospital Management: Insights Into Medical Data Inquiry. The International Journal of Health Planning and Management, 41(6), 1136-1145. https://doi.org/10.1002/hpm.70106

Vancouver

Li J, Zhang Y, Zhao J, He S, Li D. Harnessing the Potential of LLMs in Hospital Management: Insights Into Medical Data Inquiry. The International Journal of Health Planning and Management. 2026;41(6):1136-1145. doi:10.1002/hpm.70106

BibTeX
@article{Li2026,
  author = {Li, Jiaxi and Zhang, Yu and Zhao, Jing and He, Shengyang and Li, Danni},
  title = {Harnessing the Potential of LLMs in Hospital Management: Insights Into Medical Data Inquiry},
  journal = {The International Journal of Health Planning and Management},
  year = {2026},
  volume = {41},
  number = {6},
  pages = {1136--1145},
  doi = {10.1002/hpm.70106}
}
Kostenlos starten →