Toward Responsible and Privacy-Preserving Generation of Inpatient Clinical Discharge Notes Using Large Language Models
Computational and Structural Biotechnology Journal · 01.01.2026 · 35 (2)
DOI: 10.34133/csbj.0151 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational and Structural Biotechnology Journal, online erschienen am 09.07.2026. Verfasst von Felice Burn und 17 weiteren Autor:innen. Beteiligte Einrichtung: Center of Excellence for AI and Data Science, Cantonal Hospital Aarau, Aarau, Switzerland. Die Arbeit nennt 30 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Forschungsrat des Kantonsspitals Aarau, Hightech Zentrum Aargau.
Abstract (Originalsprache)
Writing discharge notes (DNs) is a time-intensive task in inpatient care that contributes substantially to physician workload and burnout. Large language models (LLMs) offer potential opportunities to automate clinical documentation. However, concerns regarding accuracy, reliability, data privacy protection laws and data governance, and compliance with healthcare privacy remain. This study evaluated the performance of locally deployed, domain-adapted LLMs for generating German-language DN in internal medicine. In this retrospective study, electronic health record data from a Swiss tertiary care hospital were used. Clinical information from 3 inpatient scenarios served as input for the 3 open source LLMs (Mixtral 8×7B, Mixtral 8×22B, and LLaMA 3.1 70B). Zero-shot prompting, 4-shot in-context learning, and supervised fine-tuning using QLoRA were compared. Generated DNs were evaluated using automated metrics, blinded physician assessment with direct comparison of all relevant clinical information using the modified Physician Documentation Quality Instrument, and additionally an LLM-as-a-judge framework and a Turing Test. Across all evaluation methods, the fine-tuned Mixtral 8×7B model achieved the best overall performance compared with prompting-based approaches and larger nonspecialized models. Simpler cases consistently received higher-quality ratings. Physician inter-rater agreement was low, highlighting the challenges of objective quality assessment for clinical documentation. In a Turing Test, physicians were unable to reliably distinguish artificial intelligence-generated from clinician-authored DNs, performing at chance level, demonstrating that high-quality DN generation is feasible using locally deployed LLMs within secure hospital infrastructures. Domain-specific fine-tuning substantially improves performance and may enable practical deployment. Future work should address further hallucination mitigation, robustness across medical specialties, and real-world integration.
Autor:innen und Institutionen
- Center of Excellence for AI and Data Science, Cantonal Hospital Aarau, Aarau, Switzerland.
- Institute for Data Science, FHNW Brugg-Windisch, Windisch, Switzerland.
- University Department, Division of General Internal and Emergency Medicine, Cantonal Hospital Aarau, Aarau, Switzerland.
- Notfall Zurich 3, NZ3, Zurich, Switzerland.
- Laboratory for Computational Physiology, Institute for Medical Engineering and Science, Massachusetts Institute of Technology, Cambridge MA, USA.
- Hospital Muri,Aargau,Switzerland.
ORCID-Profile: Felice Burn, Chantal Zwick, Joseph Weibel, Cyril Fischer, Maurin Lampart, Carola George, Simone Wildisen, Monica Alexandra Vieira, Christian Eisenring, Beat Mueller, Daniel Olivier Perruchoud, Tristan Struja
Förderung
- Forschungsrat des Kantonsspitals Aarau
- Hightech Zentrum Aargau
Zitieren
APA
Burn, F., Zwick, C., Weibel, J., Fischer, C., Veer, R., Essmann, L., Lampart, M., Chamo, M., George, C., Gafner, S., Wildisen, S., Vanecko, M., Ordoñez, K., Vieira, M. A., Eisenring, C., Mueller, B., Perruchoud, D. O., & Struja, T. (2026). Toward Responsible and Privacy-Preserving Generation of Inpatient Clinical Discharge Notes Using Large Language Models. Computational and Structural Biotechnology Journal, 35(2). https://doi.org/10.34133/csbj.0151
Vancouver
Burn F, Zwick C, Weibel J, Fischer C, Veer R, Essmann L, et al. Toward Responsible and Privacy-Preserving Generation of Inpatient Clinical Discharge Notes Using Large Language Models. Computational and Structural Biotechnology Journal. 2026;35(2). doi:10.34133/csbj.0151
BibTeX
@article{Burn2026,
author = {Burn, Felice and Zwick, Chantal and Weibel, Joseph and Fischer, Cyril and Veer, Rick and Essmann, Lennart and Lampart, Maurin and Chamo, Michael and George, Carola and Gafner, Sandra and Wildisen, Simone and Vanecko, Martin and Ordoñez, Kimberly and Vieira, Monica Alexandra and Eisenring, Christian and Mueller, Beat and Perruchoud, Daniel Olivier and Struja, Tristan},
title = {Toward Responsible and Privacy-Preserving Generation of Inpatient Clinical Discharge Notes Using Large Language Models},
journal = {Computational and Structural Biotechnology Journal},
year = {2026},
volume = {35},
number = {2},
doi = {10.34133/csbj.0151}
}
EUVIMED