EUVIMEDEUVIMED entdecken
Open Access

Summarize-then-Prompt: A Novel Prompt Engineering Strategy for Generating High-Quality Discharge Summaries

Eyal Klang, Jaskirat Gill, Aniket Sharma, Evan Leibner, Moein Sabounchi, Robert Freeman, Roopa Kohli-Seth, Patricia Kovatch, Alexander W Charney, Lisa Stump, David L Reich, Girish N Nadkarni und 1 weitere

Applied Clinical Informatics · 01.08.2025 · 16 (04) · 1325-1331

DOI: 10.1055/a-2617-6572 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Clinical Informatics, erschienen am 01.08.2025. Verfasst von Eyal Klang und 12 weiteren Autor:innen. Beteiligte Einrichtung: The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, United States. Hauptthemen laut MEDLINE: Patient Discharge, Patient Discharge Summaries. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 19 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIDDK NIH HHS, U.S. Department of Health and Human Services, National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate discharge summaries are essential for effective communication between hospital and outpatient providers but generating them is labor-intensive. Large language models (LLMs), such as GPT-4, have shown promise in automating this process, potentially reducing clinician workload and improving documentation quality. A recent study using GPT-4 to generate discharge summaries via concatenated clinical notes found that while the summaries were concise and coherent, they often lacked comprehensiveness and contained errors. To address this, we evaluated a structured prompting strategy, summarize-then-prompt, which first generates concise summaries of individual clinical notes before combining them to create a more focused input for the LLM. The objective of this study was to assess the effectiveness of a novel prompting strategy, summarize-then-prompt, in generating discharge summaries that are more complete, accurate, and concise in comparison to the approach that simply concatenates clinical notes. We conducted a retrospective study comparing two prompting strategies: direct concatenation (M1) and summarize-then-prompt (M2). A random sample of 50 hospital stays was selected from a large hospital system. Three attending physicians independently evaluated the generated hospital course summaries for completeness, correctness, and conciseness using a 5-point Likert scale. The summarize-then-prompt strategy outperformed direct concatenation strategy in both completeness (4.28 ± 0.63 vs. 4.01 ± 0.69, p < 0.001) and correctness (4.37 ± 0.54 vs. 4.17 ± 0.57, p = 0.002) of the summarization of the hospital course. However, the two strategies showed no significant difference in conciseness (p = 0.308). Summarizing individual notes before concatenation improves LLM-generated discharge summaries, enhancing their completeness and accuracy without sacrificing conciseness. This approach may facilitate the integration of LLMs into clinical workflows, offering a promising strategy for automating discharge summary generation and could reduce clinician burden.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Patient DischargePatient Discharge SummariesHumansElectronic Health Records

Autor:innen und Institutionen

  • The Charles Bronfman Institute for Personalized Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, United States.
  • Division of Data Driven and Digital Medicine, Department of Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, United States.
  • Institute for Critical Care Medicine, Icahn School of Medicine at Mount Sinai, New York, New York, United States.
  • Institute for Healthcare Delivery Science, Icahn School of Medicine at Mount Sinai, New York, New York, United States.
  • Scientific Computing, Icahn School of Medicine at Mount Sinai, New York, New York, United States.
  • Mount Sinai Health System and Icahn School of Medicine at Mount Sinai, New York, New York, United States.

Förderung

  • NIDDK NIH HHS
  • U.S. Department of Health and Human Services, National Institutes of Health, National Institute of Diabetes and Digestive and Kidney Diseases

Zitieren

APA

Klang, E., Gill, J., Sharma, A., Leibner, E., Sabounchi, M., Freeman, R., Kohli-Seth, R., Kovatch, P., Charney, A. W., Stump, L., Reich, D. L., Nadkarni, G. N., & Sakhuja, A. (2025). Summarize-then-Prompt: A Novel Prompt Engineering Strategy for Generating High-Quality Discharge Summaries. Applied Clinical Informatics, 16(04), 1325-1331. https://doi.org/10.1055/a-2617-6572

Vancouver

Klang E, Gill J, Sharma A, Leibner E, Sabounchi M, Freeman R, et al. Summarize-then-Prompt: A Novel Prompt Engineering Strategy for Generating High-Quality Discharge Summaries. Applied Clinical Informatics. 2025;16(04):1325-1331. doi:10.1055/a-2617-6572

BibTeX
@article{Klang2025,
  author = {Klang, Eyal and Gill, Jaskirat and Sharma, Aniket and Leibner, Evan and Sabounchi, Moein and Freeman, Robert and Kohli-Seth, Roopa and Kovatch, Patricia and Charney, Alexander W and Stump, Lisa and Reich, David L and Nadkarni, Girish N and Sakhuja, Ankit},
  title = {Summarize-then-Prompt: A Novel Prompt Engineering Strategy for Generating High-Quality Discharge Summaries},
  journal = {Applied Clinical Informatics},
  year = {2025},
  volume = {16},
  number = {04},
  pages = {1325--1331},
  doi = {10.1055/a-2617-6572}
}
Kostenlos starten →