Improving Large Language Models’ Summarization Accuracy by Adding Highlights to Discharge Notes: Comparative Evaluation
Feeding LLMs with highlighted discharge notes, combined with prompt engineering, results in higher-quality summaries in terms of correctness, completeness, and structural integrity compared to unhighlighted discharge notes.
Authors
- Fadi P. Deek (ORCID: https://orcid.org/0009-0001-1022-4118)
- Andrew J. Einstein (ORCID: https://orcid.org/0000-0003-2583-9278)
- Zhe He (ORCID: https://orcid.org/0000-0003-3608-0244)
- Gai Elhanan (ORCID: https://orcid.org/0000-0003-1518-5522)
- Yehoshua Perl (ORCID: https://orcid.org/0000-0003-1940-9386)
- Vipina K. Keloth (ORCID: https://orcid.org/0000-0001-6919-1122)
- Hao Liu (ORCID: https://orcid.org/0000-0002-1975-1272)
- Mahshad Koohi H. Dehkordi (ORCID: https://orcid.org/0000-0003-3489-0892)
Institutions
- Florida State University (US)
- New Jersey Institute of Technology (US)
- University of Nevada, Reno (US)
- Montclair State University (US)
- Columbia University Irving Medical Center (US)
- Yale University (US)
Publication Details
- Journal
- JMIR Medical Informatics
- Published
- 2025-07-24
- DOI
- https://doi.org/10.2196/66476
- Citations
- 7
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 17.37