---
title: "Automatic Generation of Discharge Summaries Using Large"
description: "Writing discharge summaries by hand takes a lot of clinicians' time, yet these documents are central to handing patients over… 17 references."
authors: ["Lucas Molino-Piñar", "Manuel Carlos Diaz Galiano", "María-Teresa Martín-Valdivia"]
year: 2026
venue: "Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026"
source: "https://aclanthology.org/2026.clinicalnlp-1.9/"
doi: "10.63317/5dnbkz4d44kz"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/pinar-2026-automatic-generation-discharge-summaries-large/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/pinar-2026-automatic-generation-discharge-summaries-large/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/) / Automatic Generation of Discharge Summaries Using Large Language Models: A Systematic Literature Review

# Automatic Generation of Discharge Summaries Using Large Language Models: A Systematic Literature Review

**Authors:** [Lucas Molino-Piñar](https://md.research.elamur.ai/free/en/authors/lucas-molino-pinar/), [Manuel Carlos Diaz Galiano](https://md.research.elamur.ai/free/en/authors/manuel-carlos-diaz-galiano/) and [María-Teresa Martín-Valdivia](https://md.research.elamur.ai/free/en/authors/maria-teresa-martin-valdivia/) · **Year:** 2026 · **Venue:** [Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/clinicalnlp/) ([Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026](https://md.research.elamur.ai/free/en/venues/clinicalnlp/2026/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.clinicalnlp-1.9/) · [PDF](https://aclanthology.org/2026.clinicalnlp-1.9.pdf) · [DOI 10.63317/5dnbkz4d44kz](https://doi.org/10.63317/5dnbkz4d44kz) · [OpenAlex](https://openalex.org/W7166589016)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
Writing discharge summaries by hand takes a lot of clinicians' time, yet these documents are central to handing patients over safely after a hospital stay. This review maps how NLP and LLMs are currently used to draft such summaries for physicians. It deliberately leaves out work on rewriting summaries for patients. Following the Kitchenham guidelines, with PICOC scoping and PRISMA reporting, the authors searched Scopus and PubMed for work from 2023–2026. They screened 102 records, applied a six-item quality checklist, and kept 9 primary studies. Four research questions structure the analysis: models and techniques, evaluation metrics, engineering challenges, and factuality and privacy. GPT-4-family models dominate the field. Open models like LLaMA are attractive when patient data must stay local. Evaluation typically pairs ROUGE/BLEU scores with judgments from clinical experts. Several problems recur: frequent hallucinations, omitted information, difficulty integrating with EHR systems, and limited context windows. Even so, some deployments already look clinically workable. The review gives a concise picture of a young field and its open problems.

## Key points
- Corpus of studies: 94 Scopus and 8 PubMed hits (102 total), narrowed to 9 studies. A study needed at least 3.5/6 on the quality checklist, and 29 data fields were extracted from each included paper.
- GPT-4 or one of its variants is used in 6 of the 9 studies. LLaMA is highlighted as an open-source, privacy-friendly alternative.
- Reported hallucination rates range from 33% to 64%. Mitigations include human-in-the-loop review, prompt engineering, and knowledge-graph-based correction.
- One implementation achieved a System Usability Score of 94.35%, suggesting practical clinical feasibility.
- IEEE Xplore and ACM DL were dropped for poor coverage of the topic. ACL venues are reached indirectly through Scopus indexing, and the review was managed with the Parsifal tool.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (6): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 241 works · [🩺 Health Informatics](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · 184 works · [🏥 Health Professions](https://md.research.elamur.ai/free/en/shelves/health-professions/) · 69 works · [🏥 Health Information Management](https://md.research.elamur.ai/free/en/shelves/health-professions/health-information-management/) · 50 works

## Cite

Cite as: Lucas Molino-Piñar, Manuel Carlos Diaz Galiano and María-Teresa Martín-Valdivia. 2026. Automatic Generation of Discharge Summaries Using Large Language Models: A Systematic Literature Review. Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{molinopinar2026automatic,
  title = {{Automatic Generation of Discharge Summaries Using Large Language Models: A Systematic Literature Review}},
  author = {Lucas Molino-Piñar, Manuel Carlos Diaz Galiano and María-Teresa Martín-Valdivia},
  booktitle = {Proceedings of the 8th Workshop on Clinical Natural Language Processing (Clinical NLP) @ LREC 2026},
  year = {2026},
  doi = {10.63317/5dnbkz4d44kz},
  url = {https://doi.org/10.63317/5dnbkz4d44kz}
}
```

- [← previous Automatic Extraction of Textual and Phonemic Complexity for French Cued Speech](https://md.research.elamur.ai/free/en/papers/norre-2026-automatic-extraction-textual-phonemic-complexity/)
- [next → Automatic Generation of Graded Texts in Old Church Slavonic](https://md.research.elamur.ai/free/en/papers/stoupak-2026-automatic-generation-graded-texts-old/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/23/)

## References

17 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Emma Croxford, Yanjun Gao, Elliot First, Nicholas Pellegrino, Miranda Schnier, John Caskey, Madeline Oguss, Graham Wills, Guanhua Chen, Dmitriy Dligach, Matthew M. Churpek, Anoop Mayampurath, Frank Liao, Cherodeep Goswami, Karen K. Wong, Brian W. Patterson, and Majid Afshar. 2025. Evaluating clinica… [find](https://scholar.google.com/scholar?q=Emma+Croxford%2C+Yanjun+Gao%2C+Elliot+First%2C+Nicholas+Pellegrino%2C+Miranda+Schnier%2C+John+Caskey%2C+Madeline+Oguss%2C+Graham+Wills%2C+Guanhua+Chen%2C+Dmitriy+Dligach%2C+Matthew+M%2E+Churpek%2C+Anoop+Mayampurath%2C+Frank+Li)
2. Jiaojiao Fu, Bowen Yang, Yi Guo, Yangfan Zhou, and Xin Wang. 2025. Automated clinical summary generation via integrating structured and unstructured data. Communications in Computer and Information Science, 2301:290 – 304. [find](https://scholar.google.com/scholar?q=Jiaojiao+Fu%2C+Bowen+Yang%2C+Yi+Guo%2C+Yangfan+Zhou%2C+and+Xin+Wang%2E+2025%2E+Automated+clinical+summary+generation+via+integrating+structured+and+unstructured+data%2E+Communications+in+Computer+and+Information+Sc)
3. Georgi Grazhdanski, Vasil Vasilev, Sylvia Vassileva, Dimitar Taskov, Izabel Antova, Ivan Koychev, and Svetla Boytcheva. 2025. Synthmedic: Utilizing large language models for synthetic discharge summary generation, correction and validation. Journal of Biomedical Informatics, 170. [find](https://scholar.google.com/scholar?q=Georgi+Grazhdanski%2C+Vasil+Vasilev%2C+Sylvia+Vassileva%2C+Dimitar+Taskov%2C+Izabel+Antova%2C+Ivan+Koychev%2C+and+Svetla+Boytcheva%2E+2025%2E+Synthmedic%3A+Utilizing+large+language+models+for+synthetic+discharge+summar)
4. Lewis Hains, Oliver Kleinig, Ashwin Murugappa, Samuel Gluck, Jarrod Marks, Toby Gilbert, and Stephen Bacchi. 2025. Large language model discharge summary preparation using real-world electronic medical record data shows promise. Internal Medicine Journal, 55(7):1188 – 1192. \#\# Acknowledgements Barba… [find](https://scholar.google.com/scholar?q=Lewis+Hains%2C+Oliver+Kleinig%2C+Ashwin+Murugappa%2C+Samuel+Gluck%2C+Jarrod+Marks%2C+Toby+Gilbert%2C+and+Stephen+Bacchi%2E+2025%2E+Large+language+model+discharge+summary+preparation+using+real%2Dworld+electronic+medica)
5. This work is funded by the Ministerio para la Transformación Digital y de la Función Pública and Plan de Recuperación, Transformación y Resiliencia - Funded by EU – NextGenerationEU within the framework of the project Desarrollo Modelos ALIA. This work has also been partially supported by Project RO… — [doi:10.13039/501100011033](https://doi.org/10.13039/501100011033) [find](https://scholar.google.com/scholar?q=This+work+is+funded+by+the+Ministerio+para+la+Transformaci%C3%B3n+Digital+y+de+la+Funci%C3%B3n+P%C3%BAblica+and+Plan+de+Recuperaci%C3%B3n%2C+Transformaci%C3%B3n+y+Resiliencia+%2D+Funded+by+EU+%E2%80%93+NextGenerationEU+within+the+framewo)
6. Yiming Li, Fang Li, Na Hong, Manqi Li, Kirk Roberts, Licong Cui, Cui Tao, and Hua Xu. 2025. A comparative study of recent large language models on generating hospital discharge summaries for lung cancer patients. Journal of Biomedical Informatics, 168. [find](https://scholar.google.com/scholar?q=Yiming+Li%2C+Fang+Li%2C+Na+Hong%2C+Manqi+Li%2C+Kirk+Roberts%2C+Licong+Cui%2C+Cui+Tao%2C+and+Hua+Xu%2E+2025%2E+A+comparative+study+of+recent+large+language+models+on+generating+hospital+discharge+summaries+for+lung+canc)
7. OpenAI. 2023. [Gpt-4 technical report](https://md.research.elamur.ai/free/en/papers/openai-2023-gpt-4-technical-report/). abs/2303.08774.
8. ArXiv, Brenda Y. Miao, Atul J. Butte, and Aaron E. Kornblith. 2025. Evaluating large language models for drafting emergency department encounter summaries. PLOS Digital Health, 4(6):e0000899. [find](https://scholar.google.com/scholar?q=ArXiv%2C+Brenda+Y%2E+Miao%2C+Atul+J%2E+Butte%2C+and+Aaron+E%2E+Kornblith%2E+2025%2E+Evaluating+large+language+models+for+drafting+emergency+department+encounter+summaries%2E+PLOS+Digital+Health%2C+4%286%29%3Ae0000899%2E)
9. Matthew J. Page, Joanne E. McKenzie, Patrick M. Bossuyt, Isabelle Boutron, Tammy C. Hoffmann, Cynthia D. Mulrow, Larissa Shamseer, Jennifer M. Tetzlaff, Elie A. Akl, Sue E. Brennan, Roger Chou, Julie Glanville, Jeremy M. Grimshaw, Asbjorn Hrobjartsson, Manoj M. Lalu, Tianjing Li, Elizabeth W. Loder,… [find](https://scholar.google.com/scholar?q=Matthew+J%2E+Page%2C+Joanne+E%2E+McKenzie%2C+Patrick+M%2E+Bossuyt%2C+Isabelle+Boutron%2C+Tammy+C%2E+Hoffmann%2C+Cynthia+D%2E+Mulrow%2C+Larissa+Shamseer%2C+Jennifer+M%2E+Tetzlaff%2C+Elie+A%2E+Akl%2C+Sue+E%2E+Brennan%2C+Roger+Chou%2C+Julie+)
10. Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E Gonzalez, and Ion Stoica. 2023. [Judging llm-as-a-judge with mt-bench and chatbot arena](https://md.research.elamur.ai/free/en/papers/zheng-2023-judging-llm-judge-mt-bench/). In Advances in Neural Information Processing Systems, volume 3…
11. Mark Petticrew and Helen Roberts. 2006. Systematic Reviews in the Social Sciences: A Practical Guide. Blackwell Publishing, Oxford, UK. [find](https://scholar.google.com/scholar?q=Mark+Petticrew+and+Helen+Roberts%2E+2006%2E+Systematic+Reviews+in+the+Social+Sciences%3A+A+Practical+Guide%2E+Blackwell+Publishing%2C+Oxford%2C+UK%2E)
12. Language Resource References Alistair E. W. Johnson, Tom J. Pollard, Lu Shen, Li-wei H. Lehman, Mengling Feng, Mohammad Ghassemi, Benjamin Moody, Peter Szolovits, Leo Anthony Celi, and Roger G. Mark. 2016. [MIMIC-III, a freely accessible critical care database](https://md.research.elamur.ai/free/en/papers/johnson-2016-mimic-iii-freely-accessible-critical/). Scientific Data, 3:160035.
13. Arne Schwieger, Katrin Angst, Mateo de Bardeci, Achim Burrer, Flurin Cathomas, Stefano Ferrea, Franziska Grätz, Marius Knorr, Golo Kronenberg, Tobias Spiller, David Troi, Erich Seifritz, Samantha Weber, and Sebastian Olbrich. 2024. Large language models can support generation of standardized dischar… [find](https://scholar.google.com/scholar?q=Arne+Schwieger%2C+Katrin+Angst%2C+Mateo+de+Bardeci%2C+Achim+Burrer%2C+Flurin+Cathomas%2C+Stefano+Ferrea%2C+Franziska+Gr%C3%A4tz%2C+Marius+Knorr%2C+Golo+Kronenberg%2C+Tobias+Spiller%2C+David+Troi%2C+Erich+Seifritz%2C+Samantha+Webe)
14. Christine Sinsky, Lacey Colligan, Ling Li, Mirela Prgomet, Sam Reynolds, Lindsey Goeders, Johanna Westbrook, Michael Tutty, and George Blike. 2016. Allocation of physician time in ambulatory practice: A time and motion study in 4 specialties. Annals of Internal Medicine, 165(11):753–760. [find](https://scholar.google.com/scholar?q=Christine+Sinsky%2C+Lacey+Colligan%2C+Ling+Li%2C+Mirela+Prgomet%2C+Sam+Reynolds%2C+Lindsey+Goeders%2C+Johanna+Westbrook%2C+Michael+Tutty%2C+and+George+Blike%2E+2016%2E+Allocation+of+physician+time+in+ambulatory+practice%3A)
15. Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timothée Lacroix, Baptiste Rozière, Naman Goyal, Eric Hambro, Faisal Azhar, Aurelien Rodriguez, Armand Joulin, Edouard Grave, and Guillaume Lample. 2023. [Llama: Open and efficient foundation language models](https://md.research.elamur.ai/free/en/papers/touvron-2023-llama-open-efficient-foundation-language/).
16. Alex Trejo Omeñaca, Esteve Llargués Rocabruna, Jonny Sloan, Michelle Catta-Preta, Jan Ferrer i Picó, Julio Cesar Alfaro Alvarez, Toni Alonso Solis, Eloy Lloveras Gil, Xavier Serrano Vinaixa, Daniela Velasquez Villegas, Ramon Romeu Garcia, Carles Rubies Feijoo, Josep Maria Monguet i Fierro, and Beatr… [find](https://scholar.google.com/scholar?q=Alex+Trejo+Ome%C3%B1aca%2C+Esteve+Llargu%C3%A9s+Rocabruna%2C+Jonny+Sloan%2C+Michelle+Catta%2DPreta%2C+Jan+Ferrer+i+Pic%C3%B3%2C+Julio+Cesar+Alfaro+Alvarez%2C+Toni+Alonso+Solis%2C+Eloy+Lloveras+Gil%2C+Xavier+Serrano+Vinaixa%2C+Daniela+V)
17. Christopher Y.K. Williams, Jaskaran Bains, Tianyu Tang, Kishan Patel, Alexa N. Lucas, Fiona Chen, [find](https://scholar.google.com/scholar?q=Christopher+Y%2EK%2E+Williams%2C+Jaskaran+Bains%2C+Tianyu+Tang%2C+Kishan+Patel%2C+Alexa+N%2E+Lucas%2C+Fiona+Chen%2C)

*Updated 1 November 2026*