EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

CocktailAI : Discharge Summary Generator Using Template Document and Retrieval-Augmented Generation, and Hybrid-Cloud Hospital Information System Platform to Enable It

Tomohiro Kuroda, Keina Sado, Kenji Suda, Kazuya Okamoto, Masahiro Miyake, Hiroshi Tamura, Osamu Sugiyama, Goshiro Yamamoto

Studies in Health Technology and Informatics · 2025

DOI: 10.3233/shti250875 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Studies in Health Technology and Informatics, 2025. Verfasst von Tomohiro Kuroda und 7 weiteren Autor:innen. Beteiligte Einrichtung: Division of Medical Information Technology and Administration Planning, Kyoto University Hospital, Kyoto, Japan. Hauptthemen laut MEDLINE: Artificial Intelligence, Patient Discharge Summaries, Information Storage and Retrieval, Patient Discharge. Die Arbeit wurde bisher 1-mal zitiert (Crossref). Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The recent advancement of artificial intelligence (AI) technologies initiates health data science research. The hospital information system of university hospitals should enable easy access to such new technologies without harming data safety to accelerate the research. Kyoto University Hospital developed hybrid-cloud hospital information system to let researchers apply any cloud-enabled tools to clinical data. The platform successfully initiated AI research including a discharge summary generator. Emerging generative AI technology is expected to be a silver bullet to decrease documentation tasks of clinical staff. On the other hand, the straight-forward application of generative AI may cause several errors including the hallucination. We simply introduce retrieval-augmented generation to find the key information from inpatient records to finalized template document including the key information. The developed system, named CocktailAI, is applied for daily clinical activity to generate discharge summary for referral letters for a month. 56% of generated documents are published almost as it is and other 36% of generated documents are applied with a few additional sentences. In total, 92% of referral letter writing task was supported by the developed system.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Artificial IntelligencePatient Discharge SummariesInformation Storage and RetrievalPatient DischargeElectronic Health RecordsHospital Information SystemsCloud ComputingAcademic Medical CentersJapanHumans

Stichwörter der Autor:innen

Discharge SummaryGenerative AIHybrid-Cloud Hospital Information SystemRetrieval Augmented GenerationTemplate Document

Autor:innen und Institutionen

  • Division of Medical Information Technology and Administration Planning, Kyoto University Hospital, Kyoto, Japan.
  • Department of Ophthalmology and Visual Sciences, Graduate School of Medicine, Kyoto University, Kyoto, Japan.
  • Fitting Cloud Inc., Kyoto, Japan.
  • Graduate School of Science and Engineering, Kindai University, Higashi-Osaka, Japan.
  • Preemptive Medicine and Lifestyle Related Disease Research Center, Kyoto University Hospital, Kyoto, Japan.

Zitieren

APA

Kuroda, T., Sado, K., Suda, K., Okamoto, K., Miyake, M., Tamura, H., Sugiyama, O., & Yamamoto, G. (2025). CocktailAI : Discharge Summary Generator Using Template Document and Retrieval-Augmented Generation, and Hybrid-Cloud Hospital Information System Platform to Enable It. Studies in Health Technology and Informatics. https://doi.org/10.3233/shti250875

Vancouver

Kuroda T, Sado K, Suda K, Okamoto K, Miyake M, Tamura H, et al. CocktailAI : Discharge Summary Generator Using Template Document and Retrieval-Augmented Generation, and Hybrid-Cloud Hospital Information System Platform to Enable It. Studies in Health Technology and Informatics. 2025. doi:10.3233/shti250875

BibTeX
@article{Kuroda2025,
  author = {Kuroda, Tomohiro and Sado, Keina and Suda, Kenji and Okamoto, Kazuya and Miyake, Masahiro and Tamura, Hiroshi and Sugiyama, Osamu and Yamamoto, Goshiro},
  title = {CocktailAI : Discharge Summary Generator Using Template Document and Retrieval-Augmented Generation, and Hybrid-Cloud Hospital Information System Platform to Enable It},
  journal = {Studies in Health Technology and Informatics},
  year = {2025},
  doi = {10.3233/shti250875}
}
Kostenlos starten →