EUVIMEDEUVIMED entdecken
Open Access

Improving postoperative length of stay forecasting with retrieval-augmented prediction

Brian H Park, Chun-Nan Hsu, Austin Nguyen, Ying Q Zhou iD, Rodney A Gabriel

Journal of the American Medical Informatics Association · 2025

DOI: 10.1093/jamia/ocaf154 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of the American Medical Informatics Association, 2025. Verfasst von Brian H Park und 4 weiteren Autor:innen. Beteiligte Einrichtung: Division of Perioperative Informatics, Department of Anesthesiology, University of California San Diego, La Jolla, CA 92037, United States. Hauptthemen laut MEDLINE: Length of Stay, Electronic Health Records, Machine Learning, Natural Language Processing. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: NIH HHS, NLM NIH HHS, NIGMS NIH HHS.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

The objective of this study is to evaluate retrieval-augmented prediction for forecasting hospital length of stay (LOS) following surgery compared to traditional machine learning (ML), standalone large language models (LLMs), and retrieval-augmented generation (RAG) approaches. Materials and Methods Spine surgery cases were extracted from electronic health records. Structured features and operative notes were concatenated into natural language patient representations, embedded using Sentence-Bidirectional Encoder Representations from Transformer, and stored in a vector database. Eight predictive models were implemented, including a baseline model, standalone ML with embeddings, standalone LLM (Gemma 3:27B), and combinations of these with retrieval-augmented prediction or generation. The retrieval-augmented prediction model computed a similarity-weighted average LOS from nearest neighbors. Performance was assessed using R2, mean absolute value (MAE), and root mean square error (RMSE).

Results

Retrieval-augmented prediction alone outperformed standalone ML and LLM models (R2 = 0.39, MAE = 4.47). Combining ML or LLM outputs with retrieval-augmented prediction further improved performance. The best performing model was a neural network blended with retrieval-augmented prediction (R2 = 0.52, MAE = 4.16). LLM-RAG alone reached R2 = 0.19, which improved to 0.47 when combined with retrieval-augmented predictions. Retrieval-augmented prediction consistently reduced MAE and RMSE by up to 32% and 38%, respectively.

Discussion

Retrieval-augmented prediction offers interpretable and resource-efficient forecasting by semantically leveraging prior patient cases without generative modeling. It consistently outperformed RAG and ML across metrics, approximating clinical reasoning via similarity-based inference.

Conclusion

Retrieval-augmented prediction significantly enhances LOS prediction accuracy over standard ML and LLM models. Its interpretability and scalability make it a promising solution for integrating predictive analytics into clinical workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Length of StayElectronic Health RecordsMachine LearningNatural Language ProcessingSpineHumansForecasting

Stichwörter der Autor:innen

large language modellength of staymachine learningnatural language processingspine/surgery

Autor:innen und Institutionen

  • Division of Perioperative Informatics, Department of Anesthesiology, University of California San Diego, La Jolla, CA 92037, United States.
  • School of Medicine, University of California San Diego, La Jolla, CA 92037, United States.

ORCID-Profile: Ying Q Zhou

Förderung

  • NIH HHS
  • NLM NIH HHS
  • NIGMS NIH HHS
  • National Institute of General Medical Sciences

Zitieren

APA

Park, B. H., Hsu, C. N., Nguyen, A., Zhou, Y. Q., & Gabriel, R. A. (2025). Improving postoperative length of stay forecasting with retrieval-augmented prediction. Journal of the American Medical Informatics Association. https://doi.org/10.1093/jamia/ocaf154

Vancouver

Park BH, Hsu CN, Nguyen A, Zhou YQ, Gabriel RA. Improving postoperative length of stay forecasting with retrieval-augmented prediction. Journal of the American Medical Informatics Association. 2025. doi:10.1093/jamia/ocaf154

BibTeX
@article{Park2025,
  author = {Park, Brian H and Hsu, Chun-Nan and Nguyen, Austin and Zhou, Ying Q and Gabriel, Rodney A},
  title = {Improving postoperative length of stay forecasting with retrieval-augmented prediction},
  journal = {Journal of the American Medical Informatics Association},
  year = {2025},
  doi = {10.1093/jamia/ocaf154}
}
Kostenlos starten →