Patient Event Sequences for Predicting Hospitalization Length of Stay

Emil Riis Hansen, Thomas Dyhre Nielsen, Thomas Mulvad Larsen, Mads Nibe Strausholm, Tomer Sagi, Katja Hose

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review


Predicting patients' hospital length of stay (LOS) is essential for improving resource allocation and supporting decision-making in healthcare organizations. This paper proposes a novel transformer-based model, termed Medic-BERT (M-BERT), for predicting LOS by modeling patient information as sequences of events. We performed empirical experiments on a cohort of $48k$ emergency care patients from a large Danish hospital. Experimental results show that M-BERT can achieve high accuracy on a variety of LOS problems and outperforms traditional non-sequence-based machine learning approaches.
Original languageEnglish
Title of host publicationArtificial Intelligence in Medicine - 21st International Conference on Artificial Intelligence in Medicine, AIME 2023, Proceedings
EditorsJose M. Juarez, Mar Marcos, Gregor Stiglic, Allan Tucker
Number of pages6
PublisherSpringer, Cham
Publication date7 Jun 2023
ISBN (Print)9783031343438
Publication statusPublished - 7 Jun 2023
EventInternational Conference on Artificial Intelligence in Medicine - Bernardin Congress Centre, Portoroz, Slovenia
Duration: 12 Jun 202315 Jun 2023


ConferenceInternational Conference on Artificial Intelligence in Medicine
LocationBernardin Congress Centre
Internet address


  • length of stay prediction
  • sequence models
  • transformers


Dive into the research topics of 'Patient Event Sequences for Predicting Hospitalization Length of Stay'. Together they form a unique fingerprint.

Cite this