In-hospital mortality, readmission, and prolonged length of stay risk prediction leveraging historical electronic patient records

Rajeev Bopche; Lise Tuset Gustad; Jan Egil Afset; Birgitta Ehrnström; Jan Kristian Damås; Øystein Nytrø

doi:10.1093/jamiaopen/ooae074

In-hospital mortality, readmission, and prolonged length of stay risk prediction leveraging historical electronic patient records

JAMIA Open. 2024 Sep 14;7(3):ooae074. doi: 10.1093/jamiaopen/ooae074. eCollection 2024 Oct.

Authors

Rajeev Bopche¹, Lise Tuset Gustad^{2

3}, Jan Egil Afset^{4

5}, Birgitta Ehrnström^{5

6

7}, Jan Kristian Damås^{5

6}, Øystein Nytrø^{1

8}

Affiliations

¹ Department of Computer Science, Norwegian University of Science and Technology, Trondheim, 7491, Norway.
² Faculty of Nursing and Health Sciences, Nord University, Levanger, 7600, Norway.
³ Department of Medicine and Rehabilitation, Levanger Hospital, Nord-Trøndelag Hospital Trust, Levanger, 7601, Norway.
⁴ Department of Medical Microbiology, St Olavs Hospital, Trondheim University Hospital, Trondheim, 7030, Norway.
⁵ Department of Clinical and Molecular Medicine, Norwegian University of Science and Technology, Trondheim, 7491, Norway.
⁶ Department of Infectious Diseases, Clinic of Medicine, St Olavs Hospital, Trondheim, 7006, Norway.
⁷ Clinic of Anaesthesia and Intensive Care, St Olavs Hospital, Trondheim University Hospital, Trondheim, 7006, Norway.
⁸ Department of Computer Science, The Arctic University of Norway, Tromsø, 9037, Norway.

Abstract

Objective: This study aimed to investigate the predictive capabilities of historical patient records to predict patient adverse outcomes such as mortality, readmission, and prolonged length of stay (PLOS).

Methods: Leveraging a de-identified dataset from a tertiary care university hospital, we developed an eXplainable Artificial Intelligence (XAI) framework combining tree-based and traditional machine learning (ML) models with interpretations and statistical analysis of predictors of mortality, readmission, and PLOS.

Results: Our framework demonstrated exceptional predictive performance with a notable area under the receiver operating characteristic (AUROC) of 0.9625 and an area under the precision-recall curve (AUPRC) of 0.8575 for 30-day mortality at discharge and an AUROC of 0.9545 and AUPRC of 0.8419 at admission. For the readmission and PLOS risk, the highest AUROC achieved were 0.8198 and 0.9797, respectively. The tree-based models consistently outperformed the traditional ML models in all 4 prediction tasks. The key predictors were age, derived temporal features, routine laboratory tests, and diagnostic and procedural codes.

Conclusion: The study underscores the potential of leveraging medical history for enhanced hospital predictive analytics. We present an accurate and intuitive framework for early warning models that can be easily implemented in the current and developing digital health platforms to predict adverse outcomes accurately.

Keywords: eXplainable Artificial Intelligence; electronic patient records; healthcare informatics; machine learning; medical history; mortality; predictive analytics; prolonged length of stay; readmission; tree-based models.