Interpretable machine learning-based prediction of mortality in critical cancer patients with delirium: A retrospective cohort study
This study developed an optimal and explainable ML model for predicting 28-day mortality in cancer patients with delirium. The CatBoost algorithm demonstrated stable and robust performance, and interpretability analysis highlighted key predictors. These findings may aid early clinical decision-making and targeted interventions for this high-risk population.
Authors
- Yingchun Zeng (ORCID: https://orcid.org/0000-0001-9250-4086)
- Sicheng Hao (ORCID: https://orcid.org/0000-0002-8905-005X)
- Yang He (ORCID: https://orcid.org/0009-0006-5184-3069)
- Ning Liu (ORCID: https://orcid.org/0000-0002-6552-8207)
- Min Xu (ORCID: https://orcid.org/0000-0003-3930-8718)
Institutions
- National University of Singapore (SG)
- Sir Run Run Shaw Hospital (CN)
- Quzhou City People's Hospital (CN)
- Massachusetts Institute of Technology (US)
Publication Details
- Journal
- Asia-Pacific Journal of Oncology Nursing
- Published
- 2025-07-19
- DOI
- https://doi.org/10.1016/j.apjon.2025.100760
- Citations
- 1
- Primary Topic
- Intensive Care Unit Cognitive Disorders
- Type
- article
- Field-Weighted Citation Impact
- 1.55
Funders
- National University of Singapore
- Medical Science and Technology Project of Zhejiang Province