Artificial intelligence-driven prediction and interpretation of central line-associated bloodstream infections in ICU: insights from the MIMIC-IV database
Machine learning models, particularly the random forest model, accurately predict CLABSI risk in ICU patients. The use of interpretable AI techniques such as SHAP enhances transparency and provides actionable insights for clinical practice. These findings support the development of early warning systems to reduce CLABSI incidence and improve patient outcomes.
Authors
- Gaosheng Zhou (ORCID: https://orcid.org/0000-0001-5268-1491)
- Na Li (ORCID: https://orcid.org/0000-0002-9777-5798)
- Yang He (ORCID: https://orcid.org/0009-0004-4651-328X)
- Jinglan Liu (ORCID: https://orcid.org/0000-0001-5761-8598)
- Jiali Huang
Institutions
- China Three Gorges University (CN)
- Hubei Water Resources Research Institute (CN)
- Second Hospital of Yichang (CN)
- Yichang Central People's Hospital (CN)
Publication Details
- Journal
- Frontiers in Public Health
- Published
- 2025-09-25
- DOI
- https://doi.org/10.3389/fpubh.2025.1675077
- Primary Topic
- Central Venous Catheters and Hemodialysis
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Massachusetts Institute of Technology