Estimating individual risk of catheter-associated urinary tract infections using explainable artificial intelligence on clinical data

Herdiantri Sufriyana; Chieh Chen; Hua-Sheng Chiu; Pavel Sumazin; Po-Yu Yang; Jiunn-Horng Kang; Emily Chia-Yu Su

doi:10.1016/j.ajic.2024.10.027

Estimating individual risk of catheter-associated urinary tract infections using explainable artificial intelligence on clinical data

Am J Infect Control. 2024 Oct 29:S0196-6553(24)00819-8. doi: 10.1016/j.ajic.2024.10.027. Online ahead of print.

Authors

Herdiantri Sufriyana¹, Chieh Chen², Hua-Sheng Chiu³, Pavel Sumazin³, Po-Yu Yang⁴, Jiunn-Horng Kang⁵, Emily Chia-Yu Su⁶

Affiliations

¹ Institute of Biomedical Informatics, College of Medicine, National Yang Ming Chiao Tung University, 155, Section 2, Linong Street, Taipei 112304, Taiwan; Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, 250 Wu-Xing Street, Taipei 11031, Taiwan.
² Department of Physical Medicine and Rehabilitation, Taipei Medical University Hospital, 252 Wu-Xing Street, Taipei 11031, Taiwan.
³ Texas Children's Cancer Center, Baylor College of Medicine, Houston, TX 77030, USA.
⁴ School of Medicine, College of Medicine, Taipei Medical University, 250 Wu-Xing Street, Taipei 11031, Taiwan.
⁵ Graduate Institute of Nanomedicine and Medical Engineering, Taipei Medical University, 250 Wu-Xing Street, Taipei 11031, Taiwan; Research Center for Artificial Intelligence in Medicine, Taipei Medical University, 250 Wu-Xing Street, Taipei 11031, Taiwan. Electronic address: jhk@tmu.edu.tw.
⁶ Institute of Biomedical Informatics, College of Medicine, National Yang Ming Chiao Tung University, 155, Section 2, Linong Street, Taipei 112304, Taiwan; Graduate Institute of Biomedical Informatics, College of Medical Science and Technology, Taipei Medical University, 250 Wu-Xing Street, Taipei 11031, Taiwan. Electronic address: emilysu@nycu.edu.tw.

PMID: 39481544
DOI: 10.1016/j.ajic.2024.10.027

Abstract

Background: Catheter-associated urinary tract infections (CAUTIs) increase clinical burdens. Identifying the high-risk patients is crucial. We aimed to develop and externally validate an explainable, prognostic prediction model of CAUTIs among hospitalized individuals receiving urinary catheterization.

Methods: A retrospective cohort paradigm was applied for model development and validation using data from two hospitals and used the third hospital's data for external validation. Machine learning algorithms were applied for predictive modeling. We evaluated the calibration, clinical utility, and discrimination ability to choose the best model by the validation set. The best model was assessed for the explainability.

Results: We included 122,417 instances from 20-to-75-year-old subjects. Fourteen predictors were selected from 20 candidates. The best model was the RF for prediction within 6 days. It detected 97.63% (95% confidence interval [CI]: ±0.06%) CAUTI positive, and 97.36% (95% CI: ±0.07%) of individuals that were predicted to be CAUTI negative were true negatives. Among those predicted to be CAUTI positives, we expected 22.85% (95% CI: ±0.07%) of them to truly be high-risk individuals. We provide a web-based application and a paper-based nomogram for using this model.

Conclusions: Our prediction model accurately detected most CAUTI positive cases, while most predicted negative individuals were correctly ruled out.

Keywords: catheter-associated urinary tract infection; clinical risk prediction; explainable artificial intelligence; machine learning; nomogram.