Explainable AI for Infection Prevention and Control: Modeling CPE Acquisition and Patient Outcomes in an Irish Hospital with Transformers

2025-09-18

AI Summary

Carbapenemase-producing Enterobacterales (CPE) infections are associated with adverse outcomes including readmission, mortality, and prolonged hospitalization. Method: We developed an interpretable TabTransformer-based framework integrating clinical variables (e.g., diagnosis codes, demographic features, admission background) and contact-network-derived structural features—including ward transfer trajectories and PageRank centrality computed from ward-level contact networks—using multicenter electronic health record data from Ireland. Explainable AI (XAI) techniques were applied for quantitative attribution of key risk factors (e.g., prior hospital exposure, admission context, network centrality). Contribution/Results: The model achieves significantly higher AUROC and sensitivity than conventional methods. It identifies geographic distribution, initial admitting department, and ward-level transmission hubness as critical drivers of nosocomial CPE spread. By delivering transparent, clinically actionable insights, this framework supports precision infection prevention and control.

Technology Category

• Humans and AI: Explainable AI (XAI) for Human Understanding
• Machine Learning: Transparent, Interpretable, Explainable ML
• Computer Vision: Interpretability, Explainability, and Transparency

Application Category

• Security and Privacy: Data transparency and provenance
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Responsible Web: Algorithmic accountability and transparency on the web

Abstract

Carbapenemase-Producing Enterobacteriace poses a critical concern for infection prevention and control in hospitals. However, predictive modeling of previously highlighted CPE-associated risks such as readmission, mortality, and extended length of stay (LOS) remains underexplored, particularly with modern deep learning approaches. This study introduces an eXplainable AI modeling framework to investigate CPE impact on patient outcomes from Electronic Medical Records data of an Irish hospital. We analyzed an inpatient dataset from an Irish acute hospital, incorporating diagnostic codes, ward transitions, patient demographics, infection-related variables and contact network features. Several Transformer-based architectures were benchmarked alongside traditional machine learning models. Clinical outcomes were predicted, and XAI techniques were applied to interpret model decisions. Our framework successfully demonstrated the utility of Transformer-based models, with TabTransformer consistently outperforming baselines across multiple clinical prediction tasks, especially for CPE acquisition (AUROC and sensitivity). We found infection-related features, including historical hospital exposure, admission context, and network centrality measures, to be highly influential in predicting patient outcomes and CPE acquisition risk. Explainability analyses revealed that features like "Area of Residence", "Admission Ward" and prior admissions are key risk factors. Network variables like "Ward PageRank" also ranked highly, reflecting the potential value of structural exposure information. This study presents a robust and explainable AI framework for analyzing complex EMR data to identify key risk factors and predict CPE-related outcomes. Our findings underscore the superior performance of the Transformer models and highlight the importance of diverse clinical and network features.

Problem

• Modeling CPE acquisition risk in hospital patients
• Predicting patient outcomes using EMR data
• Identifying key risk factors with explainable AI

Innovation

• Transformer-based models for clinical prediction
• Explainable AI framework for EMR analysis
• Network features and infection variables integration