Explainable Artificial Intelligence Techniques for Irregular Temporal Classification of Multidrug Resistance Acquisition in Intensive Care Unit Patients

TL;DR

This paper presents a novel explainable AI approach using GRUs and advanced interpretability techniques to detect and understand the risk factors of Multidrug-Resistant infections in ICU patients over time.

Contribution

It introduces Irregular Time Shapley Additive Explanations (IT-SHAP) for irregular multivariate time series and combines it with GRUs and attention mechanisms for improved interpretability.

Findings

Achieved an average AUC of 78.27% in predicting MDR onset.

Identified key risk factors such as prior non-resistant cultures and antibiotic patterns.

Demonstrated high specificity and increasing sensitivity over ICU stay durations.

Abstract

Antimicrobial Resistance represents a significant challenge in the Intensive Care Unit (ICU), where patients are at heightened risk of Multidrug-Resistant (MDR) infections-pathogens resistant to multiple antimicrobial agents. This study introduces a novel methodology that integrates Gated Recurrent Units (GRUs) with advanced intrinsic and post-hoc interpretability techniques for detecting the onset of MDR in patients across time. Within interpretability methods, we propose Explainable Artificial Intelligence (XAI) approaches to handle irregular Multivariate Time Series (MTS), introducing Irregular Time Shapley Additive Explanations (IT-SHAP), a modification of Shapley Additive Explanations designed for irregular MTS with Recurrent Neural Networks focused on temporal outputs. Our methodology aims to identify specific risk factors associated with MDR in ICU patients. GRU with Hadamard's attention demonstrated high initial specificity and increasing sensitivity over time, correlating with increased nosocomial infection risks during prolonged ICU stays. XAI analysis, enhanced by Hadamard attention and IT-SHAP, identified critical factors such as previous non-resistant cultures, specific antibiotic usage patterns, and hospital environment dynamics. These insights suggest that early detection of at-risk patients can inform interventions such as preventive isolation and customized treatments, significantly improving clinical outcomes. The proposed GRU model for temporal classification achieved an average Receiver Operating Characteristic Area Under the Curve of 78.27 +- 1.26 over time, indicating strong predictive performance. In summary, this study highlights the clinical utility of our methodology, which combines predictive accuracy with interpretability, thereby facilitating more effective healthcare interventions by professionals.