A Data-Driven Approach to Support Clinical Renal Replacement Therapy

2026-02-26

AI Summary

This study addresses the prediction of membrane fouling risk during continuous renal replacement therapy (CRRT) in critically ill patients to minimize treatment interruptions and optimize clinical interventions. To handle ICU time-series data, the authors propose a concise and interpretable tabular modeling strategy that avoids complex temporal architectures. Class imbalance is mitigated using ADASYN, and predictive performance is evaluated with Random Forest, XGBoost, and LightGBM. Shapley-value-based counterfactual analysis identifies key actionable variables, enabling a highly efficient model that achieves 77.6% sensitivity and 96.3% specificity using only five core features at a 10% rebalancing rate. The approach demonstrates superior performance compared to LSTM, underscoring its robustness and clinical utility.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

This study investigates a data-driven machine learning approach to predict membrane fouling in critically ill patients undergoing Continuous Renal Replacement Therapy (CRRT). Using time-series data from an ICU, 16 clinically selected features were identified to train predictive models. To ensure interpretability and enable reliable counterfactual analysis, the researchers adopted a tabular data approach rather than modeling temporal dependencies directly. Given the imbalance between fouling and non-fouling cases, the ADASYN oversampling technique was applied to improve minority class representation. Random Forest, XGBoost, and LightGBM models were tested, achieving balanced performance with 77.6% sensitivity and 96.3% specificity at a 10% rebalancing rate. Results remained robust across different forecasting horizons. Notably, the tabular approach outperformed LSTM recurrent neural networks, suggesting that explicit temporal modeling was not necessary for strong predictive performance. Feature selection further reduced the model to five key variables, improving simplicity and interpretability with minimal loss of accuracy. A Shapley value-based counterfactual analysis was applied to the best-performing model, successfully identifying minimal input changes capable of reversing fouling predictions. Overall, the findings support the viability of interpretable machine learning models for predicting membrane fouling during CRRT. The integration of prediction and counterfactual analysis offers practical clinical value, potentially guiding therapeutic adjustments to reduce fouling risk and improve patient management.

Problem

• membrane fouling
• Continuous Renal Replacement Therapy
• CRRT
• predictive modeling
• critical care

Innovation

• interpretable machine learning
• membrane fouling prediction
• counterfactual analysis
• tabular data modeling
• CRRT