Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Data-Driven Approach to Support Clinical Renal Replacement Therapy

Alice Balboni, Luis Escobar, Andrea Manno, Fabrizio Rossi, Maria Cristina Ruffa, Gianluca Villa, Giordano D'Aloisio, Antonio Consolo

TL;DR

The findings support the viability of interpretable machine learning models for predicting membrane fouling during CRRT, and the integration of prediction and counterfactual analysis offers practical clinical value, potentially guiding therapeutic adjustments to reduce fouling risk and improve patient management.

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.

A Data-Driven Approach to Support Clinical Renal Replacement Therapy

TL;DR

The findings support the viability of interpretable machine learning models for predicting membrane fouling during CRRT, and the integration of prediction and counterfactual analysis offers practical clinical value, potentially guiding therapeutic adjustments to reduce fouling risk and improve patient management.

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.
Paper Structure (13 sections, 3 equations, 4 figures, 5 tables)

This paper contains 13 sections, 3 equations, 4 figures, 5 tables.

Table of Contents

  1. Introduction
  2. Methods
  3. The dataset and the labeling process
  4. Tabular data design
  5. Rebalancing methods
  6. Model selection and hyperparameters configuration
  7. Results
  8. Post-processing function
  9. Experiments' configuration
  10. Models' predictive performance
  11. Counterfactual Analysis
  12. Conclusions
  13. Funding acknowledgments

Figures (4)

  • Figure 1: labeling process.
  • Figure 2: The real (in yellow), predicted (in blue), and post-processed predicted (in green) profiles of the class labels, for an exemplificative instance.
  • Figure 3: SHAP analysis for the XGBoost model with 10 minutes lag.
  • Figure 4: Counterfactual ability-$c_{L_1}$: number of successes over 1000 tests.