Claudius Diez
Research Subjects
Claudius Diez has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Annaclaudia Montanino
Division of Neuronic Engineering, Royal Institute of Technology (KTH), Huddinge, Sweden
1 shared publication - Ioanna Miliou
Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden
1 shared publication - Lena Mondrejevski
Stockholm University,Dept. of Computer and Systems Sciences,Stockholm,Sweden
1 shared publication - Panagiotis Papapetrou
Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden
1 shared publication
Latest Publications
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 819-826
X4FL: Explainability for Federated Learning in ICU Mortality Prediction
Federated Learning (FL) enables collaborative Machine Learning (ML) model training across institutions without sharing sensitive data, a critical advantage in healthcare. However, existing FL approaches for Intensive Care Unit (ICU) mortality prediction largely overlook explainability, which is essential for clinician trust. In this study, we present X4FL, a novel framework that integrates intrinsic and post-hoc interpretability into FL for ICU mortality prediction using the MIMIC-III dataset. X4FL employs an attention-based Long Short-Term Memory (LSTM) to capture temporal relevance at the feature level and combines it with SHapley Additive exPlanations (SHAP) to quantify feature importance. This dual explainability design yields clinically meaningful insights by highlighting both influential time segments and predictive features. Under a realistic non-Independent and Identically Distributed (non-IID) federated setup reflecting heterogeneous ICU populations, X4FL achieves predictive performance comparable to centralized models while consistently outperforming locally trained models, particularly in smaller or specialized ICUs. Attention heatmaps capture clinically relevant temporal patterns, and SHAP analyses reveal robust feature attributions across distributed settings. By addressing the trade-off between performance and interpretability, X4FL enhances transparency and trust in FL-based ICU mortality prediction, offering a step toward clinically viable federated solutions in critical care.
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 819-826
X4FL: Explainability for Federated Learning in ICU Mortality Prediction
Federated Learning (FL) enables collaborative Machine Learning (ML) model training across institutions without sharing sensitive data, a critical advantage in healthcare. However, existing FL approaches for Intensive Care Unit (ICU) mortality prediction largely overlook explainability, which is essential for clinician trust. In this study, we present X4FL, a novel framework that integrates intrinsic and post-hoc interpretability into FL for ICU mortality prediction using the MIMIC-III dataset. X4FL employs an attention-based Long Short-Term Memory (LSTM) to capture temporal relevance at the feature level and combines it with SHapley Additive exPlanations (SHAP) to quantify feature importance. This dual explainability design yields clinically meaningful insights by highlighting both influential time segments and predictive features. Under a realistic non-Independent and Identically Distributed (non-IID) federated setup reflecting heterogeneous ICU populations, X4FL achieves predictive performance comparable to centralized models while consistently outperforming locally trained models, particularly in smaller or specialized ICUs. Attention heatmaps capture clinically relevant temporal patterns, and SHAP analyses reveal robust feature attributions across distributed settings. By addressing the trade-off between performance and interpretability, X4FL enhances transparency and trust in FL-based ICU mortality prediction, offering a step toward clinically viable federated solutions in critical care.