Federated Markov Imputation: Privacy-Preserving Temporal Imputation in Multi-Centric ICU Environments
Machine Learning
2025-09-26 v1 Artificial Intelligence
Abstract
Missing data is a persistent challenge in federated learning on electronic health records, particularly when institutions collect time-series data at varying temporal granularities. To address this, we propose Federated Markov Imputation (FMI), a privacy-preserving method that enables Intensive Care Units (ICUs) to collaboratively build global transition models for temporal imputation. We evaluate FMI on a real-world sepsis onset prediction task using the MIMIC-IV dataset and show that it outperforms local imputation baselines, especially in scenarios with irregular sampling intervals across ICUs.
Keywords
Cite
@article{arxiv.2509.20867,
title = {Federated Markov Imputation: Privacy-Preserving Temporal Imputation in Multi-Centric ICU Environments},
author = {Christoph Düsing and Philipp Cimiano},
journal= {arXiv preprint arXiv:2509.20867},
year = {2025}
}
Comments
Accepted at the 1st International ECML-PKDD Workshop-Tutorial on Learning on Real and Synthetic Medical Time Series Data (MED-TIME)