Challenges in Imputation of ICU Time-Series Data: A Comparison of Classical and Machine Learning Approaches
DOI:
https://doi.org/10.32473/flairs.38.1.138964Abstract
Handling missing data is a major challenge in machine learning, particularly in clinical settings using electronic health records like ICU time-series data. Advanced imputation techniques, such as Bidirectional Recurrent Imputation for Time Series (BRITS), Self-Attention-based Imputation for Time Series (SAITS), and Multi-directional Recurrent Neural Network (M-RNN), show strong performance but are influenced by dataset characteristics like missing patterns and feature distributions. This study compares ten imputation methods on the public MIMIC-III database and COPRA, a local hospital dataset. We evaluate classical approaches (Zero, Mean, Median, Last), advanced models (BRITS, SAITS, M-RNN), and their transfer learning (TL) adaptations (TranBRITS, TranSAITS, TranM-RNN). TL was implemented by transforming COPRA to align with MIMIC-III, enabling fine-tuning of pre-trained models. TranSAITS achieved the best performance on the transformed dataset (M->C). Notably, the simple Last method also performed competitively for vital signs, underscoring its potential for real-time clinical use where low complexity and efficiency are key.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Favio Salinas, Marvin Agristean, Sobhan Moazemi, Steven Kessler, Bastian Dewitz, Hug Aubin, Artur Lichtenberg, Falko Schmid

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.