How Deep is your Guess? A Fresh Perspective on Deep Learning for Medical Time-Series Imputation
This work addresses imputation challenges in medical time-series data for healthcare applications, but it is incremental as it focuses on analyzing existing methods rather than introducing a new paradigm.
The study analyzed deep learning methods for imputing missing data in Electronic Health Record time-series, finding that model performance varies by up to 20% based on preprocessing and that larger models do not always improve results, emphasizing the need for clinically meaningful reconstruction over statistical accuracy.
We present a comprehensive analysis of deep learning approaches for Electronic Health Record (EHR) time-series imputation, examining how architectural and framework biases combine to influence model performance. Our investigation reveals varying capabilities of deep imputers in capturing complex spatiotemporal dependencies within EHRs, and that model effectiveness depends on how its combined biases align with medical time-series characteristics. Our experimental evaluation challenges common assumptions about model complexity, demonstrating that larger models do not necessarily improve performance. Rather, carefully designed architectures can better capture the complex patterns inherent in clinical data. The study highlights the need for imputation approaches that prioritise clinically meaningful data reconstruction over statistical accuracy. Our experiments show imputation performance variations of up to 20\% based on preprocessing and implementation choices, emphasising the need for standardised benchmarking methodologies. Finally, we identify critical gaps between current deep imputation methods and medical requirements, highlighting the importance of integrating clinical insights to achieve more reliable imputation approaches for healthcare applications.