A Review of Deep Learning Methods for Irregularly Sampled Medical Time Series Data

Importance: Medical time series constitute the largest data type in electronic health records and are often irregularly sampled in real-world clinical settings. Such irregularly sampled medical time series exhibit uneven time intervals, missing observations, and heterogeneous sampling rates, posing substantial challenges for deep learning models. Highlights: In this paper, from an irregularity-aware and data-centric perspective, we categorize existing deep learning methods for irregularly sampled medical time series into missing-data-based and raw-data-based approaches. We analyze their theoretical foundations and practical implications and conduct experiments on benchmark and real-world medical datasets to compare their strengths and limitations. Conclusion: Based on these analyses, we provide practical recommendations and discuss open problems and future research directions for modeling irregularly sampled medical time series.