DySurv: dynamic deep learning model for survival analysis with conditional variational inference
This work addresses the problem of dynamic survival analysis for intensive care unit patients, offering a novel deep learning method that improves predictive performance over standard clinical benchmarks, though it is incremental in applying variational inference to this domain.
The authors tackled dynamic risk prediction for time-to-event outcomes in healthcare by proposing DySurv, a conditional variational autoencoder-based model that uses static and longitudinal electronic health records to estimate individual death risk without parametric assumptions, achieving over 60% time-dependent concordance on eICU data and outperforming existing methods by over 12% in accuracy and 22% in sensitivity compared to clinical scores like APACHE and SOFA.
Machine learning applications for longitudinal electronic health records often forecast the risk of events at fixed time points, whereas survival analysis achieves dynamic risk prediction by estimating time-to-event distributions. Here, we propose a novel conditional variational autoencoder-based method, DySurv, which uses a combination of static and longitudinal measurements from electronic health records to estimate the individual risk of death dynamically. DySurv directly estimates the cumulative risk incidence function without making any parametric assumptions on the underlying stochastic process of the time-to-event. We evaluate DySurv on 6 time-to-event benchmark datasets in healthcare, as well as 2 real-world intensive care unit (ICU) electronic health records (EHR) datasets extracted from the eICU Collaborative Research (eICU) and the Medical Information Mart for Intensive Care database (MIMIC-IV). DySurv outperforms other existing statistical and deep learning approaches to time-to-event analysis across concordance and other metrics. It achieves time-dependent concordance of over 60% in the eICU case. It is also over 12% more accurate and 22% more sensitive than in-use ICU scores like Acute Physiology and Chronic Health Evaluation (APACHE) and Sequential Organ Failure Assessment (SOFA) scores. The predictive capacity of DySurv is consistent and the survival estimates remain disentangled across different datasets. Our interdisciplinary framework successfully incorporates deep learning, survival analysis, and intensive care to create a novel method for time-to-event prediction from longitudinal health records. We test our method on several held-out test sets from a variety of healthcare datasets and compare it to existing in-use clinical risk scoring benchmarks.