Deep State-Space Generative Model For Correlated Time-to-Event Predictions
This work addresses the challenge of accurate future event prediction and treatment planning for patients with correlated clinical events, representing a domain-specific incremental improvement.
The authors tackled the problem of predicting correlated clinical events like kidney failure and mortality by proposing a deep latent state-space generative model that captures interactions and temporal dynamics, resulting in significantly improved accuracy in survival distribution estimation compared to state-of-the-art baselines.
Capturing the inter-dependencies among multiple types of clinically-critical events is critical not only to accurate future event prediction, but also to better treatment planning. In this work, we propose a deep latent state-space generative model to capture the interactions among different types of correlated clinical events (e.g., kidney failure, mortality) by explicitly modeling the temporal dynamics of patients' latent states. Based on these learned patient states, we further develop a new general discrete-time formulation of the hazard rate function to estimate the survival distribution of patients with significantly improved accuracy. Extensive evaluations over real EMR data show that our proposed model compares favorably to various state-of-the-art baselines. Furthermore, our method also uncovers meaningful insights about the latent correlations among mortality and different types of organ failures.