SeqRisk: Transformer-augmented latent variable model for robust survival prediction with longitudinal data
This work addresses the challenge of leveraging longitudinal patient history for more accurate risk assessment in healthcare, though it appears incremental as it builds on existing methods like VAEs and transformers.
The authors tackled the problem of robust survival prediction from irregular and sparse longitudinal clinical data by proposing SeqRisk, a method combining latent variable models with transformers and Cox regression, which demonstrated robust performance and consistently surpassed existing approaches under increasing sparsity conditions.
In healthcare, risk assessment of patient outcomes has been based on survival analysis for a long time, i.e. modeling time-to-event associations. However, conventional approaches rely on data from a single time-point, making them suboptimal for fully leveraging longitudinal patient history and capturing temporal regularities. Focusing on clinical real-world data and acknowledging its challenges, we utilize latent variable models to effectively handle irregular, noisy, and sparsely observed longitudinal data. We propose SeqRisk, a method that combines variational autoencoder (VAE) or longitudinal VAE (LVAE) with a transformer-based sequence aggregation and Cox proportional hazards module for risk prediction. SeqRisk captures long-range interactions, enhances predictive accuracy and generalizability, as well as provides partial explainability for sample population characteristics in attempts to identify high-risk patients. SeqRisk demonstrated robust performance under conditions of increasing sparsity, consistently surpassing existing approaches.