CRISP-NAM: Competing Risks Interpretable Survival Prediction with Neural Additive Models
This addresses the need for interpretable survival prediction in healthcare, where patients face multiple risks, but it appears incremental as it builds on existing neural additive models.
The paper tackled the problem of competing risks survival analysis in healthcare by proposing CRISP-NAM, an interpretable neural additive model that extends neural additive architectures to handle multiple event types, and demonstrated competitive performance on multiple datasets.
Competing risks are crucial considerations in survival modelling, particularly in healthcare domains where patients may experience multiple distinct event types. We propose CRISP-NAM (Competing Risks Interpretable Survival Prediction with Neural Additive Models), an interpretable neural additive model for competing risks survival analysis which extends the neural additive architecture to model cause-specific hazards while preserving feature-level interpretability. Each feature contributes independently to risk estimation through dedicated neural networks, allowing for visualization of complex non-linear relationships between covariates and each competing risk. We demonstrate competitive performance on multiple datasets compared to existing approaches.