Deep Kernel Aalen-Johansen Estimator: An Interpretable and Flexible Neural Net Framework for Competing Risks
This work addresses the need for interpretable and flexible models in survival analysis for domains like healthcare, though it is incremental as it builds on existing methods.
The authors tackled the problem of estimating cumulative incidence functions in competing risks data by proposing the Deep Kernel Aalen-Johansen estimator, which generalizes a classical nonparametric method and achieves competitive performance with state-of-the-art baselines on four standard datasets while providing interpretable visualizations.
We propose an interpretable deep competing risks model called the Deep Kernel Aalen-Johansen (DKAJ) estimator, which generalizes the classical Aalen-Johansen nonparametric estimate of cumulative incidence functions (CIFs). Each data point (e.g., patient) is represented as a weighted combination of clusters. If a data point has nonzero weight only for one cluster, then its predicted CIFs correspond to those of the classical Aalen-Johansen estimator restricted to data points from that cluster. These weights come from an automatically learned kernel function that measures how similar any two data points are. On four standard competing risks datasets, we show that DKAJ is competitive with state-of-the-art baselines while being able to provide visualizations to assist model interpretation.