Deep Kernel Aalen-Johansen Estimator: An Interpretable and Flexible Neural Net Framework for Competing Risks

TL;DR

The paper introduces the Deep Kernel Aalen-Johansen estimator, a neural network framework that provides interpretable, flexible predictions for competing risks by combining classical nonparametric estimates with learned similarity kernels.

Contribution

It presents a novel deep competing risks model that generalizes the Aalen-Johansen estimator using learned kernels for interpretability and flexibility.

Findings

Competitive performance on four datasets

Provides visualizations for model interpretation

Generalizes classical nonparametric estimates

Abstract

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.