Generating Survival Interpretable Trajectories and Data

TL;DR

This paper introduces a novel autoencoder-based model that generates survival data, predicts event times, and creates interpretable trajectories, offering a new way to understand and augment survival analysis with counterfactual insights.

Contribution

It presents a new autoencoder structure that predicts survival outcomes, generates additional data, and produces interpretable, time-dependent trajectories for counterfactual analysis.

Findings

Model is robust during training and inference.

Effective on synthetic and real datasets.

Provides interpretable trajectories for survival analysis.

Abstract

A new model for generating survival trajectories and data based on applying an autoencoder of a specific structure is proposed. It solves three tasks. First, it provides predictions in the form of the expected event time and the survival function for a new generated feature vector on the basis of the Beran estimator. Second, the model generates additional data based on a given training set that would supplement the original dataset. Third, the most important, it generates a prototype time-dependent trajectory for an object, which characterizes how features of the object could be changed to achieve a different time to an event. The trajectory can be viewed as a type of the counterfactual explanation. The proposed model is robust during training and inference due to a specific weighting scheme incorporating into the variational autoencoder. The model also determines the censored indicators of new generated data by solving a classification task. The paper demonstrates the efficiency and properties of the proposed model using numerical experiments on synthetic and real datasets. The code of the algorithm implementing the proposed model is publicly available.