Continuous Treatment Recommendation with Deep Survival Dose Response Function

TL;DR

This paper introduces DeepSDRF, a novel deep learning framework for estimating continuous treatment effects in clinical survival data, enabling bias-corrected recommendations from observational datasets.

Contribution

It presents the first causal model for continuous treatment effects in medical settings using observational data, with new recommender algorithms based on DeepSDRF.

Findings

DeepSDRF accurately estimates treatment effects in simulations.

Recommender algorithms perform similarly in patient outcome optimization.

Model validated on extensive simulation and real-world eICU data.

Abstract

We propose a general formulation for continuous treatment recommendation problems in settings with clinical survival data, which we call the Deep Survival Dose Response Function (DeepSDRF). That is, we consider the problem of learning the conditional average dose response (CADR) function solely from historical data in which observed factors (confounders) affect both observed treatment and time-to-event outcomes. The estimated treatment effect from DeepSDRF enables us to develop recommender algorithms with the correction for selection bias. We compared two recommender approaches based on random search and reinforcement learning and found similar performance in terms of patient outcome. We tested the DeepSDRF and the corresponding recommender on extensive simulation studies and the eICU Research Institute (eRI) database. To the best of our knowledge, this is the first time that causal models are used to address the continuous treatment effect with observational data in a medical context.