# Continuous Treatment Recommendation with Deep Survival Dose Response Function

arXiv: https://arxiv.org/abs/2108.10453 · HTML: https://mlsanity.com/paper/2108.10453/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 33 references that are in the map.
- First posted on arXiv 24 Aug 2021.

## Builds on (most cited first, 6 of 6)

- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems](https://mlsanity.com/paper/1603.04467/) (2016)
- [Recurrent Neural Networks for Multivariate Time Series with Missing Values](https://mlsanity.com/paper/1606.01865/) (2016)
- [Evaluating Reinforcement Learning Algorithms in Observational Health Settings](https://mlsanity.com/paper/1805.12298/) (2018)
- [Converting High-Dimensional Regression to High-Dimensional Conditional Density Estimation](https://mlsanity.com/paper/1704.08095/) (2017)
- [Targeted Estimation of Heterogeneous Treatment Effect in Observational Survival Analysis](https://mlsanity.com/paper/1910.08877/) (2019)

## Abstract (arXiv)

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.