Unknown

Dataset Information

0

Improving counterfactual reasoning with kernelised dynamic mixing models.


ABSTRACT: Simulation-based approaches to disease progression allow us to make counterfactual predictions about the effects of an untried series of treatment choices. However, building accurate simulators of disease progression is challenging, limiting the utility of these approaches for real world treatment planning. In this work, we present a novel simulation-based reinforcement learning approach that mixes between models and kernel-based approaches to make its forward predictions. On two real world tasks, managing sepsis and treating HIV, we demonstrate that our approach both learns state-of-the-art treatment policies and can make accurate forward predictions about the effects of treatments on unseen patients.

SUBMITTER: Parbhoo S 

PROVIDER: S-EPMC6231902 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

altmetric image

Publications

Improving counterfactual reasoning with kernelised dynamic mixing models.

Parbhoo Sonali S   Gottesman Omer O   Ross Andrew Slavin AS   Komorowski Matthieu M   Faisal Aldo A   Bon Isabella I   Roth Volker V   Doshi-Velez Finale F  

PloS one 20181112 11


Simulation-based approaches to disease progression allow us to make counterfactual predictions about the effects of an untried series of treatment choices. However, building accurate simulators of disease progression is challenging, limiting the utility of these approaches for real world treatment planning. In this work, we present a novel simulation-based reinforcement learning approach that mixes between models and kernel-based approaches to make its forward predictions. On two real world task  ...[more]

Similar Datasets

| S-EPMC4734710 | biostudies-literature
| S-EPMC6127036 | biostudies-literature
| S-EPMC5460856 | biostudies-literature
| S-EPMC9805594 | biostudies-literature
| S-EPMC2424052 | biostudies-literature
| S-EPMC5152910 | biostudies-literature
| S-EPMC2972923 | biostudies-other
| S-EPMC4211462 | biostudies-literature
| S-EPMC6015753 | biostudies-literature
| S-EPMC5798352 | biostudies-literature