Improving counterfactual reasoning with kernelised dynamic mixing models

Parbhoo, Sonali and Gottesman, Omer and Ross, Andrew Slavin and Komorowski, Matthieu and Faisal, Aldo and Bon, Isabella and Roth, Volker and Doshi-Velez, Finale. (2018) Improving counterfactual reasoning with kernelised dynamic mixing models. PloS one, 13 (11). e0205839.

[img] PDF - Published Version
Available under License CC BY (Attribution).


Official URL: https://edoc.unibas.ch/69172/

Downloads: Statistics Overview


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.
Faculties and Departments:05 Faculty of Science > Departement Mathematik und Informatik > Informatik > Biomedical Data Analysis (Roth)
UniBasel Contributors:Roth, Volker and Parbhoo, Sonali
Item Type:Article, refereed
Article Subtype:Research Article
Publisher:Public Library of Science
Note:Publication type according to Uni Basel Research Database: Journal article
Identification Number:
edoc DOI:
Last Modified:05 Mar 2019 15:09
Deposited On:05 Mar 2019 15:09

Repository Staff Only: item control page