Notice

This record has been edited as far as possible, missing data will be added when the version of record is issued.

Show simple item record

dc.contributor.author
Blümlein, Theresa
dc.contributor.author
Persson, Joel
dc.contributor.author
Feuerriegel, Stefan
dc.date.accessioned
2022-08-04T11:57:19Z
dc.date.available
2022-06-25T02:11:00Z
dc.date.available
2022-06-28T12:45:00Z
dc.date.available
2022-08-04T11:57:19Z
dc.date.issued
2022
dc.identifier.issn
2640-3498
dc.identifier.uri
http://hdl.handle.net/20.500.11850/554606
dc.description.abstract
Dynamic treatment regimes (DTRs) are used in medicine to tailor sequential treatment decisions to patients by considering patient heterogeneity. Common methods for learning optimal DTRs, however, have shortcomings: they are typically based on outcome prediction and not treatment effect estimation, or they use linear models that are restrictive for patient data from modern electronic health records. To address these shortcomings, we develop two novel methods for learning optimal DTRs that effectively handle complex patient data. We call our methods DTR causal trees (DTR-CT) and DTR causal forest (DTR-CF). Our methods are based on a data-driven estimation of heterogeneous treatment effects using causal tree methods, specifically causal trees and causal forests, that learn non-linear relationships, control for time-varying confounding, are doubly robust, and explainable. To the best of our knowledge, our paper is the first that adapts causal tree methods for learning optimal DTRs. We evaluate our proposed methods using synthetic data and then apply them to real-world data from intensive care units. Our methods outperform state- of-the-art baselines in terms of cumulative regret and percentage of optimal decisions by a considerable margin. Our work improves treatment recommendations from electronic health record and is thus of direct relevance for personalized medicine.
en_US
dc.language.iso
en
en_US
dc.title
Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine
en_US
dc.type
Conference Paper
ethz.book.title
Proceedings of Machine Learning for Healthcare 2022
en_US
ethz.journal.title
Proceedings of Machine Learning Research
ethz.journal.volume
182
en_US
ethz.size
25 p.
en_US
ethz.event
Machine Learning for Healthcare 2022 (MLHC 2022)
en_US
ethz.event.location
Durham, NC, USA
en_US
ethz.event.date
August 5-6, 2022
en_US
ethz.notes
Poster presentation ID 34.
en_US
ethz.grant
Data-driven health management
en_US
ethz.publication.status
accepted
en_US
ethz.leitzahl
ETH Zürich::00002 - ETH Zürich::00012 - Lehre und Forschung::00007 - Departemente::02120 - Dep. Management, Technologie und Ökon. / Dep. of Management, Technology, and Ec.::09623 - Feuerriegel, Stefan (ehemalig) / Feuerriegel, Stefan (former)
en_US
ethz.grant.agreementno
186932
ethz.grant.agreementno
186932
ethz.grant.fundername
SNF
ethz.grant.fundername
SNF
ethz.grant.funderDoi
10.13039/501100001711
ethz.grant.funderDoi
10.13039/501100001711
ethz.grant.program
Eccellenza
ethz.grant.program
Eccellenza
ethz.date.deposited
2022-06-25T02:11:30Z
ethz.source
FORM
ethz.eth
yes
en_US
ethz.availability
Metadata only
en_US
ethz.rosetta.exportRequired
true
ethz.COinS
ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.atitle=Learning%20Optimal%20Dynamic%20Treatment%20Regimes%20Using%20Causal%20Tree%20Methods%20in%20Medicine&rft.jtitle=Proceedings%20of%20Machine%20Learning%20Research&rft.date=2022&rft.volume=182&rft.issn=2640-3498&rft.au=Bl%C3%BCmlein,%20Theresa&Persson,%20Joel&Feuerriegel,%20Stefan&rft.genre=proceeding&rft.btitle=Proceedings%20of%20Machine%20Learning%20for%20Healthcare%202022
 Search print copy at ETH Library

Files in this item

FilesSizeFormatOpen in viewer

There are no files associated with this item.

Publication type

Show simple item record