Robust outcome weighted learning for optimal individualized treatment rules

Personalized medicine has received increasing attentions among scientific communities in recent years. Because patients often have heterogenous responses to treatments, discovering individualized treatment rules (ITR) is an important component of precision medicine. To that end, one needs to develop...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	Journal of biopharmaceutical statistics Ročník 29; číslo 4; s. 606 - 624
Hlavní autori:	Fu, Sheng, He, Qinying, Zhang, Sanguo, Liu, Yufeng
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	England Taylor & Francis 04.07.2019 Taylor & Francis Ltd
Predmet:	Angle-based classifiers multiple treatments non-convex optimization Precision medicine robustness soft and hard classification robustness non-convex optimization precision medicine multiple treatments Angle-based classifiers soft and hard classification
ISSN:	1054-3406, 1520-5711, 1520-5711
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	Personalized medicine has received increasing attentions among scientific communities in recent years. Because patients often have heterogenous responses to treatments, discovering individualized treatment rules (ITR) is an important component of precision medicine. To that end, one needs to develop a proper decision rule using patient-specific characteristics to maximize the expected clinical outcome, i.e. the optimal ITR. Recently, outcome weighted learning (OWL) has been proposed to estimate optimal ITR under a weighted classification framework. Since most of commonly used loss functions are unbounded, the resulting ITR may suffer similar effects of outliers as the corresponding classifiers. In this paper, we propose robust OWL (ROWL) to build more stable ITRs using a new family of bounded and non-convex loss functions. Moreover, we extend the proposed ROWL method to the multiple treatment setting under the angle-based classification structure. Our theoretical results show that ROWL is Fisher consistent, and can provide the estimation of rewards' ratios for the resulting ITRs. We develop an efficient difference of convex functions algorithm (DCA) to solve the corresponding nonconvex optimization problem. Through analysis of simulated examples and a real medical dataset, we demonstrate that the proposed ROWL method yields more competitive performance in terms of the empirical value function and the misclassification error than several existing methods.
AbstractList	Personalized medicine has received increasing attentions among scientific communities in recent years. Because patients often have heterogenous responses to treatments, discovering individualized treatment rules (ITR) is an important component of precision medicine. To that end, one needs to develop a proper decision rule using patient-specific characteristics to maximize the expected clinical outcome, i.e. the optimal ITR. Recently, outcome weighted learning (OWL) has been proposed to estimate optimal ITR under a weighted classification framework. Since most of commonly used loss functions are unbounded, the resulting ITR may suffer similar effects of outliers as the corresponding classifiers. In this paper, we propose robust OWL (ROWL) to build more stable ITRs using a new family of bounded and non-convex loss functions. Moreover, we extend the proposed ROWL method to the multiple treatment setting under the angle-based classification structure. Our theoretical results show that ROWL is Fisher consistent, and can provide the estimation of rewards' ratios for the resulting ITRs. We develop an efficient difference of convex functions algorithm (DCA) to solve the corresponding nonconvex optimization problem. Through analysis of simulated examples and a real medical dataset, we demonstrate that the proposed ROWL method yields more competitive performance in terms of the empirical value function and the misclassification error than several existing methods. Personalized medicine has received increasing attentions among scientific communities in recent years. Because patients often have heterogenous responses to treatments, discovering individualized treatment rules (ITR) is an important component of precision medicine. To that end, one needs to develop a proper decision rule using patient-specific characteristics to maximize the expected clinical outcome, i.e. the optimal ITR. Recently, outcome weighted learning (OWL) has been proposed to estimate optimal ITR under a weighted classification framework. Since most of commonly used loss functions are unbounded, the resulting ITR may suffer similar effects of outliers as the corresponding classifiers. In this paper, we propose robust OWL (ROWL) to build more stable ITRs using a new family of bounded and non-convex loss functions. Moreover, we extend the proposed ROWL method to the multiple treatment setting under the angle-based classification structure. Our theoretical results show that ROWL is Fisher consistent, and can provide the estimation of rewards' ratios for the resulting ITRs. We develop an efficient difference of convex functions algorithm (DCA) to solve the corresponding nonconvex optimization problem. Through analysis of simulated examples and a real medical dataset, we demonstrate that the proposed ROWL method yields more competitive performance in terms of the empirical value function and the misclassification error than several existing methods.Personalized medicine has received increasing attentions among scientific communities in recent years. Because patients often have heterogenous responses to treatments, discovering individualized treatment rules (ITR) is an important component of precision medicine. To that end, one needs to develop a proper decision rule using patient-specific characteristics to maximize the expected clinical outcome, i.e. the optimal ITR. Recently, outcome weighted learning (OWL) has been proposed to estimate optimal ITR under a weighted classification framework. Since most of commonly used loss functions are unbounded, the resulting ITR may suffer similar effects of outliers as the corresponding classifiers. In this paper, we propose robust OWL (ROWL) to build more stable ITRs using a new family of bounded and non-convex loss functions. Moreover, we extend the proposed ROWL method to the multiple treatment setting under the angle-based classification structure. Our theoretical results show that ROWL is Fisher consistent, and can provide the estimation of rewards' ratios for the resulting ITRs. We develop an efficient difference of convex functions algorithm (DCA) to solve the corresponding nonconvex optimization problem. Through analysis of simulated examples and a real medical dataset, we demonstrate that the proposed ROWL method yields more competitive performance in terms of the empirical value function and the misclassification error than several existing methods.
Author	Fu, Sheng Zhang, Sanguo Liu, Yufeng He, Qinying
Author_xml	– sequence: 1 givenname: Sheng surname: Fu fullname: Fu, Sheng organization: Department of Industrial and Systems Engineering, National University of Singapore – sequence: 2 givenname: Qinying surname: He fullname: He, Qinying organization: College of Economics and Management, South China Agricultural University – sequence: 3 givenname: Sanguo surname: Zhang fullname: Zhang, Sanguo organization: Key Laboratory of Big Data Mining and Knowledge Management, Chinese Academy of Sciences – sequence: 4 givenname: Yufeng orcidid: 0000-0002-1686-0545 surname: Liu fullname: Liu, Yufeng email: yfliu@email.unc.edu organization: Department of Statistics and Operations Research, Department of Genetics, Department of Biostatistics, Carolina Center for Genome Sciences, Lineberger Comprehensive Cancer Center, University of North Carolina
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/31309858$$D View this record in MEDLINE/PubMed
BookMark	eNqFkU1v1DAQhi1URNuFnwCKxIVLFk9ix7a4gCq-RCUkBGfLcSbFlWMvtkNVfj1e7e6lBzh5Ds8745nnkpyFGJCQ50C3QCV9DZSzntFh21FQWxj6fuDiEbkA3tGWC4CzWlem3UPn5DLnW0qBC8mekPMeeqoklxfky7c4rrk0cS02Ltjcobv5WXBqPJoUXLhp5piauCtuMb5xYXK_3bQa7_5UpiQ0ZcFQmrR6zE_J49n4jM-O74b8-PD--9Wn9vrrx89X765byxiUFjmlapgtgBpQyVGgHQVTg8AJ7DhYoCioMXMP3CpmOZNKWWlh5pMCLkW_Ia8OfXcp_loxF724bNF7EzCuWXfdnuo6kBV9-QC9jWsK9Xe6p1Iw2Yt6xg15caTWccFJ71LdNt3r05kq8OYA2BRzTjhr64opLoaSjPMaqN5L0Scpei9FH6XUNH-QPg34X-7tIedClbCYu5j8pIu59zHNyQTr6hb_bvEXbi6h-A
CitedBy_id	crossref_primary_10_1109_TIT_2022_3222266 crossref_primary_10_1080_01621459_2020_1862671
Cites_doi	10.1093/biomet/asm077 10.1002/sim.8102 10.1198/016214507000000617 10.1093/biomet/asu017 10.1198/016214505000000907 10.1016/j.jmva.2018.03.004 10.1111/j.1541-0420.2012.01763.x 10.1198/016214504000000098 10.1080/01621459.2012.695674 10.1016/0022-247X(71)90184-3 10.1093/biomet/asv028 10.1198/106186005X37238 10.1080/01621459.2014.951443 10.1198/jcgs.2010.09206 10.1208/ps020104 10.1214/10-AOS864 10.2174/138920210791110951 10.1111/biom.12865 10.1023/A:1008288411710 10.1080/01621459.2015.1093947 10.1073/pnas.97.1.262 10.1090/S0025-5718-1980-0572855-7 10.1023/A:1015469627679 10.1111/rssb.12216 10.1080/10618600.2012.680866 10.1007/s10107-017-1209-5 10.1137/1.9781611970128 10.1017/CBO9780511804441 10.1198/jasa.2011.tm10319
ContentType	Journal Article
Copyright	2019 Taylor & Francis Group, LLC 2019 2019 Taylor & Francis Group, LLC
Copyright_xml	– notice: 2019 Taylor & Francis Group, LLC 2019 – notice: 2019 Taylor & Francis Group, LLC
DBID	AAYXX CITATION NPM 7X8
DOI	10.1080/10543406.2019.1633657
DatabaseName	CrossRef PubMed MEDLINE - Academic
DatabaseTitle	CrossRef PubMed MEDLINE - Academic
DatabaseTitleList	PubMed MEDLINE - Academic
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Statistics Pharmacy, Therapeutics, & Pharmacology
EISSN	1520-5711
EndPage	624
ExternalDocumentID	31309858 10_1080_10543406_2019_1633657 1633657
Genre	Article Research Support, Non-U.S. Gov't Journal Article Research Support, N.I.H., Extramural
GrantInformation_xml	– fundername: Division of Mathematical Sciences grantid: 1821231 funderid: 10.13039/100000121 – fundername: National Institute of General Medical Sciences grantid: 126550 funderid: 10.13039/100000057 – fundername: Division of Information and Intelligent Systems grantid: 1632951 funderid: 10.13039/100000145 – fundername: National Cancer Institute grantid: 142538 funderid: 10.13039/100000054 – fundername: NCI NIH HHS grantid: P01 CA142538 – fundername: NIGMS NIH HHS grantid: R01 GM126550
GroupedDBID	--- .7F .QJ 0BK 0R~ 29K 30N 36B 4.4 53G 5GY 5VS 8VB AAENE AAGDL AAHIA AAJMT AALDU AAMIU AAPUL AAQRR ABCCY ABDBF ABFIM ABHAV ABJNI ABLIJ ABPAQ ABPEM ABTAI ABXUL ABXYU ACGEJ ACGFS ACTIO ACUHS ADCVX ADGTB ADXPE AEISY AEMOZ AENEX AEOZL AEPSL AEYOC AFKVX AFRVT AGDLA AGMYJ AHDZW AHQJS AIJEM AIYEW AJWEG AKBVH AKOOK AKVCP ALMA_UNASSIGNED_HOLDINGS ALQZU AQRUH AQTUD AVBZW AWYRJ BLEHA CCCUG CE4 CS3 D-I DGEBU DKSSO DU5 EAP EBC EBD EBR EBS EBU EHE EJD EMB EMK EMOBN EPL EST ESX E~A E~B F5P GTTXZ H13 HF~ HZ~ H~P IPNFZ J.P K1G KYCEM LJTGL M4Z MK0 ML~ NA5 NY~ O9- P2P PQQKQ QWB RIG RNANH ROSJB RTWRZ S-T SNACF SV3 TASJS TBQAZ TDBHL TEJ TFL TFT TFW TH9 TTHFI TUROJ TUS TWF UT5 UU3 ZGOLN ZL0 ~S~ AAYXX CITATION 07G 1TA AAIKQ AAKBW ACAGQ ACGEE ADYSH AEUMN AGCQS AGLEN AGROQ AHMOU ALCKM AMEWO AMXXU BCCOT BPLKW C06 CAG COF CRFIH DMQIW DWIFK IVXBP NPM NUSFT QCRFL TAQ TFMCV TOXWX UB9 UU8 V3K V4Q 7X8
ID	FETCH-LOGICAL-c441t-e50096fc1196e98b7ecb74967ed1cb6c10e70aaf315c94c54899c8c1f5d915873
IEDL.DBID	TFW
ISICitedReferencesCount	4
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000477961800004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1054-3406 1520-5711
IngestDate	Fri Sep 05 06:06:19 EDT 2025 Sat Jul 26 02:06:30 EDT 2025 Mon Jul 21 06:03:08 EDT 2025 Sat Nov 29 02:13:01 EST 2025 Tue Nov 18 22:22:50 EST 2025 Mon Oct 20 23:48:56 EDT 2025
IsDoiOpenAccess	false
IsOpenAccess	true
IsPeerReviewed	true
IsScholarly	true
Issue	4
Keywords	robustness non-convex optimization precision medicine multiple treatments Angle-based classifiers soft and hard classification
Language	English
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c441t-e50096fc1196e98b7ecb74967ed1cb6c10e70aaf315c94c54899c8c1f5d915873
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-1686-0545
OpenAccessLink	https://figshare.com/articles/Robust_outcome_weighted_learning_for_optimal_individualized_treatment_rules/8904743
PMID	31309858
PQID	3087483754
PQPubID	196226
PageCount	19
ParticipantIDs	crossref_citationtrail_10_1080_10543406_2019_1633657 proquest_miscellaneous_2258732218 informaworld_taylorfrancis_310_1080_10543406_2019_1633657 crossref_primary_10_1080_10543406_2019_1633657 proquest_journals_3087483754 pubmed_primary_31309858
PublicationCentury	2000
PublicationDate	2019-07-04
PublicationDateYYYYMMDD	2019-07-04
PublicationDate_xml	– month: 07 year: 2019 text: 2019-07-04 day: 04
PublicationDecade	2010
PublicationPlace	England
PublicationPlace_xml	– name: England – name: Philadelphia
PublicationTitle	Journal of biopharmaceutical statistics
PublicationTitleAlternate	J Biopharm Stat
PublicationYear	2019
Publisher	Taylor & Francis Taylor & Francis Ltd
Publisher_xml	– name: Taylor & Francis – name: Taylor & Francis Ltd
References	CIT0010 CIT0032 CIT0031 CIT0012 CIT0034 CIT0011 CIT0033 CIT0014 CIT0016 CIT0015 CIT0018 CIT0017 CIT0019 Nocedal J. (CIT0020) 2006 CIT0021 CIT0001 CIT0023 CIT0022 CIT0003 CIT0025 CIT0002 CIT0024 CIT0005 Liu Y. (CIT0013) 2007 CIT0027 Zhang C. (CIT0030) 2013; 14 CIT0004 CIT0026 CIT0007 CIT0029 CIT0006 CIT0028 CIT0009 CIT0008
References_xml	– ident: CIT0015 – ident: CIT0024 doi: 10.1093/biomet/asm077 – ident: CIT0027 doi: 10.1002/sim.8102 – volume-title: Sequential quadratic programming year: 2006 ident: CIT0020 – ident: CIT0025 doi: 10.1198/016214507000000617 – ident: CIT0031 doi: 10.1093/biomet/asu017 – ident: CIT0002 doi: 10.1198/016214505000000907 – ident: CIT0008 doi: 10.1016/j.jmva.2018.03.004 – ident: CIT0028 doi: 10.1111/j.1541-0420.2012.01763.x – ident: CIT0029 – ident: CIT0011 doi: 10.1198/016214504000000098 – start-page: 291 volume-title: Artificial intelligence and statistics year: 2007 ident: CIT0013 – ident: CIT0033 doi: 10.1080/01621459.2012.695674 – ident: CIT0009 doi: 10.1016/0022-247X(71)90184-3 – ident: CIT0010 doi: 10.1093/biomet/asv028 – ident: CIT0014 doi: 10.1198/106186005X37238 – ident: CIT0022 doi: 10.1080/01621459.2014.951443 – ident: CIT0016 doi: 10.1198/jcgs.2010.09206 – ident: CIT0018 doi: 10.1208/ps020104 – ident: CIT0021 doi: 10.1214/10-AOS864 – ident: CIT0006 doi: 10.2174/138920210791110951 – ident: CIT0005 doi: 10.1111/biom.12865 – ident: CIT0001 doi: 10.1023/A:1008288411710 – ident: CIT0034 doi: 10.1080/01621459.2015.1093947 – ident: CIT0004 doi: 10.1073/pnas.97.1.262 – volume: 14 start-page: 1349 issue: 1 year: 2013 ident: CIT0030 publication-title: Journal of Machine Learning Research – ident: CIT0019 doi: 10.1090/S0025-5718-1980-0572855-7 – ident: CIT0012 doi: 10.1023/A:1015469627679 – ident: CIT0007 doi: 10.1111/rssb.12216 – ident: CIT0026 doi: 10.1080/10618600.2012.680866 – ident: CIT0032 doi: 10.1007/s10107-017-1209-5 – ident: CIT0023 doi: 10.1137/1.9781611970128 – ident: CIT0003 doi: 10.1017/CBO9780511804441 – ident: CIT0017 doi: 10.1198/jasa.2011.tm10319
SSID	ssj0015784
Score	2.2014532
Snippet	Personalized medicine has received increasing attentions among scientific communities in recent years. Because patients often have heterogenous responses to...
SourceID	proquest pubmed crossref informaworld
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	606
SubjectTerms	Angle-based classifiers multiple treatments non-convex optimization Precision medicine robustness soft and hard classification
Title	Robust outcome weighted learning for optimal individualized treatment rules
URI	https://www.tandfonline.com/doi/abs/10.1080/10543406.2019.1633657 https://www.ncbi.nlm.nih.gov/pubmed/31309858 https://www.proquest.com/docview/3087483754 https://www.proquest.com/docview/2258732218
Volume	29
WOSCitedRecordID	wos000477961800004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVAWR databaseName: Taylor & Francis Journals customDbUrl: eissn: 1520-5711 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0015784 issn: 1054-3406 databaseCode: TFW dateStart: 19910101 isFulltext: true titleUrlDefault: https://www.tandfonline.com providerName: Taylor & Francis
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV3BTtwwEB1RxIFLWyhtlwIyUsWJoHjtrO1jVXWFBEIrtBV7i5KJXSHRTbVJQPD1HSdOKAfEoZyiKJnEHo_tN_bMM8BXIRBx4p0cRE0OSqaizLg80g4TU1glxtiy65-riwu9WJhZiCasQlil96FdRxTRjtW-c2d51UfE0dXnQ8Y-wICbEwIUYpL4fHJC9j6obz69GvYRyB7bfWWSiLxIn8Pz3FeezE5PuEufR6DtTDR99wp1eA9vAwxl3zq72YI1u9yGo1nHY31_zOaPaVnVMTtis0eG6_tt2PQQtWN4_gBnl2XeVDUrm5qKYNldu9hqCxYOpPjFqHqspKHpN_3xekgAu36gd4Y4d7Zqbmy1Az-nP-bfT6NwREOEhKPqyCbeB3LIqSNbo3NlMVfSTJQtOOYT5LFVcZY5wRM0Esk9MgY1cpcUhidaiY-wviyX9jMwVEWciwIJsDmpYp4VSOhHSpR6LN1YjkD2TZNi4C_3x2jcpDzQnPY6Tb1O06DTEZwMYn86Ao-XBMy_7Z7W7cqJ6445ScULsnu9kaRhLCCRWCvP259QFQ6Hx9SL_dZMtrRlU6U0qpIyxoS3RvCpM66htIJghtGJ3v2Pgn2BTX_bxhnLPVivV43dhw28JWNZHcAbtdAHbc_5C7lOEeM
linkProvider	Taylor & Francis
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1LT9wwEB5RqFQu5dGWbgvUlSpOBMVrZ20fK9QViO0Koa3KzUomdoUEm2o3aUV_fcd5AQfEoT3l4Ezix9j-xp75BuCTEIg4CkYOoiYDJVVRanwWaY-JyZ0SQ6zZ9SdqOtWXl-Z-LExwqww2tG-IIuq1OkzucBjducTRMwRExsHDgJsjQhRilKhnsBay0wUDbDb-3t8kkEbWN8skEgWZLornsc882J8esJc-jkHrvWi88T9asQkvWyTKPjeqswUrbr4NB-cNlfXtIZvdRWYtD9kBO78jub7dhvWAUhuS51dwdlFk1bJkRVVSHRz7XZ-3upy1OSl-MGofK2h1uqE_XvUxYFd_6J3e1Z0tqmu3fA3fxl9mxydRm6UhQoJSZeSSYAZ55DSXndGZcpgpaUbK5RyzEfLYqThNveAJGolkIRmDGrlPcsMTrcQbWJ0Xc_cWGKo8zkSOhNm8VDFPcyQAJCVKPZR-KAcgu7Gx2FKYh0wa15a3TKddn9rQp7bt0wEc9WI_Gw6PpwTM_YG3ZX144ptMJ1Y8IbvbaYltlwMSibUK1P0JNeFjX0wTOdzOpHNXVEtLCyt1xpAg1wB2Gu3qaysIaRid6Hf_ULEP8OJk9nViJ6fTs_ewHopqt2O5C6vlonJ78Bx_keIs9usJ9BeDbhUe
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lb9QwEB5BQagXHuW1UMBIqKemijf22j4iYAVqtVqhRfRmJRO7qlQ21SYBlV_POHFSeqh6gFMOziR-zNjf2ONvAN5lGSLOgpODqMlByVWSG18k2qM0pVPZFDt2_SO1WOjjY7OM0YR1DKsMPrTviSK6uToY93nph4g4eob7kGkIMODmgABFNpPqNtwh6CyDYq_m38eDBFLI7mCZRJIgM1ziue4zV5anK-Sl10PQbimaP_gPjXgI9yMOZe97xXkEt9x6B_aWPZH1xT5bXd7LqvfZHlteUlxf7MB2wKg9xfNjOPxaFW3dsKptqAqO_ep2W13JYkaKE0bNYxXNTT_oj6fjDbDT3_TOGOjONu2Zq5_At_mn1YfPSczRkCABqSZxMjhBHjlZsjO6UA4LJcxMuZJjMUOeOpXmuc-4RCOQ_CNjUCP3sjRcapU9ha11tXbPgaEq0yIrkRCbFyrleYkEf4RAoafCT8UExDA0FiOBecijcWZ55Dkd-tSGPrWxTydwMIqd9wweNwmYv8fdNt3Wie_znNjsBtndQUlsnAxIJNUqEPdLasLbsZjMOJzN5GtXtbWlaZU6Y0qAawLPeuUaa5sRzjBa6hf_ULE3cG_5cW6PviwOX8J2KOlijsUubDWb1r2Cu_iT9GbzujOfPyVVE9A
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Robust+outcome+weighted+learning+for+optimal+individualized+treatment+rules&rft.jtitle=Journal+of+biopharmaceutical+statistics&rft.au=Fu%2C+Sheng&rft.au=He%2C+Qinying&rft.au=Zhang%2C+Sanguo&rft.au=Liu%2C+Yufeng&rft.date=2019-07-04&rft.pub=Taylor+%26+Francis&rft.issn=1054-3406&rft.eissn=1520-5711&rft.volume=29&rft.issue=4&rft.spage=606&rft.epage=624&rft_id=info:doi/10.1080%2F10543406.2019.1633657&rft.externalDocID=1633657
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1054-3406&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1054-3406&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1054-3406&client=summon