Afficher la notice abrégée

Do machine learning methods lead to similar individualized treatment rules? A comparison study on real data

dc.rights.licenseopenen_US
hal.structure.identifierCentre for Research in Epidemiology and Statistics | Centre de Recherche Épidémiologie et Statistiques [CRESS (U1153 / UMR_A 1125)]
hal.structure.identifierMethods of therapeutic evaluation of chronic diseases | Méthodes de l’évaluation thérapeutique des maladies chroniques [METHODS [CRESS - U1153 / UMR_A 1125]]
dc.contributor.authorBOUVIER, Florie
hal.structure.identifierCentre for Research in Epidemiology and Statistics | Centre de Recherche Épidémiologie et Statistiques [CRESS (U1153 / UMR_A 1125)]
hal.structure.identifierMethods of therapeutic evaluation of chronic diseases | Méthodes de l’évaluation thérapeutique des maladies chroniques [METHODS [CRESS - U1153 / UMR_A 1125]]
dc.contributor.authorPEYROT, Etienne
hal.structure.identifierCentre for Research in Epidemiology and Statistics | Centre de Recherche Épidémiologie et Statistiques [CRESS (U1153 / UMR_A 1125)]
hal.structure.identifierMethods of therapeutic evaluation of chronic diseases | Méthodes de l’évaluation thérapeutique des maladies chroniques [METHODS [CRESS - U1153 / UMR_A 1125]]
dc.contributor.authorBALENDRAN, Alan
hal.structure.identifierBordeaux population health [BPH]
dc.contributor.authorSÉGALAS, Corentin
hal.structure.identifierLondon School of Hygiene and Tropical Medicine [LSHTM]
dc.contributor.authorROBERTS, Ian
hal.structure.identifierCentre for Research in Epidemiology and Statistics | Centre de Recherche Épidémiologie et Statistiques [CRESS (U1153 / UMR_A 1125)]
hal.structure.identifierMethods of therapeutic evaluation of chronic diseases | Méthodes de l’évaluation thérapeutique des maladies chroniques [METHODS [CRESS - U1153 / UMR_A 1125]]
dc.contributor.authorPETIT, François
hal.structure.identifierCentre for Research in Epidemiology and Statistics | Centre de Recherche Épidémiologie et Statistiques [CRESS (U1153 / UMR_A 1125)]
hal.structure.identifierMethods of therapeutic evaluation of chronic diseases | Méthodes de l’évaluation thérapeutique des maladies chroniques [METHODS [CRESS - U1153 / UMR_A 1125]]
hal.structure.identifierCentre d'épidémiologie Clinique [Hôtel-Dieu]
dc.contributor.authorPORCHER, Raphaël
dc.date.accessioned2024-10-31T09:13:45Z
dc.date.available2024-10-31T09:13:45Z
dc.date.issued2024-05-20
dc.identifier.issn0277-6715en_US
dc.identifier.urihttps://oskar-bordeaux.fr/handle/20.500.12278/203074
dc.description.abstractEnIdentifying patients who benefit from a treatment is a key aspect of personalized medicine, which allows the development of individualized treatment rules (ITRs). Many machine learning methods have been proposed to create such rules. However, to what extent the methods lead to similar ITRs, that is, recommending the same treatment for the same individuals is unclear. In this work, we compared 22 of the most common approaches in two randomized control trials. Two classes of methods can be distinguished. The first class of methods relies on predicting individualized treatment effects from which an ITR is derived by recommending the treatment evaluated to the individuals with a predicted benefit. In the second class, methods directly estimate the ITR without estimating individualized treatment effects. For each trial, the performance of ITRs was assessed by various metrics, and the pairwise agreement between all ITRs was also calculated. Results showed that the ITRs obtained via the different methods generally had considerable disagreements regarding the patients to be treated. A better concordance was found among akin methods. Overall, when evaluating the performance of ITRs in a validation sample, all methods produced ITRs with limited performance, suggesting a high potential for optimism. For non‐parametric methods, this optimism was likely due to overfitting. The different methods do not lead to similar ITRs and are therefore not interchangeable. The choice of the method strongly influences for which patients a certain treatment is recommended, drawing some concerns about their practical use.
dc.description.sponsorshipPaRis Artificial Intelligence Research InstitutE - ANR-19-P3IA-0001en_US
dc.language.isoENen_US
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 United States*
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/us/*
dc.subject.encomparison study
dc.subject.enindividualized treatment rule
dc.subject.enmachine learning
dc.subject.enpersonalized medicine
dc.title.enDo machine learning methods lead to similar individualized treatment rules? A comparison study on real data
dc.title.alternativeStat Meden_US
dc.typeArticle de revueen_US
dc.identifier.doi10.1002/sim.10059en_US
dc.subject.halStatistiques [stat]/Autres [stat.ML]en_US
dc.subject.halStatistiques [stat]/Applications [stat.AP]en_US
dc.subject.halSciences du Vivant [q-bio]/Santé publique et épidémiologieen_US
dc.identifier.pubmed38472745en_US
bordeaux.journalStatistics in Medicineen_US
bordeaux.page2043-2061en_US
bordeaux.volume43en_US
bordeaux.hal.laboratoriesBordeaux Population Health Research Center (BPH) - UMR 1219en_US
bordeaux.issue11en_US
bordeaux.institutionUniversité de Bordeauxen_US
bordeaux.institutionINSERMen_US
bordeaux.teamBIOSTAT_BPHen_US
bordeaux.peerReviewedouien_US
bordeaux.inpressnonen_US
bordeaux.import.sourcehal
hal.identifierhal-04503566
hal.version1
hal.popularnonen_US
hal.audienceInternationaleen_US
hal.exportfalse
workflow.import.sourcehal
dc.rights.ccPas de Licence CCen_US
bordeaux.COinSctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=Statistics%20in%20Medicine&rft.date=2024-05-20&rft.volume=43&rft.issue=11&rft.spage=2043-2061&rft.epage=2043-2061&rft.eissn=0277-6715&rft.issn=0277-6715&rft.au=BOUVIER,%20Florie&PEYROT,%20Etienne&BALENDRAN,%20Alan&S%C3%89GALAS,%20Corentin&ROBERTS,%20Ian&rft.genre=article


Fichier(s) constituant ce document

Thumbnail
Nom:
BPH_SiM_2024_Bouvier.pdf
Taille:
3.333Mo
Format:
PDF
Voir/Ouvrir
Thumbnail
Nom:
license_rdf
Taille:
811octets
Format:
application/rdf+xml
Voir/Ouvrir

Ce document figure dans la(les) collection(s) suivante(s)

Afficher la notice abrégée