001010405 001__ 1010405
001010405 005__ 20230905204623.0
001010405 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-03045
001010405 037__ $$aFZJ-2023-03045
001010405 041__ $$aEnglish
001010405 1001_ $$0P:(DE-Juel1)184874$$aHamdan, Sami$$b0$$eCorresponding author
001010405 1112_ $$aOrganization for Human Brain Mapping (OHBM)$$cMontreal$$d2023-07-22 - 2023-07-26$$wCanada
001010405 245__ $$aCofound-Leakage: Confound Removal In Machine Learning Leads To Leakage
001010405 260__ $$c2023
001010405 3367_ $$033$$2EndNote$$aConference Paper
001010405 3367_ $$2BibTeX$$aINPROCEEDINGS
001010405 3367_ $$2DRIVER$$aconferenceObject
001010405 3367_ $$2ORCID$$aCONFERENCE_POSTER
001010405 3367_ $$2DataCite$$aOutput Types/Conference Poster
001010405 3367_ $$0PUB:(DE-HGF)24$$2PUB:(DE-HGF)$$aPoster$$bposter$$mposter$$s1693893044_16257$$xAfter Call
001010405 500__ $$aAcknowledgments: This work was partly supported by the Helmholtz-AI project DeGen, the Helmholtz Portfolio Theme ‘Supercomputing and Modeling for the Human Brain’ and Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) Poster: Pitfalls of Confound Regression in Machine Learning. Der Postertitel lautet anders, doch das war ok fuer OHBM Veranstalter
001010405 520__ $$aModern Machine Learning (ML) approaches are now regularly employed forindividual-level prediction, e.g. personalized medicine.Particularly in such critical-decision making, it is of utmost importance to not onlyachieve high accuracy but also to trust that models rely on actual features-targetrelationships [1, 2]. To this end, it is crucial to consider confounding variables as theycan obstruct the features-target relationship. For instance, a researcher might wantto identify a biomarker showing high classification accuracy between controls andpatients. However, the model might have just learned simpler confounders like ageor sex as a good proxy of the disease [3]. To counteract such unwanted confoundingeffects, investigators often use linear models to remove confounding variables fromeach feature separately before employing ML. While this confound regression (CR)approach is popular [4], its pitfalls, especially when paired with non-linear MLmodels, are not well understood.
001010405 536__ $$0G:(DE-HGF)POF4-5254$$a5254 - Neuroscientific Data Analytics and AI (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001010405 536__ $$0G:(DE-Juel1)JL SMHB-2021-2027$$aJL SMHB - Joint Lab Supercomputing and Modeling for the Human Brain (JL SMHB-2021-2027)$$cJL SMHB-2021-2027$$x1
001010405 7001_ $$0P:(DE-HGF)0$$aLove, Bradley C.$$b1
001010405 7001_ $$0P:(DE-HGF)0$$aPolier, Georg von$$b2
001010405 7001_ $$0P:(DE-Juel1)172811$$aWeis, Susanne$$b3$$ufzj
001010405 7001_ $$0P:(DE-HGF)0$$aSchwender, Holger$$b4
001010405 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon$$b5$$ufzj
001010405 7001_ $$0P:(DE-Juel1)172843$$aPatil, Kaustubh$$b6$$ufzj
001010405 8564_ $$uhttps://juser.fz-juelich.de/record/1010405/files/SamiHamdanOHBM.pdf$$yOpenAccess
001010405 909CO $$ooai:juser.fz-juelich.de:1010405$$pdriver$$pVDB$$popen_access$$popenaire
001010405 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)184874$$aForschungszentrum Jülich$$b0$$kFZJ
001010405 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)184874$$a HHU Düsseldorf$$b0
001010405 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a University College London$$b1
001010405 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172811$$aForschungszentrum Jülich$$b3$$kFZJ
001010405 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)172811$$a HHU Düsseldorf$$b3
001010405 9101_ $$0I:(DE-HGF)0$$6P:(DE-HGF)0$$a HHU Düsseldorf$$b4
001010405 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b5$$kFZJ
001010405 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)131678$$a HHU Düsseldorf$$b5
001010405 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172843$$aForschungszentrum Jülich$$b6$$kFZJ
001010405 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)172843$$a HHU Düsseldorf$$b6
001010405 9131_ $$0G:(DE-HGF)POF4-525$$1G:(DE-HGF)POF4-520$$2G:(DE-HGF)POF4-500$$3G:(DE-HGF)POF4$$4G:(DE-HGF)POF$$9G:(DE-HGF)POF4-5254$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001010405 9141_ $$y2023
001010405 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001010405 920__ $$lyes
001010405 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001010405 980__ $$aposter
001010405 980__ $$aVDB
001010405 980__ $$aUNRESTRICTED
001010405 980__ $$aI:(DE-Juel1)INM-7-20090406
001010405 9801_ $$aFullTexts