001019408 001__ 1019408
001019408 005__ 20231214201906.0
001019408 0247_ $$2doi$$a10.1101/2023.08.30.555495
001019408 0247_ $$2datacite_doi$$a10.34734/FZJ-2023-05368
001019408 037__ $$aFZJ-2023-05368
001019408 1001_ $$0P:(DE-Juel1)176497$$aWiersch, Lisa$$b0$$eCorresponding author
001019408 245__ $$aSex classification from functional brain connectivity: Generalization to multiple datasets
001019408 260__ $$c2023
001019408 3367_ $$0PUB:(DE-HGF)25$$2PUB:(DE-HGF)$$aPreprint$$bpreprint$$mpreprint$$s1702546914_9629
001019408 3367_ $$2ORCID$$aWORKING_PAPER
001019408 3367_ $$028$$2EndNote$$aElectronic Article
001019408 3367_ $$2DRIVER$$apreprint
001019408 3367_ $$2BibTeX$$aARTICLE
001019408 3367_ $$2DataCite$$aOutput Types/Working Paper
001019408 520__ $$aMachine learning (ML) approaches are increasingly being applied to neuroimaging data. Studies in neuroscience typically have to rely on a limited set of training data which may impair the generalizability of ML models. However, it is still unclear which kind of training sample is best suited to optimize generalization performance. In the present study, we systematically investigated the generalization performance of sex classification models trained on the parcelwise connectivity profile of either single samples or a compound sample containing data from four different datasets. Generalization performance was quantified in terms of mean across-sample classification accuracy and spatial consistency of accurately classifying parcels. Our results indicate that generalization performance of pwCs trained on single dataset samples is dependent on the specific test samples. Certain datasets seem to “match” in the sense that classifiers trained on a sample from one dataset achieved a high accuracy when tested on the respected other one and vice versa. The pwC trained on the compound sample demonstrated overall highest generalization performance for all test samples, including one derived from a dataset not included in building the training samples. Thus, our results indicate that a big and heterogenous training sample comprising data of multiple datasets is best suited to achieve generalizable results.
001019408 536__ $$0G:(DE-HGF)POF4-5251$$a5251 - Multilevel Brain Organization and Variability (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001019408 536__ $$0G:(GEPRIS)491111487$$aDFG project 491111487 - Open-Access-Publikationskosten / 2022 - 2024 / Forschungszentrum Jülich (OAPKFZJ) (491111487)$$c491111487$$x1
001019408 588__ $$aDataset connected to CrossRef
001019408 7001_ $$0P:(DE-Juel1)185938$$aFriedrich, Patrick$$b1
001019408 7001_ $$0P:(DE-Juel1)184874$$aHamdan, Sami$$b2
001019408 7001_ $$0P:(DE-Juel1)187351$$aKomeyer, Vera$$b3
001019408 7001_ $$0P:(DE-Juel1)131684$$aHoffstaedter, Felix$$b4
001019408 7001_ $$0P:(DE-Juel1)172843$$aPatil, Kaustubh$$b5
001019408 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon$$b6
001019408 7001_ $$0P:(DE-Juel1)172811$$aWeis, Susanne$$b7$$eCorresponding author
001019408 773__ $$a10.1101/2023.08.30.555495
001019408 8564_ $$uhttps://juser.fz-juelich.de/record/1019408/files/Preprint_PDF.pdf$$yOpenAccess
001019408 8564_ $$uhttps://juser.fz-juelich.de/record/1019408/files/Preprint_PDF.gif?subformat=icon$$xicon$$yOpenAccess
001019408 8564_ $$uhttps://juser.fz-juelich.de/record/1019408/files/Preprint_PDF.jpg?subformat=icon-1440$$xicon-1440$$yOpenAccess
001019408 8564_ $$uhttps://juser.fz-juelich.de/record/1019408/files/Preprint_PDF.jpg?subformat=icon-180$$xicon-180$$yOpenAccess
001019408 8564_ $$uhttps://juser.fz-juelich.de/record/1019408/files/Preprint_PDF.jpg?subformat=icon-640$$xicon-640$$yOpenAccess
001019408 909CO $$ooai:juser.fz-juelich.de:1019408$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001019408 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)176497$$aForschungszentrum Jülich$$b0$$kFZJ
001019408 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)185938$$aForschungszentrum Jülich$$b1$$kFZJ
001019408 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)184874$$aForschungszentrum Jülich$$b2$$kFZJ
001019408 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187351$$aForschungszentrum Jülich$$b3$$kFZJ
001019408 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131684$$aForschungszentrum Jülich$$b4$$kFZJ
001019408 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172843$$aForschungszentrum Jülich$$b5$$kFZJ
001019408 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b6$$kFZJ
001019408 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172811$$aForschungszentrum Jülich$$b7$$kFZJ
001019408 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)POF4-5251$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x0
001019408 9141_ $$y2023
001019408 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001019408 920__ $$lyes
001019408 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001019408 980__ $$apreprint
001019408 980__ $$aVDB
001019408 980__ $$aUNRESTRICTED
001019408 980__ $$aI:(DE-Juel1)INM-7-20090406
001019408 9801_ $$aFullTexts