001047524 001__ 1047524
001047524 005__ 20251107202105.0
001047524 0247_ $$2doi$$a10.1038/s41598-025-24325-9
001047524 0247_ $$2datacite_doi$$a10.34734/FZJ-2025-04364
001047524 037__ $$aFZJ-2025-04364
001047524 041__ $$aEnglish
001047524 082__ $$a600
001047524 1001_ $$0P:(DE-Juel1)187476$$aKuhles, Gianna$$b0$$eCorresponding author
001047524 245__ $$aPitfalls in using ML to predict cognitive function performance
001047524 260__ $$a[London]$$bSpringer Nature$$c2025
001047524 3367_ $$2DRIVER$$aarticle
001047524 3367_ $$2DataCite$$aOutput Types/Journal article
001047524 3367_ $$0PUB:(DE-HGF)16$$2PUB:(DE-HGF)$$aJournal Article$$bjournal$$mjournal$$s1762517970_3373
001047524 3367_ $$2BibTeX$$aARTICLE
001047524 3367_ $$2ORCID$$aJOURNAL_ARTICLE
001047524 3367_ $$00$$2EndNote$$aJournal Article
001047524 500__ $$aThis study was supported by the Deutsche Forschungsgemeinschaft (DFG, GE 2835/2–1, EI 816/16 − 1 and EI 816/21 − 1), the National Institute of Mental Health (R01-MH074457), the Helmholtz Portfolio Theme “Supercomputing and Modeling for the Human Brain”, the Virtual Brain Cloud (EU H2020, no. 826421) & the National Institute on Aging (R01AG067103).
001047524 520__ $$aMachine learning analyses are widely used for predicting cognitive abilities, yet there are pitfalls that need to be considered during their implementation and interpretation of the results. Hence, the present study aimed at drawing attention to the risks of erroneous conclusions incurred by confounding variables illustrated by a case example predicting executive function (EF) performance by prosodic features. Healthy participants (n = 231) performed speech tasks and EF tests. From 264 prosodic features, we predicted EF performance using 66 variables, controlling for confounding effects of age, sex, and education. A reasonable prediction performance was apparently achieved for EF variables of the Trail Making Test. However, in-depth analyses revealed indications of confound leakage, leading to inflated prediction accuracies, due to a strong relationship between confounds and targets. These findings highlight the need to control confounding variables in ML pipelines and caution against potential pitfalls in ML predictions.
001047524 536__ $$0G:(DE-HGF)POF4-5251$$a5251 - Multilevel Brain Organization and Variability (POF4-525)$$cPOF4-525$$fPOF IV$$x0
001047524 536__ $$0G:(DE-HGF)POF4-5252$$a5252 - Brain Dysfunction and Plasticity (POF4-525)$$cPOF4-525$$fPOF IV$$x1
001047524 588__ $$aDataset connected to CrossRef, Journals: juser.fz-juelich.de
001047524 65027 $$0V:(DE-MLZ)SciArea-190$$2V:(DE-HGF)$$aMedicine$$x0
001047524 65017 $$0V:(DE-MLZ)GC-120-2016$$2V:(DE-HGF)$$aInformation and Communication$$x0
001047524 7001_ $$0P:(DE-Juel1)184874$$aHamdan, Sami$$b1
001047524 7001_ $$0P:(DE-Juel1)131644$$aHeim, Stefan$$b2
001047524 7001_ $$0P:(DE-Juel1)131678$$aEickhoff, Simon B.$$b3
001047524 7001_ $$0P:(DE-Juel1)172843$$aPatil, Kaustubh R.$$b4
001047524 7001_ $$0P:(DE-Juel1)172024$$aCamilleri, Julia A.$$b5$$eLast author
001047524 7001_ $$0P:(DE-Juel1)172811$$aWeis, Susanne$$b6$$eLast author
001047524 773__ $$0PERI:(DE-600)2615211-3$$a10.1038/s41598-025-24325-9$$gVol. 15, no. 1, p. 37747$$n1$$p37747$$tScientific reports$$v15$$x2045-2322$$y2025
001047524 8564_ $$uhttps://www.nature.com/articles/s41598-025-24325-9?utm_source=rct_congratemailt&utm_medium=email&utm_campaign=oa_20251029&utm_content=10.1038/s41598-025-24325-9#Sec11
001047524 8564_ $$uhttps://juser.fz-juelich.de/record/1047524/files/Pitfalls%20in%20using%20ML%20to%20predict%20cognitive%20function%20performance.pdf$$yOpenAccess
001047524 909CO $$ooai:juser.fz-juelich.de:1047524$$popenaire$$popen_access$$pVDB$$pdriver$$pdnbdelivery
001047524 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)187476$$aForschungszentrum Jülich$$b0$$kFZJ
001047524 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131644$$aForschungszentrum Jülich$$b2$$kFZJ
001047524 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)131678$$aForschungszentrum Jülich$$b3$$kFZJ
001047524 9101_ $$0I:(DE-HGF)0$$6P:(DE-Juel1)131678$$a HHU Düsseldorf$$b3
001047524 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172843$$aForschungszentrum Jülich$$b4$$kFZJ
001047524 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172024$$aForschungszentrum Jülich$$b5$$kFZJ
001047524 9101_ $$0I:(DE-588b)5008462-8$$6P:(DE-Juel1)172811$$aForschungszentrum Jülich$$b6$$kFZJ
001047524 9131_ $$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
001047524 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)POF4-5252$$aDE-HGF$$bKey Technologies$$lNatural, Artificial and Cognitive Information Processing$$vDecoding Brain Organization and Dysfunction$$x1
001047524 9141_ $$y2025
001047524 915__ $$0StatID:(DE-HGF)0200$$2StatID$$aDBCoverage$$bSCOPUS$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0160$$2StatID$$aDBCoverage$$bEssential Science Indicators$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)1050$$2StatID$$aDBCoverage$$bBIOSIS Previews$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)1190$$2StatID$$aDBCoverage$$bBiological Abstracts$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0600$$2StatID$$aDBCoverage$$bEbsco Academic Search$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)1040$$2StatID$$aDBCoverage$$bZoological Record$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0100$$2StatID$$aJCR$$bSCI REP-UK : 2022$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0501$$2StatID$$aDBCoverage$$bDOAJ Seal$$d2024-07-29T15:28:26Z
001047524 915__ $$0StatID:(DE-HGF)0500$$2StatID$$aDBCoverage$$bDOAJ$$d2024-07-29T15:28:26Z
001047524 915__ $$0StatID:(DE-HGF)0113$$2StatID$$aWoS$$bScience Citation Index Expanded$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0700$$2StatID$$aFees$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0150$$2StatID$$aDBCoverage$$bWeb of Science Core Collection$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)9900$$2StatID$$aIF < 5$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0510$$2StatID$$aOpenAccess
001047524 915__ $$0StatID:(DE-HGF)0030$$2StatID$$aPeer Review$$bASC$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0561$$2StatID$$aArticle Processing Charges$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)1150$$2StatID$$aDBCoverage$$bCurrent Contents - Physical, Chemical and Earth Sciences$$d2024-12-18
001047524 915__ $$0StatID:(DE-HGF)0300$$2StatID$$aDBCoverage$$bMedline$$d2024-12-18
001047524 915__ $$0LIC:(DE-HGF)CCBY4$$2HGFVOC$$aCreative Commons Attribution CC BY 4.0
001047524 915__ $$0StatID:(DE-HGF)0199$$2StatID$$aDBCoverage$$bClarivate Analytics Master Journal List$$d2024-12-18
001047524 920__ $$lyes
001047524 9201_ $$0I:(DE-Juel1)INM-7-20090406$$kINM-7$$lGehirn & Verhalten$$x0
001047524 9201_ $$0I:(DE-Juel1)INM-1-20090406$$kINM-1$$lStrukturelle und funktionelle Organisation des Gehirns$$x1
001047524 980__ $$ajournal
001047524 980__ $$aVDB
001047524 980__ $$aUNRESTRICTED
001047524 980__ $$aI:(DE-Juel1)INM-7-20090406
001047524 980__ $$aI:(DE-Juel1)INM-1-20090406
001047524 9801_ $$aFullTexts