Home > Publications database > Pitfalls in using ML to predict cognitive function performance > print

001     1047524
005     20260223202244.0
024 7 _ |2 doi
|a 10.1038/s41598-025-24325-9
024 7 _ |2 datacite_doi
|a 10.34734/FZJ-2025-04364
024 7 _ |2 pmid
|a 41162556
024 7 _ |a WOS:001605877700001
|2 WOS
037 _ _ |a FZJ-2025-04364
041 _ _ |a English
082 _ _ |a 600
100 1 _ |0 P:(DE-Juel1)187476
|a Kuhles, Gianna
|b 0
|e Corresponding author
245 _ _ |a Pitfalls in using ML to predict cognitive function performance
260 _ _ |a [London]
|b Springer Nature
|c 2025
336 7 _ |2 DRIVER
|a article
336 7 _ |2 DataCite
|a Output Types/Journal article
336 7 _ |0 PUB:(DE-HGF)16
|2 PUB:(DE-HGF)
|a Journal Article
|b journal
|m journal
|s 1762517970_3373
336 7 _ |2 BibTeX
|a ARTICLE
336 7 _ |2 ORCID
|a JOURNAL_ARTICLE
336 7 _ |0 0
|2 EndNote
|a Journal Article
500 _ _ |a This 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).
520 _ _ |a Machine 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.
536 _ _ |0 G:(DE-HGF)POF4-5251
|a 5251 - Multilevel Brain Organization and Variability (POF4-525)
|c POF4-525
|f POF IV
|x 0
536 _ _ |0 G:(DE-HGF)POF4-5252
|a 5252 - Brain Dysfunction and Plasticity (POF4-525)
|c POF4-525
|f POF IV
|x 1
588 _ _ |a Dataset connected to CrossRef, Journals: juser.fz-juelich.de
650 2 7 |0 V:(DE-MLZ)SciArea-190
|2 V:(DE-HGF)
|a Medicine
|x 0
650 1 7 |0 V:(DE-MLZ)GC-120-2016
|2 V:(DE-HGF)
|a Information and Communication
|x 0
700 1 _ |0 P:(DE-Juel1)184874
|a Hamdan, Sami
|b 1
700 1 _ |0 P:(DE-Juel1)131644
|a Heim, Stefan
|b 2
700 1 _ |0 P:(DE-Juel1)131678
|a Eickhoff, Simon B.
|b 3
700 1 _ |0 P:(DE-Juel1)172843
|a Patil, Kaustubh R.
|b 4
700 1 _ |0 P:(DE-Juel1)172024
|a Camilleri, Julia A.
|b 5
|e Last author
700 1 _ |0 P:(DE-Juel1)172811
|a Weis, Susanne
|b 6
|e Last author
773 _ _ |0 PERI:(DE-600)2615211-3
|a 10.1038/s41598-025-24325-9
|g Vol. 15, no. 1, p. 37747
|n 1
|p 37747
|t Scientific reports
|v 15
|x 2045-2322
|y 2025
856 4 _ |u https://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
856 4 _ |u https://juser.fz-juelich.de/record/1047524/files/Pitfalls%20in%20using%20ML%20to%20predict%20cognitive%20function%20performance.pdf
|y OpenAccess
909 C O |o oai:juser.fz-juelich.de:1047524
|p openaire
|p open_access
|p OpenAPC
|p driver
|p VDB
|p openCost
|p dnbdelivery
910 1 _ |0 I:(DE-588b)5008462-8
|6 P:(DE-Juel1)187476
|a Forschungszentrum Jülich
|b 0
|k FZJ
910 1 _ |0 I:(DE-588b)5008462-8
|6 P:(DE-Juel1)131644
|a Forschungszentrum Jülich
|b 2
|k FZJ
910 1 _ |0 I:(DE-588b)5008462-8
|6 P:(DE-Juel1)131678
|a Forschungszentrum Jülich
|b 3
|k FZJ
910 1 _ |0 I:(DE-HGF)0
|6 P:(DE-Juel1)131678
|a HHU Düsseldorf
|b 3
910 1 _ |0 I:(DE-588b)5008462-8
|6 P:(DE-Juel1)172843
|a Forschungszentrum Jülich
|b 4
|k FZJ
910 1 _ |0 I:(DE-588b)5008462-8
|6 P:(DE-Juel1)172024
|a Forschungszentrum Jülich
|b 5
|k FZJ
910 1 _ |0 I:(DE-588b)5008462-8
|6 P:(DE-Juel1)172811
|a Forschungszentrum Jülich
|b 6
|k FZJ
913 1 _ |0 G:(DE-HGF)POF4-525
|1 G:(DE-HGF)POF4-520
|2 G:(DE-HGF)POF4-500
|3 G:(DE-HGF)POF4
|4 G:(DE-HGF)POF
|9 G:(DE-HGF)POF4-5251
|a DE-HGF
|b Key Technologies
|l Natural, Artificial and Cognitive Information Processing
|v Decoding Brain Organization and Dysfunction
|x 0
913 1 _ |0 G:(DE-HGF)POF4-525
|1 G:(DE-HGF)POF4-520
|2 G:(DE-HGF)POF4-500
|3 G:(DE-HGF)POF4
|4 G:(DE-HGF)POF
|9 G:(DE-HGF)POF4-5252
|a DE-HGF
|b Key Technologies
|l Natural, Artificial and Cognitive Information Processing
|v Decoding Brain Organization and Dysfunction
|x 1
914 1 _ |y 2025
915 _ _ |0 StatID:(DE-HGF)0160
|2 StatID
|a DBCoverage
|b Essential Science Indicators
|d 2024-12-18
915 _ _ |0 StatID:(DE-HGF)1190
|2 StatID
|a DBCoverage
|b Biological Abstracts
|d 2024-12-18
915 _ _ |0 StatID:(DE-HGF)0113
|2 StatID
|a WoS
|b Science Citation Index Expanded
|d 2024-12-18
915 _ _ |0 StatID:(DE-HGF)0700
|2 StatID
|a Fees
|d 2024-12-18
915 _ _ |0 StatID:(DE-HGF)0510
|2 StatID
|a OpenAccess
915 _ _ |0 StatID:(DE-HGF)0561
|2 StatID
|a Article Processing Charges
|d 2024-12-18
915 _ _ |0 LIC:(DE-HGF)CCBY4
|2 HGFVOC
|a Creative Commons Attribution CC BY 4.0
915 _ _ |0 StatID:(DE-HGF)0100
|2 StatID
|a JCR
|b SCI REP-UK : 2022
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)0200
|2 StatID
|a DBCoverage
|b SCOPUS
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)0300
|2 StatID
|a DBCoverage
|b Medline
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)0320
|2 StatID
|a DBCoverage
|b PubMed Central
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)0501
|2 StatID
|a DBCoverage
|b DOAJ Seal
|d 2025-08-21T14:09:21Z
915 _ _ |0 StatID:(DE-HGF)0500
|2 StatID
|a DBCoverage
|b DOAJ
|d 2025-08-21T14:09:21Z
915 _ _ |0 StatID:(DE-HGF)0030
|2 StatID
|a Peer Review
|b DOAJ : Anonymous peer review
|d 2025-08-21T14:09:21Z
915 _ _ |0 StatID:(DE-HGF)0600
|2 StatID
|a DBCoverage
|b Ebsco Academic Search
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)0030
|2 StatID
|a Peer Review
|b ASC
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)0199
|2 StatID
|a DBCoverage
|b Clarivate Analytics Master Journal List
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)1150
|2 StatID
|a DBCoverage
|b Current Contents - Physical, Chemical and Earth Sciences
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)1040
|2 StatID
|a DBCoverage
|b Zoological Record
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)0150
|2 StatID
|a DBCoverage
|b Web of Science Core Collection
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)1050
|2 StatID
|a DBCoverage
|b BIOSIS Previews
|d 2025-11-07
915 _ _ |0 StatID:(DE-HGF)9900
|2 StatID
|a IF < 5
|d 2025-11-07
915 p c |a APC keys set
|2 APC
|0 PC:(DE-HGF)0000
915 p c |a Local Funding
|2 APC
|0 PC:(DE-HGF)0001
915 p c |a DFG OA Publikationskosten
|2 APC
|0 PC:(DE-HGF)0002
915 p c |a DOAJ Journal
|2 APC
|0 PC:(DE-HGF)0003
915 p c |a DEAL: Springer Nature 2020
|2 APC
|0 PC:(DE-HGF)0113
920 _ _ |l yes
920 1 _ |0 I:(DE-Juel1)INM-7-20090406
|k INM-7
|l Gehirn & Verhalten
|x 0
920 1 _ |0 I:(DE-Juel1)INM-1-20090406
|k INM-1
|l Strukturelle und funktionelle Organisation des Gehirns
|x 1
980 1 _ |a FullTexts
980 _ _ |a journal
980 _ _ |a VDB
980 _ _ |a UNRESTRICTED
980 _ _ |a I:(DE-Juel1)INM-7-20090406
980 _ _ |a I:(DE-Juel1)INM-1-20090406
980 _ _ |a APC

LibraryCollectionCLSMajorCLSMinorLanguageAuthor
Marc 21