TY  - JOUR
AU  - Kuhles, Gianna
AU  - Hamdan, Sami
AU  - Heim, Stefan
AU  - Eickhoff, Simon B.
AU  - Patil, Kaustubh R.
AU  - Camilleri, Julia A.
AU  - Weis, Susanne
TI  - Pitfalls in using ML to predict cognitive function performance
JO  - Scientific reports
VL  - 15
IS  - 1
SN  - 2045-2322
CY  - [London]
PB  - Springer Nature
M1  - FZJ-2025-04364
SP  - 37747
PY  - 2025
N1  - 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).
AB  - 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.
LB  - PUB:(DE-HGF)16
DO  - DOI:10.1038/s41598-025-24325-9
UR  - https://juser.fz-juelich.de/record/1047524
ER  -