Pitfalls in using ML to predict cognitive function performance

TL;DR

This paper warns that machine learning models predicting cognitive performance can be misleading if confounding variables are not properly controlled.

Contribution

The study demonstrates how confound leakage can inflate prediction accuracy in ML models for cognitive function.

Findings

A model predicting executive function using prosodic features showed reasonable fit.

Confounding variables like age and education were strongly related to the target, causing inflated accuracy.

The results emphasize the need for careful control of confounding variables in ML pipelines.

Abstract

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 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 model fit 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.