Controlling for effects of confounding variables on machine learning predictions
Dinga, R.; Schmaal, L.; Penninx, B. W.; Veltman, D. J.; Marquand, A. F.
Show abstract
Machine learning predictive models are being used in neuroimaging to predict information about the task or stimuli or to identify potentially clinically useful biomarkers. However, the predictions can be driven by confounding variables unrelated to the signal of interest, such as scanner effect or head motion, limiting the clinical usefulness and interpretation of machine learning models. The most common method to control for confounding effects is regressing out the confounding variables separately from each input variable before machine learning modeling. However, we show that this method is insufficient because machine learning models can learn information from the data that cannot be regressed out. Instead of regressing out confounding effects from each input variable, we propose controlling for confounds post-hoc on the level of machine learning predictions. This allows partitioning of the predictive performance into the performance that can be explained by confounds and performance independent of confounds. This approach is flexible and allows for parametric and non-parametric confound adjustment. We show in real and simulated data that this method correctly controls for confounding effects even when traditional input variable adjustment produces false-positive findings.
Matching journals
The top 7 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- Relationship Between Prediction Accuracy and Feature Importance Reliability: an Empirical and Theoretical Study 97%
- Fighting or Embracing Multiplicity in Neuroimaging? Neighborhood Leverage versus Global Calibration 96%
- Selective peak inference: Unbiased estimation of raw and standardized effect size at local maxima 96%
Similar papers in this journal
- Using extreme value statistics to reconceptualize psychopathology as extreme deviations from a normative reference model 97%
- Predicting sex, age, general cognition and mental health with machine learning on brain structural connectomes 95%
- DeepComBat: A Statistically Motivated, Hyperparameter-Robust, Deep Learning Approach to Harmonization of Neuroimaging Data 95%
Similar papers in this journal
Similar papers in this journal
Similar papers in this journal
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.