Confound Removal and Normalization in Practice: A Neuroimaging Based Sex Prediction Case Study

Dong, Yuxiao; Eickhoff, Simon B.; Patil, Kaustubh R.; Saunders, Craig; Van Hoecke, Sofie; More, Shammi; Caspers, Julian; Mladenić, Dunja; Ifrim, Georgiana

doi:10.1007/978-3-030-67670-4_1

Contribution to a book

FZJ-2021-01463

Confound Removal and Normalization in Practice: A Neuroimaging Based Sex Prediction Case Study

Dong, Y. (Editor) ; Ifrim, G. (Editor) ; Mladenić, D. (Editor) ; Saunders, C. (Editor) ; Van Hoecke, S. (Editor) ; More, S.FZJ* ; Eickhoff, S. B.FZJ* ; Caspers, J. ; Patil, K. R. (Corresponding author)FZJ*

2021
Springer International Publishing Cham
ISBN: 978-3-030-67669-8 (print), 978-3-030-67670-4 (electronic)

Machine Learning and Knowledge Discovery in Databases. Applied Data Science and Demo Track / Dong, Yuxiao (Editor) ; Cham : Springer International Publishing, 2021, Chapter 1 ; ISSN: 0302-9743=1611-3349 ; ISBN: 978-3-030-67669-8=978-3-030-67670-4 ; doi:10.1007/978-3-030-67670-4 Cham : Springer International Publishing, Lecture Notes in Computer Science 12461, 3 - 18 (2021) [10.1007/978-3-030-67670-4_1]

This record in other databases:

Please use a persistent id in citations: http://hdl.handle.net/2128/27537 doi:10.1007/978-3-030-67670-4_1

Abstract: Machine learning (ML) methods are increasingly being used to predict pathologies and biological traits using neuroimaging data. Here controlling for confounds is essential to get unbiased estimates of generalization performance and to identify the features driving predictions. However, a systematic evaluation of the advantages and disadvantages of available alternatives is lacking. This makes it difficult to compare results across studies and to build deployment quality models. Here, we evaluated two commonly used confound removal schemes–whole data confound regression (WDCR) and cross-validated confound regression (CVCR)–to understand their effectiveness and biases induced in generalization performance estimation. Additionally, we study the interaction of the confound removal schemes with Z-score normalization, a common practice in ML modelling. We applied eight combinations of confound removal schemes and normalization (pipelines) to decode sex from resting-state functional MRI (rfMRI) data while controlling for two confounds, brain size and age. We show that both schemes effectively remove linear univariate and multivariate confounding effects resulting in reduced model performance with CVCR providing better generalization estimates, i.e., closer to out-of-sample performance than WDCR. We found no effect of normalizing before or after confound removal. In the presence of dataset and confound shift, four tested confound removal procedures yielded mixed results, raising new questions. We conclude that CVCR is a better method to control for confounding effects in neuroimaging studies. We believe that our in-depth analyses shed light on choices associated with confound removal and hope that it generates more interest in this problem instrumental to numerous applications.

Contributing Institute(s):