Addressing Confounding in Predictive Models with an Application to Neuroimaging.

We just began a large new study on
Autism, ADHD, Anxiety & Depression in 12-17 year-olds.
Read more and learn how you can help!

TitleAddressing Confounding in Predictive Models with an Application to Neuroimaging.
Publication TypeJournal Article
Year of Publication2016
AuthorsLinn, KA, Gaonkar, B, Doshi, J, Davatzikos, C, Shinohara, RT
JournalInt J Biostat
Date Published2016 05 01
KeywordsBrain, Humans, Machine Learning, Magnetic Resonance Imaging, Neuroimaging, Pattern Recognition, Automated

Understanding structural changes in the brain that are caused by a particular disease is a major goal of neuroimaging research. Multivariate pattern analysis (MVPA) comprises a collection of tools that can be used to understand complex disease efxcfects across the brain. We discuss several important issues that must be considered when analyzing data from neuroimaging studies using MVPA. In particular, we focus on the consequences of confounding by non-imaging variables such as age and sex on the results of MVPA. After reviewing current practice to address confounding in neuroimaging studies, we propose an alternative approach based on inverse probability weighting. Although the proposed method is motivated by neuroimaging applications, it is broadly applicable to many problems in machine learning and predictive modeling. We demonstrate the advantages of our approach on simulated and real data examples.

Alternate JournalInt J Biostat
PubMed ID26641972
PubMed Central IDPMC5154735
Grant ListR01 AG014971 / AG / NIA NIH HHS / United States
R01 NS085211 / NS / NINDS NIH HHS / United States
U24 CA189523 / CA / NCI NIH HHS / United States