Benchmarking functional connectome-based predictive models for resting-state fMRI

• Published in: NeuroImage (Orlando, Fla.) Vol. 192; no. 192; pp. 115 - 134
• Main Authors: Dadi, Kamalaker, Rahim, Mehdi, Abraham, Alexandre, Chyzhyk, Darya, Milham, Michael, Thirion, Bertrand, Varoquaux, Gaël
• Format: Journal Article
• Language: English
• Published: United States Elsevier Inc 15.05.2019; Elsevier Limited; Elsevier
• Subjects: Accuracy; Alzheimer's disease; Autism; Benchmarking - methods; Biomarkers; Brain - diagnostic imaging; Brain - physiology; Brain mapping; Cannabis; Classification; Computer Science; Connectome - methods; Connectome - standards; Datasets; Dictionaries; Functional connectomes; Functional magnetic resonance imaging; Humans; Intelligence; Machine Learning; Magnetic Resonance Imaging - methods; Magnetic Resonance Imaging - standards; Medical Imaging; Mental disorders; Models, Neurological; Neurodegenerative diseases; Neuroimaging; Population study; Post traumatic stress disorder; Prediction models; Predictive modeling; Rest; Resting-state fMRI; Schizophrenia; Trends; Resting-state fMRI; Predictive modeling; Population study; Functional connectomes; Classification

Functional connectomes reveal biomarkers of individual psychological or clinical traits. However, there is great variability in the analytic pipelines typically used to derive them from rest-fMRI cohorts. Here, we consider a specific type of studies, using predictive models on the edge weights of fu...