Deriving reproducible biomarkers from multi-site resting-state data: An Autism-based example

• DOI: 10.1016/j.neuroimage.2016.10.045
• Publication Date: 2016-11-16T22:00:24Z
• Authors: Alexandre Abraham; Michael P. Milham; Adriana Di Martino; R. Cameron Craddock; Dimitris Samaras; Bertrand Thirion; Gael Varoquaux
• Keywords: Adult; 0301 basic medicine; FOS: Computer and information sciences; Adolescent; Autism Spectrum Disorder; autism spectrum disorders; data heterogeneity; Datasets as Topic; Machine Learning (stat.ML); 03 medical and health sciences; 0302 clinical medicine; [STAT.ML]Statistics [stat]/Machine Learning [stat.ML]; Statistics - Machine Learning; data pipelines; [INFO.INFO-IM]Computer Science [cs]/Medical Imaging; Connectome; Image Processing, Computer-Assisted; Humans; Multicenter Studies as Topic; Child; [ STAT.ML ] Statistics [stat]/Machine Learning [stat.ML]; Cerebral Cortex; [ INFO.INFO-IM ] Computer Science [cs]/Medical Imaging; [SCCO.NEUR]Cognitive science/Neuroscience; connectome; biomarkers; Reproducibility of Results; 16. Peace & justice; Magnetic Resonance Imaging; 3. Good health; Quantitative Biology - Neurons and Cognition; FOS: Biological sciences; [ SCCO.NEUR ] Cognitive science/Neuroscience; Neurons and Cognition (q-bio.NC); resting-state fMRI; Biomarkers

Resting-state functional Magnetic Resonance Imaging (R-fMRI) holds the promise to reveal functional biomarkers of neuropsychiatric disorders. However, extracting such biomarkers is challenging for complex multi-faceted neuropatholo-gies, such as autism spectrum disorders. Large multi-site datasets increase sample sizes to compensate for this complexity, at the cost of uncontrolled heterogeneity. This heterogeneity raises new challenges, akin to those face in realistic diagnostic applications. Here, we demonstrate the feasibility of inter-site classification of neuropsychiatric status, with an application to the Autism Brain Imaging Data Exchange (ABIDE) database, a large (N=871) multi-site autism dataset. For this purpose, we investigate pipelines that extract the most predictive biomarkers from the data. These R-fMRI pipelines build participant-specific connectomes from functionally-defined brain areas. Connectomes are then compared across participants to learn patterns of connectivity that differentiate typical controls from individuals with autism. We predict this neuropsychiatric status for participants from the same acquisition sites or different, unseen, ones. Good choices of methods for the various steps of the pipeline lead to 67% prediction accuracy on the full ABIDE data, which is significantly better than previously reported results. We perform extensive validation on multiple subsets of the data defined by different inclusion criteria. These enables detailed analysis of the factors contributing to successful connectome-based prediction. First, prediction accuracy improves as we include more subjects, up to the maximum amount of subjects available. Second, the definition of functional brain areas is of paramount importance for biomarker discovery: brain areas extracted from large R-fMRI datasets outperform reference atlases in the classification tasks.<br/>in NeuroImage, Elsevier, 2016<br/>