Automated diagnoses of attention deficit hyperactive disorder using magnetic resonance imaging

Abstract

Successful automated diagnoses of attention deficit hyperactive disorder (ADHD) using imaging and functional biomarkers would have fundamental consequences on the public health impact of the disease. In this work, we show results on the predictability of ADHD using imaging biomarkers and discuss the scientific and diagnostic impacts of the research. We created a prediction model using the landmark ADHD 200 data set focusing on resting state functional connectivity (rs-fc) and structural brain imaging. We predicted ADHD status and subtype, obtained by behavioral examination, using imaging data, intelligence quotients and other covariates. The novel contributions of this manuscript include a thorough exploration of prediction and image feature extraction methodology on this form of data, including the use of singular value decompositions (SVDs), CUR decompositions, random forest, gradient boosting, bagging, voxel-based morphometry, and support vector machines as well as important insights into the value, and potentially lack thereof, of imaging biomarkers of disease. The key results include the CUR-based decomposition of the rs-fc-fMRI along with gradient boosting and the prediction algorithm based on a motor network parcellation and random forest algorithm. We conjecture that the CUR decomposition is largely diagnosing common population directions of head motion. Of note, a byproduct of this research is a potential automated method for detecting subtle in-scanner motion. The final prediction algorithm, a weighted combination of several algorithms, had an external test set specificity of 94% with sensitivity of 21%. The most promising imaging biomarker was a correlation graph from a motor network parcellation. In summary, we have undertaken a large-scale statistical exploratory prediction exercise on the unique ADHD 200 data set. The exercise produced several potential leads for future scientific exploration of the neurological basis of ADHD.

Comparison of statistical tests for group differences in brain functional networks

“…There is evidence showing that connectivity changes between two conditions could be in one direction; for example, functional connectivity could be weakened in cases than in controls (Eloyan et al 2012; Mostofsky et al 2008). To mimic this circumstance, we defined…”

Classification on ADHD with Deep Learning

“…With the belief that a community-wide effort focused on advancing functional and structural imaging examinations of the developing brain will accelerate the rate at which neuroscience can inform clinical practice, the 1000 Functional Connectomes Project provided a model which includes large-scale datasets [6], which overcomes the defects of fewer subjects. Eloyan et al [7] used decomposition of CUR and gradient boosting with motor network segmentation and random forest for prediction based on rs-fc-fMRI. They achieved the best score among the participants of the global ADHD-200 competition.…”

Discovery of Therapy-targeting Biomarkers for Post-Concussion Syndrome using Functional Neurocognitive Imaging

“…Interpretability refers to the capability of the biomarker to be meaningful in terms of any prior neuroimaging studies or evidence from other sources. That is, the biomarker should avoid capitalizing on confounding variables that are not neuro-scientifically meaningful, such as scanner head movement [53]. After discovery, the second phase of biomarker development is validation.…”