Automated diagnosis of HIV-associated neurocognitive disorders using large-scale Granger causality analysis of resting-state functional MRI

• Published in: Computers in biology and medicine Vol. 106; pp. 24 - 30
• Main Authors: Chockanathan, Udaysankar, DSouza, Adora M., Abidin, Anas Z., Schifitto, Giovanni, Wismüller, Axel
• Format: Journal Article
• Language: English
• Published: United States Elsevier Ltd 01.03.2019; Elsevier Limited
• Subjects: Adult; Age; Artificial intelligence; Automated diagnosis; Basal ganglia; Biomarkers; Brain; Brain - diagnostic imaging; Brain mapping; Caudate nucleus; Causality; Classifiers; Cognition; Cognitive ability; Cognitive tasks; Cortex (cingulate); Diagnosis; Diagnosis, Computer-Assisted; Diagnostic systems; Disorders; Drug abuse; Female; functional connectivity; Functional magnetic resonance imaging; Ganglia; Graph theory; Graphs; HIV; HIV Infections - diagnostic imaging; HIV-Associated neurocognitive disorders (HAND); Human immunodeficiency virus; Humans; Internal Medicine; Large-scale Granger causality; Learning algorithms; Machine learning; Magnetic Resonance Imaging; Male; Medical diagnosis; Medical imaging; Mental disorders; Middle Aged; Neural networks; Neurocognitive Disorders - diagnostic imaging; Neurological complications; NMR; Nuclear magnetic resonance; Other; Personal computers; Regression analysis; Resting-state fMRI; Structure-function relationships; Support Vector Machine; Support vector machines; United States > US; functional connectivity; Resting-state fMRI; Graph theory; Support vector machine; Large-scale Granger causality; HIV-Associated neurocognitive disorders (HAND); Automated diagnosis
• ISSN: 0010-4825; 1879-0534; 1879-0534
• DOI: 10.1016/j.compbiomed.2019.01.006

HIV-associated neurocognitive disorders (HAND) represent an important source of neurologic complications in individuals with HIV. The dynamic, often subclinical, course of HAND has rendered diagnosis, which currently depends on neuropsychometric (NP) evaluation, a challenge for clinicians. Here, we present evidence that functional brain connectivity, derived by large-scale Granger causality (lsGC) analysis of resting-state functional MRI (rs-fMRI) time-series, represents a potential biomarker to address this critical diagnostic need. Brain graph properties were used as features in machine learning tasks to 1) classify individuals as HIV+ or HIV− and 2) to predict overall cognitive performance, as assessed by NP scores, in a 22-subject (13 HIV−, 9 HIV+) cohort. Over nearly all seven brain parcellation templates considered, support vector machine (SVM) classifiers based on lsGC-derived brain graph features significantly outperformed those based on conventional Pearson correlation (PC)-derived features (p<0.05, Bonferroni-corrected). In a second task for which the objective was to predict the overall NP score of each subject, the lsGC-based SVM regressors consistently outperformed the PC-based regressors (p<0.05, Bonferroni-corrected) on nearly all templates. With the widely used Automated Anatomical Labeling (AAL90) template, it was determined that the brain regions that figured most strongly in the SVM classifiers included those of the default mode network (posterior cingulate cortex, angular gyrus) and basal ganglia (caudate nucleus), dysfunction in both of which have been observed in previous structural and functional analyses of HAND. •Large-scale Granger causality (lsGC) was used to derive functional brain networks.•Machine learning performed on networks accurately classified subjects as HIV+ or HIV-.•Machine learning performed on networks accurately predicted neuropsychometric scores.•lsGC-derived networks were more informative than correlation-based networks.•Results were robust across several parcellation schemes.