Supervised machine learning method tailored for five brain MRI events is predictive of cognitive status

Abstract

AbstractBackgroundDespite the large neuroanatomic measurements obtained from brain MRI segmentation, we do not have yet a definitive neuroanatomic or vascular feature/even that can precisely delineate a cognitively normal subject from cognitively impaired and Alzheimer’s disease (AD). Increasing lifespan of population accompanied with increased prevalence of cardiovascular risks across globe demands for precise early detection of AD and cognitive status (impaired or normal) in the aging individuals. Here, we have employed machine learning (ML) method on neuroanatomic volume and white matter hyperintensity (WMH) volume obtained from MRI analyses of data from National Alzheimer’s Coordinating Center (NACC) to identify participants as cognitively normal (CN), cognitively impaired with etiological diagnosis as AD and cognitively impaired (CI) subjects.MethodBrain segmentation outputs for neuroanatomic‐volume and White matter hyperintensity (WMH) was obtained from NACC for 1290 unique subjects with total of 3684 longitudinal‐MRI. Supervised ML was performed using the MRI parameters for identifying the subjects as AD, CI, and CN. 50% of the MRI were used as training set while another 50% was used as test. Various combinations of neuroanatomic volume with WMH quantity were tested for accuracy of delineating the AD, CI and CN groups using random forest method. Furthermore, various ML methods such as XGB classifiers, classification tree, bagging classifier and simple classification were tested for accuracy using the optimized neuroanatomic volume and WMH.ResultRandom forest method converged with a combination of 5‐MRI features, intracranial, gray‐matter, cerebral CSF, hippocampus, and White‐matter hyperintensity volume with highest accuracy (83.3%) in identifying AD, CI, and CN subjects (Fig. 1). Inclusion of normal appearing white‐matter volume during the ML optimization of MRI features led to significant reduction in the accuracy. Simple random forest ML method showed highest accuracy using the optimized MRI features (Fig. 2).ConclusionAll the neuroanatomic events obtained from brain MRI may not be specific in providing diagnostic features for evaluating brain health. Here we show that a combination of 5 MRI features that includes microvascular pathology and neuroanatomic volume may provide a specific and efficient non‐invasive imaging biomarker to evaluate brain health in aging population.