Research Paper Volume 11, Issue 8 pp 2185—2201

Predicting progression from mild cognitive impairment to Alzheimer’s disease on an individual subject basis by applying the CARE index across different independent cohorts

Figure 4. Comparisons of the power of ROC curve of the CARE index with behavioral, gray matter, and functional indices in predicting the P-MCI versus N-MCI subjects in the ADNI and NADS datasets. (AC) represent comparisons of the power of ROC curve of the CARE index and individual behavioral, gray matter, and functional indices in the ADNI dataset, respectively. (DF) represent comparisons of the power of ROC curve of the CARE index and individual behavioral, gray matter, and functional indices in the NADS dataset, respectively. Abbreviations: ADNI, Alzheimer’s Disease Neuroimaging Initiative; AD, Alzheimer’s disease; P-MCI, progressive MCI, including MCI subjects who progressed to AD-type dementia at the three-year follow up; N-MCI, nonprogressive MCI, including MCI subjects who had not progressed to dementia at the three-year follow up; MCI, mild cognitive impairment; CARE, characterizing AD risk event; ROC, receiver operating characteristic; AUC, area under curve; HIP, hippocampus; PCC, posterior cingulate cortex; FG, fusiform gyrus; FCI, functional connectivity indices; GMI, gray matter indices; Aβ, β-amyloid; p-tau, phosphorylated tau; MMSE, Mini-Mental State Examination; ADAS-Cog, Alzheimer’s Disease Assessment Scale-Cognitive Subscale; AVLT, Rey Auditory Verbal Learning Test.