Machine-learning derived MRI-based atrophy biomarker predicts long-term cognitive decline in stroke or transient ischemic attack

Abstract

Introduction: Alzheimer's disease-resemblance atrophy index (AD-RAI) is a machine-learning derived MRI-based brain atrophy biomarker that is valid in predicting cognitive decline in subjects with AD. We investigated the performance of AD-RAI in predicting long-term cognitive decline in subjects with stroke or transient ischemic attack (TIA). Methods: We recruited consecutive dementia-free stroke/TIA subjects who had brain MRI at baseline (i.e., within 3-6 months after the index event) and cognitive data at both baseline and 3 years. We defined cognitive decline as an increase in clinical dementia rating scale from 0 to 0.5 or above or from 0.5 to 1 or above at 3 years when compared with baseline. We investigated the association between AD-RAI, traditional brain atrophy biomarkers (hippocampus volume [HV], hippocampal fraction [HF], total brain volume [TBV], TBV/intracranial volume [ICV] ratio, ventricular-brain-ratio, presence of medial temporal lobe atrophy [MTLA]), and cerebral small vessel disease biomarkers (white matter hyperintensity [WMH]) volume, WMHV/ICV ratio presence of confluent WMH, presence of >/=3 lacunes) with cognitive decline. Results: Of 231 participants (mean age 66.0 ± 10.9, 124 [53.7] male), 55(23.8) had cognitive decline at 3 years. Among all the imaging biomarkers, AD-RAI and HV were associated with cognitive decline in univariate regression. Such a relationship was still significant with AD-RAI after adjusted for age, gender, and education (aOR [95%CI] 3.900 [1.221-12.458]). Among all imaging biomarkers, only AD-RAI was associated with slope of Montreal cognitive assessment (MoCA) after adjusted to age, gender, education (β(SE) −0.742[0.242], p=0.002). Discussion: AD-RAI predicted long term cognitive decline in subjects with stroke/TIA.