Abstract
INTRODUCTION: Cerebral amyloid angiopathy (CAA) increases the risk of amyloid-related imaging abnormalities in Alzheimer's disease (AD) patients receiving anti-amyloid-beta therapies, emphasizing the need to identify its risk factors. METHODS: Data were collected from three cohort studies, and a machine learning model was developed to predict CAA occurrence using the selected risk factors. RESULTS: The AD neuropathologic changes (ADNC)-CAA association was significantly positive in the cross-sectional analysis. When stratified by selected risk factors, this association was generally stronger among females, smokers, people with a history of stroke/memory complaints, apolipoprotein E (APOE)-ε4 carriers, and those without diabetes/heart conditions. In the longitudinal analysis of the association between potential risk factors and CAA, a higher risk of CAA was observed among males, older individuals, smokers, people with diabetes/heart conditions, lower Mini-Mental State Examination (MMSE) scores, and APOE-ε4 carriers compared to their respective reference groups. DISCUSSION: Our study identified risk factors for cerebral amyloid angiopathy, informing potential prevention strategies. HIGHLIGHTS: ADNC were significantly positively associated with the risk of CAA. The ADNC-CAA association was generally stronger among females, smokers, people with a history of stroke/memory complaints, APOE-ε4 carriers, and those without diabetes or heart conditions. Longitudinally, higher CAA risk was observed among males, older individuals, smokers, people with diabetes/heart conditions/lower MMSE scores, and APOE-ε4 carriers compared to their reference groups.