Covert Cerebrovascular Disease Detected by Artificial Intelligence (C2D2AI): A Platform for Pragmatic Evidence Generation for Stroke and Dementia Prevention

Silent cerebrovascular disease (SCD), including silent brain infarction (SBI) and white matter disease, is commonly found incidentally on neuroimaging scans obtained in routine clinical care. In prior studies, imaging findings of SCD are strong, independent risk factors for future stroke and dementia. The American Heart Association/American Stroke Association has identified SBI as a major priority for new studies on stroke prevention. Having established that natural language processing of routinely obtained neuroimaging reports can be used to identify SCD, and that incidentally discovered SCD is common and associated with substantial future neurological morbidity, the new study will leverage this natural language processing system and the expanded partnership with Kaiser Permanente Northern California as a platform to further characterize the observational cohort with SCD regarding their risk of future stroke and dementia and estimate treatment effects of different risk factors modification algorithms on future stroke.

0