Incidentally-Discovered Silent Cerebrovascular Disease Identified Using Natural Language Processing Are Strong Risk Markers for Future Ischemic Stroke

Abstract

Background: White matter disease (WMD) and silent brain infarction (SBI) are known risk markers for stroke. Nevertheless, the predictive value of these changes when seen incidentally on routinely-obtained neuroimages is unknown. Methods: We included patients age ≥ 50 in the Kaiser Permanente Southern California (KPSC) health system scanned between 2009-2019 with a head CT or MRI and no prior history of ischemic stroke, transient ischemic attack, or dementia. We used natural language processing (NLP) to identify patients with SBI and WMD from the corresponding report of the index neuroimage. We used Cox proportional hazards to estimate the risk of future ischemic stroke associated with the presence of SBI and of WMD, controlling for major stroke risk factors. Results: Among 262,875 individuals receiving neuroimaging, NLP identified 13,154 (5·0%) with SBI and 78,330 (29·8%) with WMD. The incidence rate of future stroke was 32·5 (95% CI 31·1, 33·9) per 1,000 patient-years for patients with SBI; 19·3 (95% CI 18·9, 19·8) for patients with WMD and 6.8 (95% CI 6·7, 7·0) for patients without silent cerebrovascular disease. The crude HR associated with SBI was 3.40 (95% CI 3·25 to 3·56); and for WMD was 2·63 (95% CI 2·54 to 2·71). Adjusted for major stroke risk factors, the effect of incidentally-discovered SBI was found to be stronger in younger compared to older patients and for MRI- compared to CT-discovered lesions. With MRI, the adjusted HR was 2·95 (95% CI 2·53 to 3·44) for those = age 65. The adjusted HR associated with a finding of WMD was 1·76 (95% CI 1·69 to 1·82) and was not modified by age or imaging modality. Conclusion: Incidentally-discovered SBI and WMD are common in patients > age 50 and are associated with substantial increases in the risk of subsequent symptomatic stroke. These findings present an opportunity for stroke prevention. Funding Statement: This work was funded by a National Institutes of Health (NIH) grant (R01-NS102233). Declaration of Interests: None to declare. Ethics Approval Statement: The study protocol was approved by Tufts Medical Center’s and KPSC’s Institutional Review Board.