BackgroundAccurate prediction of clinical outcomes in individual patients following acute stroke is vital for healthcare providers to optimize treatment strategies and plan further patient care. Here, we use advanced machine learning (ML) techniques to systematically compare the prediction of functional recovery, cognitive function, depression, and mortality of first-ever ischemic stroke patients and to identify the leading prognostic factors.MethodsWe predicted clinical outcomes for 307 patients (151 females, 156 males; 68 ± 14 years) from the PROSpective Cohort with Incident Stroke Berlin study using 43 baseline features. Outcomes included modified Rankin Scale (mRS), Barthel Index (BI), Mini-Mental State Examination (MMSE), Modified Telephone Interview for Cognitive Status (TICS-M), Center for Epidemiologic Studies Depression Scale (CES-D) and survival. The ML models included a Support Vector Machine with a linear kernel and a radial basis function kernel as well as a Gradient Boosting Classifier based on repeated 5-fold nested cross-validation. The leading prognostic features were identified using Shapley additive explanations.ResultsThe ML models achieved significant prediction performance for mRS at patient discharge and after 1 year, BI and MMSE at patient discharge, TICS-M after 1 and 3 years and CES-D after 1 year. Additionally, we showed that National Institutes of Health Stroke Scale (NIHSS) was the top predictor for most functional recovery outcomes as well as education for cognitive function and depression.ConclusionOur machine learning analysis successfully demonstrated the ability to predict clinical outcomes after first-ever ischemic stroke and identified the leading prognostic factors that contribute to this prediction.
Background White matter hyperintensities (WMH) are the result of cerebral small vessel disease and may increase the risk of cognitive impairment (CI), recurrent stroke, and depression. We aimed to explore the association between selected cerebrovascular risk factors (CVRF) and WMH load as well as the effect of increased WMH burden on recurrent vascular events, CI, and depression in first-ever ischemic stroke patients. Methods 431 from the PROSpective Cohort with Incident Stroke (PROSCIS) were included; Age-Related White Matter Changes (ARWMC) score was used to assess WMH burden on FLAIR. The presence of CVRF (defined via blood pressure, body-mass-index, and serological markers of kidney dysfunction, diabetes mellitus, and hyperlipoproteinemia) was categorized into normal, borderline, and pathological profiles based on commonly used clinical definitions. The primary outcomes included recurrent vascular events (combined endpoint of recurrent stroke, myocardial infarction and/or death), CI 3 years post-stroke, and depression 1-year post-stroke. Results There was no clear association between CVRF profiles and WMH burden. High WMH lesion load (ARWMC score ≥ 10) was found to be associated with CI (adjusted OR 1.05 [95% CI 1.00–1.11]; p < 0.02) in a mixed-model analysis. Kaplan–Meier survival analysis showed a visible increase in the risk of recurrent vascular events following stroke; however, after adjustment, the risk was non-significant (HR 1.5 [95% CI 0.76–3]; p = 0.18). WMH burden was not associated with depression 1-year post stroke (adjusted OR 0.72 [95% CI 0.31–1.64]; p = 0.44). Conclusion Higher WMH burden was associated with a significant decline in cognition 3 years post-stroke in this cohort of first-ever stroke patients.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.