Beyond diagnosis: Leveraging routine blood and urine biomarkers to predict severity and functional outcome in acute ischemic stroke

Abstract

Background: The initial severity of acute ischemic stroke (AIS) is a crucial predictor of the disease outcome. In this study, blood and urine biomarkers from patients with AIS were measured to estimate stroke severity and predict long-term stroke outcomes. Methods: The medical records of patients with AIS between October 2016 and May 2020 were retrospectively analyzed. The relationships of blood and urine biomarkers with stroke severity at admission were evaluated in patients with AIS. Predictive models for initial stroke severity and long-term prognosis were then developed using a panel of identified biomarkers. Results: A total of 2229 patients were enrolled. Univariate analysis revealed 12 biomarkers associated with the National Institutes of Health Stroke Scale scores at admission. The area under the curve values for predicting initial stroke severity and long-term prognosis on the basis of these biomarkers were 0.7465, 0.7470, and 0.8061, respectively. Among multiple tested machine-learning, eXtreme gradient boosting exhibited the highest effectiveness in predicting 90-day modified Rankin Scale scores. SHapley Additive exPlanations revealed fasting glucose, albumin, hemoglobin, prothrombin time, and urine-specific gravity to be the top five most crucial biomarkers. Conclusion: These findings demonstrate that clinically available blood and urine biomarkers can effectively estimate initial stroke severity and predict long-term prognosis in patients with AIS. Our results provide a scientific basis for developing tailored clinical treatment and management strategies for AIS, through incorporating liquid biomarkers into stroke risk assessment and patient care protocols for patients with AIS.

Keywords

• Biomarker
• Ischemic stroke
• Liquid biopsy
• Machine learning
• Outcome
• Prognosis