Development and internal validation of a clinical risk score for in-hospital mortality after stroke: a single-centre retrospective cohort study in Northwest Ethiopia

Abstract

OBJECTIVE: To develop and validate a clinical risk score for in-hospital stroke mortality. DESIGN: The study used a retrospective cohort study design. SETTING: The study was carried out in a tertiary hospital in the Northwest Ethiopian region. PARTICIPANTS: The study included 912 patients who had a stroke admitted to a tertiary hospital between 11 September 2018 and 7 March 2021. MAIN OUTCOME MEASURES: Clinical risk score for in-hospital stroke mortality. METHODS: We used EpiData V.3.1 and R V.4.0.4 for data entry and analysis, respectively. Predictors of mortality were identified by multivariable logistic regression. A bootstrapping technique was performed to internally validate the model. Simplified risk scores were established from the beta coefficients of predictors of the final reduced model. Model performance was evaluated using the area under the receiver operating characteristic curve and calibration plot. RESULTS: From the total stroke cases, 132 (14.5%) patients died during the hospital stay. We developed a risk prediction model from eight prognostic determinants (age, sex, type of stroke, diabetes mellitus, temperature, Glasgow Coma Scale, pneumonia and creatinine). The area under the curve (AUC) of the model was 0.895 (95% CI: 0.859-0.932) for the original model and was the same for the bootstrapped model. The AUC of the simplified risk score model was 0.893 (95% CI: 0.856-0.929) with a calibration test p value of 0.225. CONCLUSIONS: The prediction model was developed from eight easy-to-collect predictors. The model has excellent discrimination and calibration performance, similar to that of the risk score model. It is simple, easily remembered, and helps clinicians identify the risk of patients and manage it properly. Prospective studies in different healthcare settings are required to externally validate our risk score.