Predictors of stroke favorable functional outcome in Guinea, results from the Conakry stroke registry

Abstract

Low- to middle-income countries (LMICs) now bear most of the stroke burden. In LMICs, stroke epidemiology and health care systems are different from HICs. Therefore, a high-income country (HIC)-based predictive model may not correspond to the LMIC stroke context. Identify the impact of modifiable variables in acute stroke management in Conakry, Guinea as potential predictors of favorable stroke outcome. Data were extracted from the Conakry stroke registry that includes 1018 patients. A logistic regression model was built to predict favorable stroke outcomes, defined as mRS 0-2. Age, admission NIHSS score, mean arterial blood pressure and capillary glycemia were chosen as covariates. Delay to brain CT imaging under 24 h from symptom onset, fever, presence of sores and abnormal lung auscultation were included as factors. NIHSS score on admission, age and ischemic stroke were included in the null model as nuisance parameters to determine the contribution of modifiable variables to predict stroke favorable outcome. Lower admission NIHSS, brain CT imaging within 24 h of symptoms onset and lower mean arterial blood pressure emerged as a significant positive predictors of favorable stroke outcome with respective odd ratios (OR) of 1.35 [1.28-1.43], 2.1 [1.16-3.8] and 1.01 [1.01-1.04]. The presence of fever or sores impacted negatively stroke favorable outcomes with OR of 0.3 [0.1-0.85] and 0.25 [0.14-0.45]. The area under receiver operating characteristic curves (AUC) of the model was 0.86. This model explained 44.5% of the variability of the favorable stroke outcome with 10.2% of the variability explained by the modifiable variables when admission NIHSS, and ischemic stroke were included in the null model as nuisance parameter. In the Conakry stroke registry, using a logistic regression to predict stroke favorable outcome, five variables that led to an AUC of 0.86: admission NIHSS, early brain CT imaging, fever, sores and mean blood pressure. This paves the way for future public health interventions to test whether modulating amendable variables leads to increased favorable stroke outcomes in LMICs.

Figure 1

Probability of favorable outcome according to significant predictive variables. MRS modified Rankin Scale, CT brain computed tomography, NIHSS National institute of health stroke scale. The “y” axis of the graph corresponds to the probability of achieving a favorable outcome (0: no probability, 1: 100% of probability).