Application of machine learning-based models to boost the predictive power of the SPAN index

Background: This study re-explored the predictive validity of Stroke Prognostication using Age and National Institutes of Health Stroke Scale (SPAN) index in patients who received different treatments for acute ischemic stroke (AIS) and developed machine learning-boosted outcome prediction models. Methods: We evaluated the prognostic relevance of SPAN index in patients with AIS who received intravenous tissue-type plasminogen activator (IV-tPA), intra-arterial thrombolysis (IAT) or non-thrombolytic treatments (non-tPA), and applied machine learning algorithms to develop SPAN-based outcome prediction models in a cohort of 2145 hospitalized AIS patients. The performance of the models was assessed and compared using the area under the receiver operating characteristic curves (AUCs). Results: SPAN index ≥100 was associated with higher mortality rate and higher modified Rankin Scale at discharge in AIS patients who received the different treatments. Compared to the lower AUCs for the SPAN-alone model across all groups, the AUCs of the logistic regression-boosted model were 0.838, 0.857, 0.766 and 0.875 for the whole cohort, non-tPA, IV-tPA and IAT groups, respectively. Similarly, the AUCs of the generated artificial neural network were 0.846, 0.858, 0.785 and 0.859 for the whole cohort, non-tPA, IV-tPA and IAT groups, respectively, while for gradient boosting decision tree model, we computed 0.850, 0.863, 0.779 and 0.815. Conclusions: SPAN index has prognostic relevance in patients with AIS who received different treatments. The generated machine learning-based models exhibit good performance for predicting the functional recovery of AIS; thus, their proposed clinical application to aid outcome prediction and decision-making for the patients with AIS.