Enhancing ischemic stroke management: leveraging machine learning models for predicting patient recovery after Alteplase treatment.

Abstract

Aim: Ischemic stroke remains a leading global cause of morbidity and mortality, emphasizing the need for timely treatment strategies. This study aimed to develop a machine learning model to predict clinical outcomes in ischemic stroke patients undergoing Alteplase therapy.

Methods: Data from 457 ischemic stroke patients were analyzed, including 50 demographic, clinical, laboratory, and imaging variables. Five machine learning algorithms - k-nearest neighbors (KNN), support vector machines (SVM), Naïve Bayes (NB), decision trees (DT), and random forest (RF) - were applied for constructing models. Additional feature importance analysis were p to identify high-impact predictors.

Results: The Random Forest model showed the highest predictive reliability, outperforming other algorithms in sensitivity (0.97 ± 0.02) and F-measure (0.96 ± 0.02). feature importance analysis identified NIH1C (LOC commands (eye and hand movements)), NIH1B (LOC questions (birthday and age recall)), and NIH_noValue (the absence of any stroke characteristics) as the most influential predictors. Using only the top-ranked features identified from the feature importance analysis, the model maintained comparable performance, suggesting a streamlined yet effective predictive approach.

Conclusion: Our findings highlight the potential of machine learning in optimizing ischemic stroke treatment outcomes. Random Forest, in particular, proved effective as a decision-support tool, offering clinicians valuable insights for more tailored treatment approaches.