Prediction of recurrence and functional status in young ischemic stroke patients: Comparison of machine learning and traditional statistical methods.

Introduction: Ischemic stroke in young adults is a significant social and economic burden. Machine learning (ML) techniques can potentially predict the outcomes of recurrence and functional status after a stroke more accurately than traditional statistical methods. We sought to predict these outcomes in young individuals with stroke with machine learning and compare that with traditional statistical methods. Methods: This study is part of Global Outcome Assessment Lifelong After Stroke in Young Adults (GOAL) initiative, which collects individual patient data from hospital-based young stroke (18–50 years) cohorts from 29 countries covering all continents worldwide. We compared several common machine learning models with traditional logistic regression to investigate the best models for predicting functional outcome, as measured by the modified Rankin scale at three months post-stroke, and stroke recurrence during follow-up. Results: Functional outcome was available for 7937 patients, and stroke recurrence for 9366 patients. Poor functional outcomes post-stroke occurred in 27.0% of cases, and stroke recurrence in 10.1% of cases during a median follow-up time of 75 months. For functional outcome, multilayer perceptron model achieved the highest mean area under the receiver operating characteristic curve (AUC) at 0.92 ± 0.08. Random forest model attained the highest AUC (0.68 ± 0.03) for predicting stroke recurrence. However, their results were not statistically significantly higher than those for logistic regression. Conclusion: Our work explored the use of machine learning to predict outcomes in young stroke patients. However, in our cohort, ML methods provided only moderate added value compared to logistic regression for predicting stroke recurrence and functional outcome.