Joint opposite selection enhanced Mountain Gazelle Optimizer for brain stroke classification.

A significant cause of death and long-term disability globally is brain stroke. Stroke falls into one of two categories: (1) ischemic, which accounts for roughly 85% of cases when it is caused by abrupt cessation of blood supply to a particular area of the brain, and (2) hemorrhagic, which refers to bleeding or blood leakage. To provide stroke patients with individualized therapeutic care, meta-heuristic algorithms make accurate and timely predictions. The use of meta-heuristic algorithms and machine learning in the healthcare sector is growing. A new meta-heuristic algorithm called the Mountain Gazelle Optimizer (MGO) was developed in part as a result of wild mountain gazelles' social structure but suffered from slow convergence speed. Consequently, a modified MGO (mMGO) approach uses the joint opposite selection operator, which combines the selective leading opposition and the dynamic opposite learning approaches, to improve MGO. The purpose of this study is to evaluate the performance of mMGO based on the k-nearest neighbor (kNN) classifier in predicting brain stroke in data sets taken from Kaggle. Performance was assessed on the challenging CEC 2020 benchmark test functions. Compared to seven well-known optimization algorithms, the statistical results demonstrated the superiority of mMGO. Furthermore, the experimental results of mMGO-kNN for categorizing brain stroke data sets revealed that it outperformed competitors in all data sets with an overall accuracy of 95.5%, a sensitivity of 99.34%, a specificity of 98.99%, and a precision of 99.21%. [ABSTRACT FROM AUTHOR]