Decision-making in clinical diagnostic for brain tumor detection based on advanced machine learning algorithm

Brain tumors, abnormal growths in the brain or spinal canal, can be benign or malignant, causing symptoms like headaches, seizures, and cognitive decline by disrupting brain function. Therefore, developing reliable predictive models for diagnosis and prognosis is crucial. In this paper, the prediction of brain tumors is made using machine learning models enhanced by an optimizer, namely Escaping Bird Search Optimization. Optimized models incorporate Ada Boost Classifier (ADEB), Gaussian Process Classifier (GPEB), and Support Vector Classifier (SVC) which, after being tested on a few databases, were named ADEB, SVEB, and GPEB, respectively, and their predictive power was assessed. The best single model performance overall on all databases is the SVC with an average accuracy of 0.981, while among enhanced models, the optimized model, called SVEB, using SVC, attained the highest accuracy for all models and reached as high as 0.990. These findings underscore the role of optimization techniques and demonstrate the effectiveness of machine learning in predicting brain cancers. The improved performance of the enhanced SVC model, SVEB, suggests it could offer a reliable approach for accurate brain tumor prediction. Enhanced patient outcomes and early diagnosis could be an implication of this in the field of neuro-oncology.