Exploring the Efficacy of Machine Learning Models for Brain Tumor Detection with Binary Classification

The main objective of this research is to examine the utilization of artificial intelligence models, such as K-Nearest Neighbours (KNN), Logistic Regression, and Neural Networks, in the classification of brain tumors into two distinct groups: benign and malignant.In order to create a sustainable and ecologically friendly healthcare infrastructure for underdeveloped countries, the project uses MRI scans and clinical data. By utilizing a comprehensive dataset comprising medical pictures in the form of MRI scans and their related clinical data, to implement preprocessing, feature selection, and extraction techniques to improve the effectiveness of our model. The K-Nearest Neighbours (KNN) algorithm and Logistic Regression were utilized as baseline models to establish first performance standards. However, it was observed that Neural Networks exhibited exceptional proficiency in collecting intricate patterns and correlations that are inherent in the information. The results of our research underscore the notable advancements made by the Neural Network (NN). This research presents evidence of the effectiveness of artificial intelligence (AI) techniques in accurately identifying brain tumors with a notable level of accuracy. The neural network model demonstrated notable performance in terms of precision, recall, and F1 scores, consistently obtaining an 87.4% value for each evaluation criterion. The results presented above suggest that the NN(Neural Network Model) has the potential to improve diagnosis accuracy within the realm of clinical neuro-oncology.