Improved accuracy in early identification of ischaemic stroke using convolutional neural network with support vector machine

The purpose of this study was to compare the effectiveness of two distinct neural network architectures—a support vector machine (SVM) and a customized convolution neural network (CNN)—in brain MRI imaging and stroke scan categorization. The results showed that accuracy and precision improved when the CNN was used. In this study, two groups are compared: one using a support vector machine (N = 20) and the other a convolution neural network (N = 20). We used power software to compute the total sample size using the following parameters: 98% pre-test power, 0.05 alpha, 0.1 enrollment ratio, and 95% confidence interval. The recommended solution outperforms the alternative, according to assessments utilizing the most advanced Convolution Neural Network (98%) and Support Vector Machine (89%). After using SPSS to analyze the data, we discovered that the specificity (p = 0.010) and accuracy rate (p = 0.044) had significant statistical significance. The novel Convolution Neural Network classifier significantly outperforms Support Vector Machine classifiers in the diagnosis of brain strokes.