The prevalence of Diabetes Heart Disease, a chronic ailment that affects a significant proportion of the global populace, underscores the importance of accurate predictive models. To this end, we present a novel approach that combines feature extraction and selection using support vector machine (SVM) weights and weights between layers of a feed-forward neural network. By leveraging the strengths of both SVM and neural networks, we aim to enhance the accuracy of Diabetes Heart Disease prediction. Initially, SVM weights are utilized to extract and select pertinent features from the input data. Next, the chosen features are input into a feed-forward neural network to make predictions. Our study demonstrates the efficacy of our approach in predicting Diabetes Heart Disease with exceptional precision. By proposing a fresh and innovative approach that incorporates the strengths of different machine learning techniques, this study contributes to the field of Diabetes Heart Disease prediction.

Diabetic Heart Disease, Prediction, Support Vector Machine, Feed Forward Neural Network