An Efficient SMOTE-Based Deep Learning Model for Heart Attack Prediction

Cardiac disease treatments are often being subjected to the acquisition and analysis of vast quantity digital cardiac data. These data can be utilized for various beneficial purposes. data’s utilization becomes more important when we dealing with critical diseases like a heart attack where patient life is at stake. Machine learning deep two famous techniques that helping in making raw useful. Some biggest problems arise from usage aforementioned massive resource utilization, extensive preprocessing, need features engineering, ensuring reliability classification results. The proposed research work presents cost-effective solution predict high accuracy reliability. It uses UCI dataset via machine algorithms without involvement any feature engineering. Moreover, given has an unequal distribution positive negative classes which reduce performance. synthetic minority oversampling technique (SMOTE) handle imbalance system discarded engineering dataset. This led efficient as proves costly process. results show among all algorithms, SMOTE-based artificial neural network tuned properly outperformed other models many existing systems. ensures it effectively used prediction attack.