An Integrated Machine Learning and Deep Learning Framework for Predicting Cardiovascular Disorder

One of the biggest and most prominent cardiac conditions that affects humans of any age is a heart attack. Physicians must be accurate in their findings since they work with the lives of people, which is priceless. If people consume their drugs and therapy diligently according to the schedule, early identification of cardiovascular illness may extend many lives. Earlier approaches for predicting cardiovascular illnesses were helpful in decision-making regarding the adjustments that should have taken place in people at greatest risk, thereby lowering their risks. Machine learning (ML) algorithms are necessary to make accurate choices in the forecasting of cardiac problems because the healthcare sector has a large amount of clinical information. In order to classify coronary illness, this research compares machine learning methods such as Logistic Regression (LR), Random Forest (RF), Support Vector Machine (SVM), XGBoost, and Artificial Neural Network (ANN). The algorithms with the most significant accuracy in forecasting were LR, RF, SVM, XGBoost, and ANN (80.33%, 81.97%, 80.33%, 78.69%). These findings suggested that RF and SVM are the best techniques for CVD forecasting and categorization. The ML methods Random Forest and SVM is utilized in the suggested approach since it has been shown through a contrast investigation to possess the most highly precise and dependable technique.