Big Data Predictive Analytics Model for Cardiovascular Risk Detection using Machine Learning Techniques

Cardiovascular Disease (CVD) is a leading global cause of incapacity and premature mortality. The discovery of early sickness symptoms using geospatial data will facilitate the development of fact-based health policies and suitable disease management strategies. Early identification of CVDs is one of the essential methods; researchers in the field have presented several methods for risk prediction. Most practices have used traditional machine learning techniques, which have historically produced excellent results. However, the development of artificial intelligence and neural network models has created countless new prospects in medical science. The present technique has reached 99% recognition accuracy after considerable experimentation with the Artificial Neural Network (ANN) model. A dataset with data on around 1500 patients was used to train and test the presented framework. A patient-level risk detection system will be made available as a result of the research so that patients may be aware of the Risk and implement the recommended preventive measures.