Machine Learning-Based Cardiovascular Heart Disease Detection: A Review with Future Scope

Cardiovascular Disease is one of the major vital diseases causing premature death throughout the nation. One of the difficult tasks is predicting the onset of cardiovascular disease, normally which will be carried out with clinical data analysis. Nowadays enforcement of machine learning and neural networks in the healthcare sector has shown promising in assisting and predicting disease. This paper briefed about the work done so far to predict, detect, and classify cardiovascular diseases by applying machine learning algorithms using features and appropriate datasets. The main focus here is to give a future scope for eminent and young researchers to carry their work in the field by opting for an appropriate model, datasets, and features to develop a better predictive model. The object detection algorithm model such as Random Forest, Logistic Regression, Decision Tree, and Support Vector Machine model performance with the clinical datasets have shown immersive responses. Even though to improve reliability and performance here provided the framework for the prediction, detection, and classification of cardiovascular disease by applying machine learning model using algorithms such as Convolutional Neural Network, Region-based CNN, Fast RCNN, Mask RCNN, SSD, YOLO and MobileNet.