Impact of Deep Learning Algorithms in Cardiovascular Disease Prediction

Heart disease is a life-threatening condition that can strike anyone anywhere in the world. If it can be predicted, then actions can be taken to avoid it. According to the World Health Organization (WHO), cardiovascular diseases (CVDs) are the largest cause of death worldwide, killing an estimated 17.9 million of people each year. In healthcare, a predictive model learns from a patient's past data in order to forecast their future illnesses and prescribe treatment. A deep learning model can help health professionals make quick judgments about medications and hospitalizations, saving time and improving the healthcare business. The use of deep learning and machine learning models like Support Vector Machine (SVM), Naive Bayes (NB), Random Forest (RF), Decision Trees (DT), Multilayer Perceptron Neural Network and K-nearest neighbor(KNN), Artificial Neural Network (ANN), Auto Encoder (AE) and Recurrent Neural Network (RNN) on various healthcare applications is highlighted in this review. The result indicates that, machine learning\deep learning model with feature selection and optimization techniques improves the prediction accuracy and effectiveness of the model by reducing the system's learning time. This paper analyzes the various studies conducted in cardiovascular disease prediction (CVD)using deep learning\machine learning approaches.