Enhanced Machine Learning Model for Design and Evaluation of Various Algorithms Applied in Clinical Cardiovascular Disease

Cardiovascular Diseases (CVD) are the category of diseases mainly involving the heart and the blood vessels of our body. It is one of the most challenging obstacles to combat for the healthcare sector. The early prediction of Cardiovascular Diseases is essential in saving human lives from these diseases. Many methods exist for reducing risk factors such as blood pressure and cholesterol levels. In our research work, we are considering 4133 range of index as an input dataset. The machine learning algorithm is a prominent technology to predict diseases at earlier stages. The various machine learning algorithms are implemented in our research work such as KNN, SVM, Kernel SVM, Decision Tree, Random Forest, Naïve Bayes, XGBoost. Due to the Covid 19 pandemic, people around the world were forced to quarantine at home for long periods, encouraging a rise in parameters such as BMI Hypertension, improper nutrition, diets, sodium, lack of exercise, high cholesterol, etc. These factors have dramatically increased by 62% from 2019 to 2022. Our implementation results shows logistic regression – 85.39%, KNN – 84.42%, SVM–84.71%, Kernel SVM–84.81%, Naïve Bayes – 83.17%, Decision Tree – 77.17%, Random Forest 85%, and XGBoost–85.49% respectively. The overall highest accuracy out of all these algorithms is of XGBoost, at 85.49%.