A Pragmatic Approach of Heart and Liver Disease Prediction using Machine Learning Classifiers

heart disease, also known as cardiovascular disease, can cause a heart attack by altering the body’s blood flow. Liver disease contributes to a global death toll of about 2 million each year. The adaptation of Artificial Intelligence and Machine Learning has the latent capacity to fundamentally metamorphize the healthcare sector. This paper proposes undertaking a comparison analysis of different machine learning classifiers such as Random Forest, Logistic Regression, Support Vector, Naive Bayes, Decision Tree, and K-Nearest Neighbors. In our experiment, we employed four datasets, all sourced from Kaggle. In the Heart disease dataset, the best accuracy achieved was 82.35%. For the Heart Disease 2020 dataset, the highest accuracy was 74.59%. In the Framingham dataset, the top accuracy reached 68.6%. Lastly in the liver disease dataset, the highest accuracy was 83.33%.