I am #SM Mahamudul Hasan. This is my Machine Learning academic project. I collect the dataset from Kaggle.com. Then I plot the dataset and create EDA . Also i implement different Machine Learning algorithm to the dataset and predict the output.
The heart is the most vital organ in the human body. It transports oxygen and critical nutrients to all regions of the body through the blood, assists in metabolic functions, and eliminates metabolic wastes. Thus, even modest cardiac issues may have a detrimental effect on the whole system. Researchers are devoting a large portion of their data analytic efforts to help physicians in predicting cardiac problems. Thus, an examination of data relating to various health concerns and the organ's function may assist in forecasting the organ's healthiness with a certain likelihood. To aid clinicians, a machine learning method for detecting cardiac disease has been built. The heart, being a vital part of the human body, and the disorders associated with it, such as cardiovascular disorders, have killed many people in our society over the previous decades and are also recognized as one of the most life-threatening illnesses on the planet. Today's healthcare sector is data-rich but knowledge-deficient. There are several data mining techniques and machine learning algorithms available for extracting information from data stores and using that information for more precise diagnosis and decision making. The primary contribution of this review is to present contemporary research on heart disease prediction with comparison findings and to draw analytical conclusions. The study's accuracy in predicting heart disease using several Machine Learning models is summarized below.
● XGBoost: 95.08%
● AdaBoost: 93.44%
● MLPClassifier: 93.44%
● Random Forest: 91.8%
● Gradient Boosting: 91.8%
● Logistic Regression: 90.16%
● SVM: 90.16%
● KNN: 88.52%
● Decision Tree: 81.97%