A Machine Learning Based Analysis of Heart Disease Diagnosis

Heart disease has been one of the leading causes of death globally, but it is challenging to predict without medical tests. Machine learning algorithms can process vast amounts of data in medicine, revealing confidential information. The paper aims to find out how machine learning algorithms can be employed to predict cardiac disease. Naive Bayes, Support Vector Machines, Decision Trees, Bagging and Boosting, and Random Forest are used to diagnose cardiac disease using machine learning techniques accurately. All these machine learning methods/algorithms can examine vast amounts of data, enabling medical practitioners to make more cost-effective judgments. By analyzing clinical data, establishing connections among multiple diagnostic variables, building a predictive model, and comparing it to a new dataset, the study found that the RandomForest Classifier predicted heart illnesses with highest accuracy. The study found that employing a larger dataset for training and testing can improve the model's accuracy and modify different hyperparameters. The study concludes that artificial intelligence using ML modeling can categorize people with or without cardiovascular conditions.