Heart Disease Prediction using Machine Learning

Vishal Kumar Sharma, Aviral Siwach, Ms. Arpan Kumari

DecisionTree, NaiveBayes, LogisticRegression, Random Forest, Heart Disease Prediction.

It is one of the most challenging tasks in medicine to forecast the prevalence of cardiovascular disease. Nearly one person dies from cardiovascular disease per minute these days.Datascience is essential for healthcare companies to manage large data sets. Because predicting cardiac sickness is so difficult, automating the prediction process is vital for reducing risk and notifying patients early. The UCI Machine Learning Repository has a dataset pertaining to cardiac disease that was utilized in this work. In order to assess the likelihood of cardiovascular disease and categorize patients' risk levels, the proposed study employs a number of data mining methods, including Naive Bayes, Decision Tree, Logistic Regression, and Random Forest.The purpose of this research was to examine and contrast different machine learning techniques. The testing results showed that the Random Forest approach had the highest accuracy rate of 90.16 percent compared to all other machine learning algorithms.

https://dx.doi.org/10.31873/IJEAS.12.02.02