Abstract: According to WHO data, cardiac disorders cause around one crore twenty lakh deaths annually. Heart illness and cardiovascular disease have historically had a significant impact on the medical field, indicating their extreme hazards and widespread impact. Though it is not feasible to predict heart illnesses or CD in advance, nor is it feasible to monitor patients around the clock due to the high time and expertise requirements, treatment and diagnosis for heart disease can be extremely difficult, especially in developing or impoverished nations. Additionally, a person may pass away as a result of inadequate medical care or a delayed diagnosis. Researchers often use the wealth of data from the medical business to produce new science and technologies aimed at reducing the number of heart disease-related deaths. Numerous algorithms and data mining approaches are available to extract information from databases and utilize that information to make highly accurate predictions about cardiac ailments. We used machine learning in this heart disease model. The whole process was implemented on a dataset from Kaggle that contained 14 attributes and 303 rows in total. The model employs the following algorithms: Random Forest, SVM, NB, K-NN, Decision Tree, and Logistic Regression.

Keywords: Machine Learning, Heart Disease, Kaggle, Cardiovascular Disease, WHO, Classification, Dataset, ML Algorithm.

Suwarna Nimkarde, Omkar Chavan, Shlok Damudre, Bhagyashree Nikam , "Machine Learning and Web Solution for Heart Disease Prediction", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 2, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13227.

PDF | DOI: 10.17148/IJARCCE.2024.13227

Open chat
Chat with IJARCCE