Application of Machine Learning for the Detection of Heart Disease

Abstract

One of the most common tasks in machine learning is data classification. Machine learning emerges as a key feature to derive information from corporate operating datasets to large databases. Machine Learning in medical health care is evolving as a significant research field for delivering prognosis and a deeper understanding on medical data. Most methods of machine learning depend on several features defining the behavior of the algorithm, influencing the output, and the complexity of the resulting models either directly or indirectly. Many machine learning methods have been used in the past to detect heart diseases. Neural network and logistic regression are some of the few popular machine learning methods used in heart disease diagnosis. They analyze multiple algorithms such as neural network, K-nearest neighbor, naive bayes, and logistic regression along with composite approaches incorporating the aforementioned heart disease diagnostic algorithms. The system was implemented and trained in the python platform by using the UCI machine learning repository benchmark dataset. For the new data collection, the framework can be extended.