Machine Learning Strategies for Heart Disease Prediction in Healthcare

  • B. Aruna Kumari, P. Anjaiah, R. L. Pravallika


Heart disease is a typical issue which can be extreme in mature ages and also in individuals not having a healthy lifestyle. In the present era, death due to heart disease has become a signification issue roughly one individual dies per minute because of it. In addition to a tolerable diet, with a normal check-up and diagnosis, one can prevent it up to some extent. To bring down the number of deaths from coronary disease, there must be a quick and productive discovery mechanism. There is no compelling use of the information which is produced from the emergency clinics. Though some tools are utilized to separate the data from the database for the discovery of heart disease and many functions are having limitations. Machine learning (ML) strategies are a piece of Artificial Intelligence (AI) and the emerging field, utilized to solve numerous real-world issues and heart disease prediction is not an exception. In the literature, various data-driven methodologies are found reasonable for predicting heart disease. To improve the classification accuracy feature extraction, feature selection and optimization stages placed a key role. Classification algorithms can perform forecasting based on the training data and hence known as supervised ML algorithms. In this paper, we presented various perspectives identified with ML for predicting heart disease. It tosses light into strategies that improve the order of execution too and such techniques are known as feature selection techniques. With such techniques, the performance of ML are algorithms are improved and few strategies are discussed in this paper. With every one of these strategies, this paper gives helpful insights to the scholarly community and industry research concerning heart disease prediction.

How to Cite
B. Aruna Kumari, P. Anjaiah, R. L. Pravallika. (2020). Machine Learning Strategies for Heart Disease Prediction in Healthcare. International Journal of Advanced Science and Technology, 29(3), 8647 - 8655. Retrieved from