Heart Disease Prediction Using Machine Learning as a Problem Solving Innovation
Anupam Garain Kashyap1, Prof.Ramesh Kumar2
1,2 Department of Computer Science & Engineering, K.K. University, Berauti, Nepura,
Biharsharif, Nalanda, Bihar, 803115, India
Abstract:
The main aim of our project is to provide a solution to people who are unaware of multiple cardiac issues faced by them. We have utilized the technical advantages of Machine Learning which has allowed us to analyze datasets and furthermore seek multiple algorithms that has allowed us to reach to most optimized and efficient results. We focus on providing significant advantages in health industry with the perfect amalgam of our technical expertise to ensure that each person gets a chance to be aware of cardiac issues faced by him.
Heart diseases contribute to a greater section of global deaths which is highly visible in the death index and it has been noted that majority of people were unable of their cardiac diseases. These cardiovascular diseases have been the cause of death for almost 17.9 million deaths as per 2019 census. This is highly believed that almost 1/3rd of deaths are caused due to health negligence and unable to comprehend the common causes of cardiovascular diseases. In low income or developing countries this issue is a major concern and one of the most prominent reasons for the same is their eating habits and lifestyle which has serious long term effects. Nowadays people are using smart watches that allow them to track their breath rate and heart rate but without a reliable portal that allows them to analyze the gathered information it just remains a data sets. Without proper management and medical care these diseases have serious concerns in the long term which could affect the lifespan of the person. Heart stroke and regular chest pains are more common issues then they are understood which is the major reason why a person must keep a track of his cardiac health.
Keywords: Machine Learning, Cardiovascular Diseases, heart disease prediction, Logistic Regression, Random Forest.