Cardiovascular Disease Prediction Using Machi...

Cardiovascular Disease Prediction Using Machine Learning

Author Name : Mourya Teja Kunuku, Teja Ellendula, Vamshi Krishna Samudrala, Archana Chaluvadi, Lingala Niharika, Anshu Gupta, Jella Nikhitha

ABSTRACT

Heart disease-related deaths have become a big issue in today's world, with one person dying from the disease every minute. It considers both male and female groups, and the ratio varies by location. It is also used for the 25-69 age group. This isn't to say that people of all ages will be affected by heart disease. This condition could start in the early stages of life, and predicting the source and sickness is currently a huge challenge. Heart disease is one of the world's most fatal problems, one that cannot be seen with the naked eye and manifests itself as soon as it reaches its limits. As a result, precise diagnosis at the right moment is necessary. Every day, the health-care business generates massive amounts of patient and illness-related data. Researchers and practitioners, on the other hand, do not make appropriate use of this data. Despite its lack of knowledge, the healthcare business now has a wealth of data. In data mining and machine learning, there are a variety of approaches and tools for extracting usable information from databases and using that information to make more accurate diagnoses and decisions. So, in order to detect such disorders in time for adequate treatment, a reliable, precise, and feasible approach is required. In the realm of medicine, machine learning algorithms and approaches have been used to process enormous data sets. Researchers employ a variety of data mining and machine learning approaches to analyze large data sets and aid in the accurate prediction of cardiac illnesses. This research compares and contrasts the Nave Bayes, Help Vector Machine, Random Forest, and supervised learning models to find the most successful algorithm. When compared to other algorithms, Random Forest has 95.08 per cent more precision.

Keywords: Cardiovascular Diseases, Support Vector Machines, K- Nearest Neighbor, Naive Bayes, Decision Tree, Random Forest, Ensemble Models