Maximizing Accuracy in AI-Driven Pattern Detection in Cardiac Care

Artificial Intelligence (AI) has laid down the platform where all the emerging fields can benefit for detection of patterns. In similar, evolving AI technology has revolutionized the traditional healthcare technology to other level of technological advancement. Hence, Machine learning paradigms are designed to transform the era of learning and retrieval of hidden patterns from the healthcare databases. The current scope of the work focuses on detecting patterns from car diac care database using machine learning. The database comprise of several features such as age, gender, smoking variable, blood pressure, diabetes, alcohol consumption, sleep variables and other features which can be the potential cause for the prognosis of the disease Further, the databases applicability is measured with different classifiers such K nearest neighbours (KNN), Adaboost, XGboost, Gradient Boost, Decision Tree Logistic Regression, and Random Forest Classifiers to determine the most relevant classifier for the prognosis of the disease. The results suggest that Xgboost works efficiently with higher accuracy rate as compared to other classifiers.