A Hybrid Approach for Cardiovascular Disease Diagnosis: J48 Classifier

In today's world, we frequently hear about the heart disease issues such as the cardiovascular disease (CVD), especially in a younger generations due new culture, new virus pandemic, and food quality/habits, which has a high possibility of the leading to death. CVD is also the cause of the high global mortality rate. One of the biggest challenges is detecting cardiovascular illnesses with routine clinical data analysis, as their early detection can save countless lives. Machine learning (ML) algorithms allow for precise forecasting, intelligent decision-making, and exact predictions for data analysis. This research uses a variety of the factors that individual person has presented to a assess if a cardiac arrest has occurred. The employment of numerous ML algorithms to determine to predict CVD is common nowadays, but increasing prediction accuracy is challenge. This work tackles these issues by presenting fresh, ethically obtained using CVD dataset that includes thorough information on risk variables, examination methods, and symptoms. Through utilizing sophisticated ML methods such as SVM, Naive Bayes, LR, KNN, and J48, we were able to attain impressive testing accuracy of approximately 98.54% with J48. The suggested method is the J48 classifier, which uses a ML techniques to integrate these hybrid models and datasets. It gives an adequate diagnosis promptly and fashion designers nutritional advice each person. This study proposes a new way to find the scalable and reliable signs of heart disease by using structured datasets in tandem with sophisticated machine-learning techniques. This might result in greater outcomes for patients and less mortality.