A Predictive Analytics in Cardiology: Evaluating Machine Learning Algorithms

As one of the leading causes of mortality globally today, heart disease demands the development of novel approaches to early detection and prevention. Leveraging it with artificial intelligence and machine learning, the medical industry is seeing a transformative shift, enabling it more accurate, and quickly. This paper focuses on developing predictive model for heart disease using various ML algorithms, including Gradient Boost(GB) Gaussian Naive Bayes (G-NB)and Random forest (RF) using the dataset which consists of various parameters including age, gender, cholesterol levels, and presence of angina. The chance of heart disease can be accurately predicted by the GB-based heart disease prediction (HDP) model with a 92% accuracy, while the RF-HDP and G-NB-HDP models have an 89% and 85% accuracy, respectively.