A disorder known as heart disease is when the heart stops working due to blocks in the blood vessels. Multiple research studies have come to the conclusion that this condition is now the leading cause of death in patients. Early diagnosis is essential for providing the proper treatment and could save the lives of many patients. Based on the symptoms or characteristics of a specific sample or instance, heart disease prediction requires accurately classifying a given sample as either heart disease positive or heart disease negative. As a result, artificial intelligence and machine learning have a significant impact on the healthcare industry, familiarizing people with data processing methods suitable for numerical health data. The process of searching through large amounts of data for important information is known as data mining. In this work, an intelligent cardiovascular disease prediction using KNN with data mining is presented. Datasets collected from several sources, including Kaggle and the machine-learning repository at UCI (University of California, Irvine), are used to analyze this model. The cognitive process of extracting hidden approach patterns from massive data sets is called data mining. Heart disease is predicted using K-nearest Neighbor. The efficacy of prediction models was evaluated using evaluation performance such as Fmeasure, accuracy, precision, and recall.