<p>Cardiovascular disease (CD), commonly referred to as heart disease, is a major contributor to global health concern, according to the World Health Organization (WHO). Many people have been affected by heart disease over the last few decades. The shortage of radiologists and physicians in different countries results in hindering its early diagnosis. But timely detection and prognosis of CD can enhance the life expectancy of its patients, reducing mortality rates and improving overall survival. Within the realm of medical science, the expansion of artificial intelligence is evident, leveraging advanced technology for identification, diagnosis and prediction of diseases. This research explores different state-of-the-art machine learning (ML) algorithms to analyze the Cleveland heart disease dataset, which includes a diverse set of patient characteristics and clinical information. Initially, the dataset was pre-processed involving normalization, encoding, splitting and scaling, subsequently feature extraction was carried out, and the resulting data was input into various ML models to identify the most suitable model based on diverse performance metrics viz. accuracy, precision, recall and F1 score. It was concluded that the standard AdaBoost model demonstrated a 91.8% accuracy rate in diagnosing heart disease. This research work is meaningful as it contributes to the development of automated decision support systems for early heart disease diagnosis.</p>