Heart disease accounts for a sizable portion of worldwide mortality and morbidity.Using clinical data analytics to predict heart disease survival is a challenging task. However, the inception of data mining tools and platforms helps transform large amounts of unstructured data generated by the healthcare industry into relevant information that allows informed decision-making. Numerous studies have proven that appropriate feature engineering techniques aimed at essential characteristics are vital for enhancing the performance of machine learning models. This study aims to identify relevant characteristics and data mining approaches that can significantly improve mortality prediction by heart failure. An intelligent computational predictive model based on machine learning has been introduced to identify and diagnose heart failure. Numerous performance indicators, including accuracy, recall, F1-score, precision, AUC, and Cohen’s Kappa statistic, are utilised to assess the proposed model’s usefulness and strength. The overall performance examination of the suggested methodology outperformed various state-of-the-art approaches in predicting patients’ deaths owing to heart failure.