In recent years, advancements in artificial intelligence and big data have opened up new possibilities for healthcare and medicine. However, there is a need for further research to ensure the accuracy and reliability of predictive models in this domain. This study aims to bridge this gap by exploring the application of machine learning algorithms to predict diseases using demographic information and laboratory results. The primary objective is to develop a highly accurate model that can diagnose illnesses and provide personalized healthcare approaches. To achieve this objective, an extensive range of data sources was utilized, including the EMRBots dataset, which serves as the foundation for training and evaluation. In addition to EMRBots, two specialized repositories focusing on cardiac disease detection were incorporated into the research. These datasets provided valuable insights into cardiovascular health and further enhanced the accuracy of the predictive model. Throughout the study, a comprehensive methodology was implemented. Data preprocessing techniques were employed to clean and format the datasets, ensuring optimal quality and consistency. Various machine learning algorithms, supported by the powerful data analysis library Pandas, the renowned machine learning library scikit-learn, and the versatile numerical computing library NumPy, were utilized to train and fine-tune the predictive model. The performance of the developed system was thoroughly evaluated using appropriate metrics, assessing its accuracy, precision, recall, and F1 score. By integrating various datasets, employing cutting-edge technologies, and focusing on cardiac disease detection, this study offers valuable insights into the development of a robust and accurate machine learning system for disease prediction.