Artificial intelligence (AI) is transforming healthcare, notably in predictive diagnosis, because of the increased availability of health data and rapid advances in machine learning. However, AI applications in healthcare encounter issues such as model transparency, interpretability and potential biases, all of which are crucial in building confidence among medical practitioners. Explainable Artificial Intelligence (XAI) addresses these concerns, promoting greater adoption of AI technologies in healthcare. This study introduces a Heart Disease Prediction System that predicts the risk of heart disease based on important health variables using machine learning models such as Random Forest, K-Nearest Neighbours (KNN), Decision Tree and XGBoost. The system uses data preprocessing, built on a patient record dataset, feature scaling and model training to ensure prediction accuracy. The application's user-friendly interface, designed using Streamlit, provides for risk assessments by allowing users to enter data such as age, gender, chest pain kind, blood pressure and cholesterol levels. Our study illustrates the need for credible, interpretable healthcare models, showing how predictive analytics can help with early diagnosis and treatment, ultimately leading to better patient outcomes in heart disease treatment.