Cardiovascular diseases remain the leading cause of death worldwide. Early detection and continuous monitoring by healthcare professionals are critical in reducing mortality rates. This study analyses various patient data to predict heart disease accurately. Key indicators such as age, gender, smoking habits, obesity, diet, physical activity levels, stress, chest pain type and duration, diastolic blood pressure, diabetes, troponin levels, and electrocardiogram (ECG) readings play a vital role in diagnosing heart conditions. We employ a diverse set of artificial intelligence techniques, including Naïve Bayes (NB), K-nearest neighbour (K-NN), logistic regression (LR), decision tree (DT), random forest (RF), support vector machine (SVM), and multilayer perceptron (MLP), to ensure a comprehensive analysis. This research introduces a cardiovascular disease detection system that explores a weighted combination of these seven machine-learning (ML) approaches to enhance prediction accuracy. The system is also validated using the Cleveland and Statlog datasets, two widely recognized open-access databases. Performance was assessed through 10-fold cross-validation, with the proposed method achieving an accuracy of 98.31%, a precision of 98.87%, a recall of 98.28%, and an F1-score of 98.58%, outperforming existing approaches.