Bubonic plague remains a significant zoonotic disease despite advances in public health interventions and disease control programs. The disease continues to occur in several endemic regions and presents substantial challenges to healthcare systems due to delayed diagnosis and limited predictive surveillance capabilities. This study developed and evaluated machine learning models for predicting bubonic plague prevalence and facilitating early diagnosis using epidemiological, environmental, demographic, and clinical variables. A quantitative predictive research design was adopted utilizing an integrated dataset comprising 5,000 observations obtained from epidemiological repositories, environmental databases, and healthcare records. Four supervised machine learning algorithms, namely Logistic Regression, Random Forest, Support Vector Machine (SVM), and Artificial Neural Network (ANN), were implemented and evaluated using Accuracy, Precision, Recall, F1-Score, and ROC-AUC metrics. Results revealed that Random Forest achieved the highest predictive performance with an accuracy of 92.7%, precision of 91.8%, recall of 92.3%, F1-score of 92.0%, and ROC-AUC of 0.964. Feature importance analysis identified swollen lymph nodes, fever, rodent exposure, flea exposure, and climatic variables as the most influential predictors. The findings demonstrate the effectiveness of machine learning in supporting disease surveillance, outbreak forecasting, and clinical decision-making. The study concludes that intelligent predictive systems can significantly strengthen public health preparedness and facilitate early intervention strategies for plague control.