Hypertension is a prevalent chronic condition and a leading risk factor for cardiovascular diseases globally. According to the results of the National Health and Nutrition Survey (ENSANUT) conducted in 2022, it was estimated that approximately 30% of adults were living with hypertension, and 43% of them were unaware of their diagnosis. Recently, the use of artificial intelligence (AI) and machine learning (ML) tools has increased significantly in the healthcare sector due to their ability to identify complex patterns and accurate predictions in medical data. In Mexico, the application of AI and ML approaches to hypertension risk prediction remains very limited. In this study, we compared four ML models, Naive Bayes, Support Vector Machine, Artificial Neural Networks (ANN) and Extreme Gradient Boosting (XGBoost), to classify risk or nor risk of hypertension using a dataset built from ENSANUT records. A key contribution of this work was the inclusion of clinical, biometric, and lifestyle variables, which enhanced the predictive performance of the models. The results demonstrate that XGBoost and ANN outperformed traditional models, achieving F1-scores of 98.19% and 93.9%, respectively, and surpassing the performance reported in prior studies. These results demonstrate the strong potential of AI-driven models to support clinicians in the early identification and management of hypertension.