Abstract—A major global health concern that raises health risks considerably is hypertension. Improving early diagnosis and management of hypertension and improving patient outcomes represent the 2 benefits of utilizing Machine Learning (ML) algorithms for early detection. A lot of attention has been paid to them. This work tackles the important issue of hypertension identification by utilizing a sizable dataset from Kaggle that contains a range of physiological and demographic features. To accurately evaluate this dataset, the suggested model incorporates a number of ML classifiers, including Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Random Forest (RF), Decision Tree Classifier (DT), Artificial Neural Network (ANN) and Covering Number 2 (CN2) rule inducer, to investigate their prediction potential. Performance criteria such as accuracy, precision, sensitivity, specificity, and F1-score were used to assess each classifier’s effectiveness. According to the results, the GB approach had the highest accuracy (99.2%), followed by AdaBoost (96.4%). The 2 algorithms that performed exceptionally well were RF and CN2 rule inducers, which had respective accuracy rates of 93.8% and 93.5%. These results demonstrate the possibility of accurately predicting hypertension with state-of-the-art ML techniques, offering useful information to support healthcare providers in making knowledgeable decisions about patient care.
 
Keywords—artificial intelligence, classification, gradient boosting, hypertension, Kaggle, machine learning


Copyright © 2026 by the authors. This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).