Proposal for a Model for Predicting High Blood Pressure Based on Clinical Data Using Machine Learning Techniques

Garay A.; Ortiz A.; Ramos-Flores C.; Ticona W. · Lecture Notes in Networks and Systems (2026) · DOI: 10.1007/978-3-032-20752-4_13

Resumen

High blood pressure is one of the leading causes of morbidity and mortality worldwide. Its incidence has been increasing because of various factors, such as lifestyle, late diagnosis, or lack of timely treatment. Artificial intelligence technologies, especially Machine Learning algorithms, have gained relevance in the field of medicine by enabling the creation of predictive models that facilitate early diagnosis and appropriate care. This study proposes a hypertension prediction model based on Machine Learning classification techniques. The methodology used consisted of four phases: Acquisition of the clinical dataset; Preprocessing (application of SMOTE and standardization); Model implementation (Random Forest, XGBoost, CatBoost, MLP, logistic regression, and SVC); and Hyperparameter tuning. The model that obtained the best results was XGBoost, achieving 91% accuracy, 89% precision, 91% recall, 90% F1 score, and 0.96 AUC. In conclusion, the results demonstrate that the appropriate use of machine learning algorithms can effectively predict the risk of hypertension from clinical data, representing a promising tool to support timely medical diagnosis and improve cardiovascular disease prevention. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.

Instituciones: Universidad ESAN; Universidad Tecnológica del Perú