Long-Term Hypertension Risk Prediction with ML Techniques in ELSA Database

• Published in: Learning and Intelligent Optimization Vol. 12931; pp. 113 - 120
• Main Authors: Dritsas, Elias, Fazakis, Nikos, Kocsis, Otilia, Fakotakis, Nikos, Moustakas, Konstantinos
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2021; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Hypertension; Risk prediction; Supervised learning
• ISBN: 3030921204; 9783030921200
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-92121-7_9

Hypertension is a leading risk factor for cardiovascular diseases (CVDs) which in their turn are among the main causes of death worldwide and public health concern, with heart diseases being the most prevalent ones. The early prediction is considered one of the most effective ways for hypertension control. Based on the English Longitudinal Study of Ageing (ELSA) [2], a large-scale database of ageing participants, a dataset is engineered to evaluate the long-term hypertension risk of men and women aged older than 50 years with Machine Learning (ML). We evaluated a series of ML prediction models concerning AUC, Sensitivity, Specificity and selected the stacking ensemble as the best performer. This work aims to identify individuals at risk and facilitate earlier intervention to prevent the future development of hypertension.