THE FUTURE OF AI IN HYPERTENSION

Objective: Hypertension, affecting over 1.28 billion adults globally, remains a major health challenge. Advances in wearable technology, particularly photoplethysmographs (PPG), combined with AI algorithms like machine learning (ML) and deep learning (DL), show promise for more accurate, continuous BP monitoring, and improved hypertension prediction and diagnosis. This review explores the potential of AI to transform hypertension management through better BP measurement and early detection of hypertension development. Design and method: This review examines the role of artificial intelligence (AI) in blood pressure (BP) measurement, hypertension (HTN) prediction, and diagnosis, focusing on wearable devices and AI algorithms. A systematic search was conducted on PubMed for studies from 2015 to 2025 using relevant keywords. Eligible studies were selected based on AI’s application in BP measurement or HTN management, particularly involving wearable devices like smartwatches. With 2,068 articles on PubMed related to AI in BP measurement and hypertension, the review prioritizes studies representing the current state of the field. Studies meeting specific inclusion criteria were chosen, including those involving AI algorithms for BP measurement or HTN prediction, clinical relevance, and high-quality methodologies. The review focuses on trials, observational studies, and research with large sample sizes. The selection process filtered by keywords, review articles, clinical trials, and citation rates to ensure quality and relevance. Results: AI-based approaches in BP measurement and HTN prediction have made significant strides, particularly with wearable devices like smartwatches using PPG. Machine learning (ML) and deep learning (DL) algorithms enhanced BP measurement accuracy and HTN risk prediction. These devices offer continuous, real-time BP monitoring as an alternative to traditional methods. However, concerns about study heterogeneity and data quality need to be addressed, and future research should focus on large-scale clinical trials to confirm the clinical applicability of AI in hypertension management. Conclusions: AI-driven wearable devices, especially those using PPG and machine learning, have the potential to revolutionize hypertension management. Future studies are needed to confirm their accuracy and clinical utility across diverse populations.