From Cuffs to Code: Machine Learning in Non-Invasive Blood Pressure Monitoring

Blood pressure (BP) measurement in both acute care and outpatient settings is essential, as conditions like hypertension and hypotension are common and often asymptomatic until organ damage occurs. These conditions significantly increase the risk of morbidity and mortality but can be effectively managed through early detection and treatment. For decades, cuff-based devices have dominated non-invasive BP monitoring; however, they are often bulky, inconvenient, and limited to intermittent measurements. In recent years, machine learning (ML) and artificial intelligence (AI)-based approaches for BP estimation from non-invasive physiological signals-such as electrocardiography (ECG) and photoplethysmography (PPG)-have generated considerable interest. These innovations promise to enable continuous, cuff-less BP monitoring, expanding the reach of BP assessment into wearable devices and facilitating more dynamic, patient-centered care. This review provides a comprehensive overview of the evolution of non-invasive BP measurement technologies, with particular emphasis on emerging AI-driven methods and trends shaping the development of continuous and wearable solutions. While these technologies offer new opportunities for continuous monitoring and patient engagement, this review focuses on their conceptual and technological development rather than detailed performance evaluation or clinical validation.