Abstract
Hypertension remains the most prevalent modifiable risk factor for cardiovascular morbidity and mortality worldwide, yet rates of effective blood pressure control remain persistently suboptimal despite the availability of multiple therapeutic options. This gap reflects fundamental limitations of current care models, which rely on episodic measurements, population-based treatment algorithms, and incomplete representation of the biological, behavioral, and social complexity underlying blood pressure regulation. Artificial intelligence (AI) offers a transformative framework to address these challenges by enabling the integration of longitudinal, multimodal data and modeling nonlinear, dynamic relationships that are difficult to capture with conventional approaches. This systematic review synthesizes emerging evidence on the application of AI across the hypertension care continuum, including risk prediction, phenotyping, blood pressure measurement, wearable-based monitoring, clinical trial analysis, population health modeling, detection of secondary hypertension, behavioral and adherence interventions, and multi-omics-driven precision medicine. We highlight the methodological foundations required for clinically meaningful AI, emphasizing robust ground-truth definitions, external and temporal validation, interpretability, workflow integration, and equity-aware design. The review also examines the promise and limitations of natural language processing, cuffless blood pressure technologies, and AI-guided decision support systems, alongside ethical, regulatory, and implementation challenges. Collectively, current evidence suggests that AI has the potential to shift hypertension management from a reactive, threshold-based paradigm toward a more predictive, personalized, and patient-centered model. Realizing this potential will depend on rigorous validation, thoughtful implementation, and sustained alignment with clinical, ethical, and equity principles.