Artificial Intelligence-Enhanced Wearable Blood Pressure Monitoring in Resource-Limited Settings: A Co-Design of Sensors, Model, and Deployment

Integrative Co-Design Framework: We synthesize current advances in sensing, models, accuracy/reliability assessment, and hardware into a sensor–model–deployment–assessment framework that organizes evidence and design trade-offs for cuffless blood pressure monitoring. The framework seeks to balance precision and efficiency by jointly considering low-power edge AI, streamlined sensor architectures, and adaptive computational models, providing a structured basis for reproducible and clinically meaningful wearable solutions. Pathways to Clinical Translation: We critically assess barriers to real-world deployment, offering actionable strategies to bridge the translational gap between laboratory innovations and scalable implementation in low-resource regions with minimal healthcare infrastructure. Interdisciplinary Synthesis: By integrating cutting-edge advances in materials science, digital health, and embedded AI, we provide evidence-based recommendations to empower biomedical researchers, engineers, and data scientists in advancing equitable diagnostic solutions. © The Author(s) 2026.