A multi-stage cuff-less continuous blood pressure estimation method for overcoming subject specificity

Cuff-less continuous blood pressure (BP) estimation is essential for hypertension prevention and management. However, subjects have differences in vascular characteristics, pre-ejection period, and dynamic physiological states, which leads to inter-class specificity of BP in different categories and individual specificity in the same category. This study proposes a multi-stage cuff-less continuous BP estimation method using photoplethysmography and electrocardiogram. (1) In the classification stage, a recursively coupled neural network capable of compensating for deep semantic expression is constructed to overcome the impact of inter-class specificity. Based on layer-wise aggregation of channel encoded information and embedded coordinate attention mechanisms, it captures spatial dependencies of multi-level features, thereby categorizing subjects into predefined classes. (2) In the BP estimation stage, a multi-operator dynamically adjusted neural network is proposed to address individual specificity. Inspired by the human brain’s multi-level and multi-perspective information processing mechanisms, it integrates multiple advanced operators to process information, deciphering the nonlinear relationship between real-time variations in blood volume, cardiac electrical activity, and BP. Simultaneously, it incorporates lightweight attention mechanism and cross-guidance strategy to adaptively adjust the responsiveness of different operators, thereby enhancing its dynamic adaptability. Under the inter-patient paradigm clinical test, mean absolute errors for mean arterial pressure, systolic blood pressure, and diastolic blood pressure reached 3.03±2.38 mmHg, 2.96±2.45 mmHg, and 2.74±2.21 mmHg respectively, meeting both the Association for the Advancement of Medical Instrumentation standards and British Hypertension Society Grade A criteria. This study demonstrates significant implications for overcoming subject specificity and achieving personalized BP management.