Cuffless Blood Pressure Estimation from Six Wearable Sensor Modalities in Multi-Motion-State Scenarios

2025-12-01

AI Summary

To address the significant accuracy degradation of cuffless continuous blood pressure (BP) monitoring under diverse physical activities, this paper proposes the first wearable multimodal framework integrating electrocardiogram (ECG), six-channel photoplethysmography (PPG), contact pressure, skin temperature, and inertial measurement unit (IMU) data (3-axis acceleration and angular velocity). We introduce cross-modal contrastive learning to achieve semantic alignment across heterogeneous physiological signals and design a lightweight branched encoder coupled with a Mixture-of-Experts (MoE) regression head to adaptively model BP–signal mapping under varying motion states. Evaluated on a public benchmark dataset, our method achieves mean absolute errors of 3.60 mmHg for systolic BP and 3.01 mmHg for diastolic BP—meeting stringent clinical standards (BHS Grade A and ANSI/AAMI SP10). This represents a substantial improvement in robustness and clinical applicability during dynamic, real-world activities.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Multi-modal Vision
• Machine Learning: Multimodal Learning

Application Category

• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Security and Privacy: Large-scale security measurements
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Cardiovascular disease (CVD) is a leading cause of morbidity and mortality worldwide, and sustained hypertension is an often silent risk factor, making cuffless continuous blood pressure (BP) monitoring with wearable devices important for early screening and long-term management. Most existing cuffless BP estimation methods use only photoplethysmography (PPG) and electrocardiography (ECG) signals, alone or in combination. These models are typically developed under resting or quasi-static conditions and struggle to maintain robust accuracy in multi-motion-state scenarios. In this study, we propose a six-modal BP estimation framework that jointly leverages ECG, multi-channel PPG, attachment pressure, sensor temperature, and triaxial acceleration and angular velocity. Each modality is processed by a lightweight branch encoder, contrastive learning enforces cross-modal semantic alignment, and a mixture-of-experts (MoE) regression head adaptively maps the fused features to BP across motion states. Comprehensive experiments on the public Pulse Transit Time PPG Dataset, which includes running, walking, and sitting data from 22 subjects, show that the proposed method achieves mean absolute errors (MAE) of 3.60 mmHg for systolic BP (SBP) and 3.01 mmHg for diastolic BP (DBP). From a clinical perspective, it attains Grade A for SBP, DBP, and mean arterial pressure (MAP) according to the British Hypertension Society (BHS) protocol and meets the numerical criteria of the Association for the Advancement of Medical Instrumentation (AAMI) standard for mean error (ME) and standard deviation of error (SDE).

Problem

• Estimates blood pressure without a cuff using multiple wearable sensors.
• Addresses accuracy loss in dynamic, multi-motion scenarios like running.
• Integrates six sensor types for robust, continuous BP monitoring.

Innovation

• Uses six sensor modalities including ECG and multi-channel PPG
• Employs contrastive learning for cross-modal semantic alignment
• Applies mixture-of-experts regression to adapt across motion states