Does a non-contact BCG-based system with deep learning accurately estimate heart rate, respiration rate, and posture compared to an FDA-approved device?
A novel non-contact BCG-based system using deep learning provides highly accurate estimation of heart rate, respiration rate, and posture compared to standard FDA-approved devices.
The study introduces an innovative approach for efficient vital signs monitoring in acupuncture by combining multi-channel ballistocardiogram (BCG) signals and multi-task learning, taking advantage of the polyvinylidene fluoride (PVDF) film sensor and deep neural networks. The proposed system utilizes non-contact under-mattress BCG signals and deep learning for heart rate (HR), respiration rate (RR) estimation and lying posture detection. A custom-designed data-logger captures the signal from a BCG sensor located under the patient's back for data acquisition, and integrates Gated Recurrent Unit (GRU) and Multi-head Self-Attention (MHSA) deep learning mechanisms for efficient HR, RR estimation and posture classification. In experiments with 25 participants, the proposed method achieved 98.7% accuracy for activity recognition and 97.6% for lying posture classification. In HR and RR estimation, the best case of mean absolute error (MAE) for HR achieves 0.77 beats per minute (bpm) in the right lateral posture, while the best value of MAE for RR is 0.43 breaths per minute (brpm) in the seated posture, compared to an FDA-approved device. The results demonstrate the high performance of multi-task learning for vital signs estimation and posture classification with our BCG-based system. This work establishes an innovative and practical pathway for medical assistance tools in non-contact monitoring and management.
Vo et al. (Sat,) studied this question.