Camera-based Blood Pressure Monitoring based on Multi-site and Multi-wavelength Pulse Transit Time Features

Yukai Huang1,2; Dongmin Huang1; Jia Huang3; Guowei Wang3; Liping Pan3; Hongzhou Lu3; Min He2,4; Wenjin Wang1

2024

10.1109/TIM.2024.3457944

IEEE Transactions on Instrumentation and Measurement   影响因子和分区

1557-9662

Pulse transit time (PTT) is a promising physiological feature for camera-based blood pressure (BP) monitoring. Existing approaches of PTT-based camera-BP estimation can be categorized into multi-site PTT (MS-PTT) based and multi-wavelength PTT (MV-PTT) based, former measures PTT between arteries at different skin locations while latter measures PTT between arteries and arterioles at different skin layers. These two types of PTT features reflect different vascular properties and thus their fusion can provide richer information for more accurate BP calibration. We therefore propose a novel multi-dimensional PTT (MD-PTT) feature set that integrates MS-PTT and MV-PTT with spatial anatomical constraints for camera-BP monitoring. An end-to-end video processing framework is developed for robust MD-PTT feature extraction and BP calibration. The proposed method was validated in both the lab setting and hospital Intensive Care Unit (ICU) setting. The lab experiment shows that MD-PTT reduced the mean absolute error (MAE) of systolic BP, diastolic BP, and mean BP by at most 1.81 mmHg, 1.93 mmHg, 1.61mmHg against MV-PTT, and by at most 2.54 mmHg, 2.46 mmHg, 2.92mmHg against MS-PTT. The clinical trial in ICU shows that the MAE of MD-PTT with generalized modeling on three types of BP were 6.49 mmHg, 6.82 mmHg, 5.98 mmHg, with personalized modeling were 4.78 mmHg, 5.52 mmHg, 4.52 mmHg, respectively. The results were in the acceptance range of the British Hypertension Society standards. The clinical evaluation shows that the novel MD-PTT feature may enable accurate BP estimation for camera-based patient monitoring.

第一

1.Department of Biomedical Engineering, Southern University of Science and Technology, China
2.Hangzhou Institute of Medicine (HIM), Chinese Academy of Sciences, Hangzhou, Zhejiang, China
3.The Third People’s Hospital of Shenzhen, China
4.Key Laboratory of Head & Neck Cancer Translational Research of Zhejiang Province, Zhejiang Cancer Hospital, China

Yukai Huang,Dongmin Huang,Jia Huang,et al. Camera-based Blood Pressure Monitoring based on Multi-site and Multi-wavelength Pulse Transit Time Features[J]. IEEE Transactions on Instrumentation and Measurement,2024,PP(99).

Yukai Huang.,Dongmin Huang.,Jia Huang.,Guowei Wang.,Liping Pan.,...&Wenjin Wang.(2024).Camera-based Blood Pressure Monitoring based on Multi-site and Multi-wavelength Pulse Transit Time Features.IEEE Transactions on Instrumentation and Measurement,PP(99).

Yukai Huang,et al."Camera-based Blood Pressure Monitoring based on Multi-site and Multi-wavelength Pulse Transit Time Features".IEEE Transactions on Instrumentation and Measurement PP.99(2024).