Key result
Deep learning model estimates systolic blood pressure via IPPG within ~5 mmHg error.
Why the study?
The study was conducted to achieve accurate and convenient monitoring of human blood pressure using non-contact imaging photoplethysmography under ambient light.
Does a multi-stage deep learning model based on IPPG signals accurately measure blood pressure in healthy adults?
Does a multi-stage deep learning model based on IPPG signals accurately measure blood pressure in healthy adults?
This camera-based IPPG signal acquisition system and deep learning model provides a non-contact method to accurately estimate blood pressure that conforms to BHS and AAMI international standards.
Offers non-contact BP estimation meeting standards in healthy adults; hypothesis-generating pending prospective validation in clinical populations.
In this paper, a multi-stage deep learning blood pressure prediction model based on imaging photoplethysmography (IPPG) signals is proposed to achieve accurate and convenient monitoring of human blood pressure. A camera-based non-contact human IPPG signal acquisition system is designed. The system can perform experimental acquisition under ambient light, effectively reducing the cost of non-contact pulse wave signal acquisition while simplifying the operation process. The first open-source dataset IPPG-BP for IPPG signal and blood pressure data is constructed by this system, and a multi-stage blood pressure estimation model combining a convolutional neural network and bidirectional gated recurrent neural network is designed. The results of the model conform to both BHS and AAMI international standards. Compared with other blood pressure estimation methods, the multi-stage model automatically extracts features through a deep learning network and combines different morphological features of diastolic and systolic waveforms, which reduces the workload while improving accuracy.
No takes yet. Share an insight, caveat, or question.
Cheng et al. (2023) studied this question. Multi-stage CNN and BiGRU deep learning blood pressure estimation model based on IPPG signals vs. Reference blood pressure measured by commercial sphygmomanometer (Yuyue YE670A) was evaluated on Mean absolute error (MAE) of systolic and diastolic blood pressure. The multi-stage deep learning model based on IPPG signals achieved a mean absolute error of 5.33 mmHg for systolic blood pressure and 3.92 mmHg for diastolic blood pressure.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: