What does this research mean for the field?

The PP-Net deep learning framework accurately and simultaneously estimates diastolic blood pressure, systolic blood pressure, and heart rate from single-channel PPG signals without requiring manual feature extraction. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

April 30, 2020

PP-Net: A Deep Learning Framework for PPG-Based Blood Pressure and Heart Rate Estimation

Q: What is the clinical evidence from this study?

Study design: Other. Population: Critically ill subjects with CVD complications (n=1557). Intervention: PP-Net (Long-term Recurrent Convolutional Network) vs. Existing methods. Primary outcome: Normalized Mean Absolute Error (NMAE) for DBP, SBP, and HR estimation.

Key Result

PP-Net accurately estimated physiological parameters from single-channel PPG signals, achieving an average NMAE of 0.09 mmHg for DBP, 0.04 mmHg for SBP, and 0.046 bpm for HR in 1557 subjects.

Structured PICO

Does the PP-Net deep learning framework accurately estimate blood pressure and heart rate from single-channel PPG signals in critically ill subjects?

Population

1557 critically ill subjects from the MIMIC-II database, including those with CVD complications

Intervention

PP-Net, a deep learning framework using Long-term Recurrent Convolutional Network (LRCN) to estimate DBP, SBP, and HR from a single channel PPG signal

Comparator

Existing methods

Outcome

Estimation accuracy of Diastolic blood pressure (DBP), Systolic blood pressure (SBP), and Heart rate (HR) measured by Normalized Mean Absolute Error (NMAE)surrogate

The PP-Net deep learning framework provides highly accurate, simultaneous estimation of blood pressure and heart rate from a single-channel PPG signal, demonstrating potential for pervasive healthcare monitoring.

Abstract

This paper presents a deep learning model 'PP-Net' which is the first of its kind, having the capability to estimate the physiological parameters: Diastolic blood pressure (DBP), Systolic blood pressure (SBP), and Heart rate (HR) simultaneously from the same network using a single channel PPG signal. The proposed model is designed by exploiting the deep learning framework of Long-term Recurrent Convolutional Network (LRCN), exhibiting inherent ability of feature extraction, thereby, eliminating the cost effective steps of feature selection and extraction, making less-complex for deployment on resource constrained platforms such as mobile platforms. The performance demonstration of the PP-Net is done on a larger and publically available MIMIC-II database. We achieved an average NMAE of 0.09 (DBP) and 0.04 (SBP) mmHg for BP, and 0.046 bpm for HR estimation on total population of 1557 critically ill subjects. The accurate estimation of HR and BP on a larger population compared to the existing methods, demonstrated the effectiveness of our proposed deep learning framework. The accurate evaluation on a huge population with CVD complications, validates the robustness of the proposed framework in pervasive healthcare monitoring especially cardiac and stroke rehabilitation monitoring.

Bookmark

Cite This Study

Panwar et al. (Thu,) conducted a other in Critically ill subjects with CVD complications (n=1,557). PP-Net (Long-term Recurrent Convolutional Network) vs. Existing methods was evaluated on Normalized Mean Absolute Error (NMAE) for DBP, SBP, and HR estimation. PP-Net accurately estimated physiological parameters from single-channel PPG signals, achieving an average NMAE of 0.09 mmHg for DBP, 0.04 mmHg for SBP, and 0.046 bpm for HR in 1557 subjects.

synapsesocial.com/papers/6a19d211443d3ecd7cdf0c72 https://doi.org/https://doi.org/10.1109/jsen.2020.2990864

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

Bookmark