Why the study?
Non-invasive blood pressure estimation using photoplethysmography is of significant interest due to its potential extensive application in wearable sensors.
Proposes a novel deep learning and image denoising-based algorithm for non-invasive blood pressure estimation and cardiovascular risk classification using PPG signals.
Answers are grounded in this paper and cite their sources.
PPG-based BP estimation needs external validation; leaves open its role in wearable risk stratification.
The non-invasive Blood Pressure Estimation (BPE) utilizing the technology of photoplethysmography (PPG) gains significant interest because PPG could be extensively employed to wearable sensors. Here, a method for estimating Systolic Blood pressure (SBP), as well as Diastolic Blood pressure (DBP), grounded only on a PPG signal utilizing the Image Denoising Algorithms (IDA) algorithms is proposed. Also, a classification methodology to execute the risk analysis (RA) of the BP patients utilizing Moore–Penrose Pseudo-Inverse Matrix-Deep Learning Neural Network (MPPIW-DLNN) is proposed. The preprocessing is then done on the input PPG signal utilizing the Modified–Chebyshev Filter (CF) to eradicate the unwanted information existent in the signal. Afterward, the BPE is done utilizing IDA, which categorizes those components into (i) SBP and (ii) DBP. The MPPIW-DLNN provides the results of four sorts of risk classes like (i) stroke, (ii) heart failure (HF), (iii) heart attack (HA), and (iv) aneurysm identified from the inputted PPG signal.
No takes yet. Share an insight, caveat, or question.
Thakkar et al. (2022) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: