Key result
ST-ResNet outperforms competing deep learning models in estimating BP from single-channel PPGs.
Why the study?
Deep learning models have been proposed to estimate blood pressure from photoplethysmograms, but non-uniform datasets and data-splitting methods make fair comparison difficult.
Which deep learning model performs best in estimating continuous blood pressure from single-channel photoplethysmograms?
Which deep learning model performs best in estimating continuous blood pressure from single-channel photoplethysmograms?
ST-ResNet is the most effective among nine tested deep learning models for non-invasive continuous blood pressure estimation using PPGs.
Answers are grounded in this paper and cite their sources.
ST-ResNet may advance PPG-based BP estimation; hypothesis-generating pending prospective validation before any clinical use.
Blood pressure (BP) is a vital parameter in medical treatment and diagnosis, and as a non-invasive method to measure BP, some deep learning models have been proposed to estimate BP from photoplethysmograms (PPGs). However, the datasets and the method of dividing them into training and testing subsets are not uniform, making it difficult to compare them fairly. In this study, we compared the performance of nine deep learning models for estimating systolic and diastolic BP using PPGs. We used PulseDB, which has "calibration-based subset" and "calibration-free subset" as test subsets. The calibration-based subset has the same subject’s data in the training subset, and the calibration-free subset does not have the same subject’s data in the training subset. The results showed that ST-ResNet performed the best, and it is important to evaluate the models using both calibration-based and calibration-free subsets, and to prevent the overfitting by using the weight decay.
No takes yet. Share an insight, caveat, or question.
Yamamoto et al. (2025) studied Blood pressure estimation. Nine deep learning models (including ST-ResNet) vs. Each other was evaluated on Performance in estimating systolic and diastolic BP using PPGs. ST-ResNet performed the best among nine deep learning models for estimating systolic and diastolic blood pressure from single-channel photoplethysmograms using the PulseDB dataset.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: