Paperdoi:10.20944/preprints202610.1859.v1
Cross-Dataset Evaluation of Interpretable Photoplethysmography Features for Blood Pressure Category Classification
Preprints.org 202610.1859 v1 (submitted 2026-10-19, posted 2026-10-20; not peer-reviewed)
Licence: CC BY (OpenAlex)
TL;DR
No summary in the hub record yet.
- Form factor: any
- Demographics carry much of the signal; cross-cohort source-only 0.556–0.696.
Abstract
Photoplethysmography (PPG) provides waveform features for blood pressure (BP) category classification, but performance may vary across recording conditions. We evaluated a framework incorporating Step-Morphological Decomposition (SMD) on Aurora-BP, PPG-BP, PulseDB-Vital and the Synchronized Signals from Wearable Cardiovascular Monitoring Sensors dataset (SWCS). Signals were processed at 125 Hz. Conventional and neural classifiers were compared using subject-grouped evaluation, feature-family ablation, Shapley additive explanations (SHAP) and cross-cohort adaptation. On Aurora-BP, XGBoost achieved a mean three-class macro one-versus-rest area under the receiver operating characteristic curve (AUC) of 0.778 ± 0.011 across five folds. Subject-aggregated binary prediction achieved AUC 0.841. Source-only AUCs were 0.662 ± 0.096 on PPG-BP, 0.556 ± 0.049 on PulseDB-Vital and 0.696 ± 0.083 on SWCS. A restricted PPG-only pipeline achieved AUC 0.704. Removing the SMD feature family changed AUC from 0.778 to 0.776. Period morphology had the largest summed SHAP attribution, whereas demographic predictors had the largest average attribution per feature. Adaptation effects varied across cohorts and available target data. These retrospective results characterize the performance and limitations of the evaluated feature framework. Prospective clinical screening performance was not evaluated.
Verbatim from the publisher's DOI record (opens in a new tab) · Publisher licence: http://creativecommons.org/licenses/by/4.0
Results on ChatPPG leaderboards · 1
All leaderboards| Leaderboard | Method | Result | Rank |
|---|---|---|---|
| aurora-bp AUROCCuffless blood pressure estimation | XGBoost on interpretable PPG + demographic featuCaveat: Demographics carry much of the signal; cross-cohort source-only 0.556–0.696. | 0.778AUROC, higher is better | #1 of 1 |
1 row is credited to this paper. Ranks apply within each leaderboard only, as reported by the source.
Tasks & signals
Tasks
Signals
Keywords
Datasets
How it works
Cite this paper
APA
Msokar, S., & Davydov, R. (2026). Cross-Dataset Evaluation of Interpretable Photoplethysmography Features for Blood Pressure Category Classification. Preprints.org 202610.1859 v1. https://doi.org/10.20944/preprints202610.1859.v1
BibTeX
@article{msokar2026crossdataset,
title = {{Cross-Dataset Evaluation of Interpretable Photoplethysmography Features for Blood Pressure Category Classification}},
author = {Msokar, Souhair and Davydov, Roman},
year = {2026},
journal = {Preprints.org 202610.1859 v1},
doi = {10.20944/preprints202610.1859.v1}
}Built from the hub record. Check it against the publisher before submitting.
Added to the ChatPPG research hub