Lightweight Calibration-Based Blood Pressure Tracking from Photoplethysmography Features for Smart Devices: Accuracy, Model Size and Recalibration Interval
Diagnostics · 10.11.2026 · 16 (22) · 3713
DOI: 10.3390/diagnostics16223713 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 10.11.2026. Verfasst von Soojeong Lee und 2 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Kwangwoon University.
Abstract (Originalsprache)
Background/Objectives: Smart devices estimate blood pressure (BP) from photoplethysmography (PPG), but models trained on other people generalize poorly, and device constraints limit model size. This study compared calibration strategies and model sizes for PPG-based BP estimation.
Methods
We used 65 hand-crafted PPG features with MIMIC-BP (1295 training and 229 subject-disjoint test subjects, ten repeats) and 17 external VitalDB surgical cases. We compared calibration-free regressors, calibration with one to five cuffs, recalibration policies and calibration models of decreasing size.
Results
Without calibration, six regressors reached a systolic BP (SBP) mean absolute error (MAE) of 13.0–13.3 mmHg on unseen subjects, close to a constant predictor (14.2 mmHg). A delta model that predicts the change from the cuff reading reduced the SBP MAE to 11.8 mmHg with one cuff and 10.8 mmHg with five, but followed only 30–50% of large changes. With five calibration readings, the model achieved a pooled area under the curve (AUC) of 0.94 for new-onset SBP ≥160 mmHg on MIMIC-BP, but sensitivity was zero at an estimated-SBP threshold of 160 mmHg. Accuracy was governed by the recalibration interval: recalibration nominally every 15 min gave 10.3 mmHg on VitalDB, and event-triggered cuffs were not better than periodic ones. A 47 KB tree model lost 0.2 mmHg against a 1.5 MB reference.
Conclusions
For these data, calibration was required, the recalibration interval mattered more than model complexity, and a compact tree model was sufficient; on-device use requires further validation. Accuracy remained poor at blood-pressure extremes, and external validation in only 17 VitalDB cases remains preliminary.
Förderung
- Kwangwoon University
Zitieren
APA
Lee, S., Al-antari, M. A., & Lee, G. (2026). Lightweight Calibration-Based Blood Pressure Tracking from Photoplethysmography Features for Smart Devices: Accuracy, Model Size and Recalibration Interval. Diagnostics, 16(22), 3713. https://doi.org/10.3390/diagnostics16223713
Vancouver
Lee S, Al-antari MA, Lee G. Lightweight Calibration-Based Blood Pressure Tracking from Photoplethysmography Features for Smart Devices: Accuracy, Model Size and Recalibration Interval. Diagnostics. 2026;16(22):3713. doi:10.3390/diagnostics16223713
BibTeX
@article{Lee2026,
author = {Lee, Soojeong and Al-antari, Mugahed A. and Lee, Gangseong},
title = {Lightweight Calibration-Based Blood Pressure Tracking from Photoplethysmography Features for Smart Devices: Accuracy, Model Size and Recalibration Interval},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {22},
pages = {3713},
doi = {10.3390/diagnostics16223713}
}
EUVIMED