ChatPPG.
Join free

PaperarXiv:2610.39394

Evaluating Generalization and Long-Term Stability of Smartwatch-Based Cuffless Blood Pressure Monitoring

Venue listed2026Added Oct 30, 2026

  • HH
  • XE
  • XL
  • ST
  • GZ
  • XY
  • HL
  • YL
  • +1

Authors: Hongda Huang, Xiao Peng (equal), Xiaoyu Li, Shuailong Tang, Guangpu Zhu, Xiajiao Yang, Hongwei Li, Yelei Li, Yali Zheng (corresponding)

IEEE EMBS BHI 2026 (accepted); arXiv eess.SP, 2026-10-29

PDF (opens in a new tab) arXiv2610.39394 (opens in a new tab) Publisher (opens in a new tab) Cite
CC BY-NC-SA 4.0

TL;DR

Data: Aurora-BP after QC (9,433 recordings, 626 participants) and a private long-term home set: single-channel wrist infrared PPG from OPPO smartwatches at 250 Hz, Omron cuff reference, 60 s PPG per reading, ≥3 readings in each of morning/noon/evening, several days to ~40 days per participant, 13 participants, 24,910 samples.

  • Form factor: wrist
Caveats
  • QC subset and single baseline reading differ from PC-AVCT (3 readings, 653) and PulseAnchor; no code.

Abstract

Smartwatch-based cuffless blood pressure (BP) monitoring is a promising low-burden solution for long-term cardiovascular management, but practical deployment remains constrained by model complexity, uncertain cross-dataset generalization, and insufficient evidence on long-term tracking stability. This study presents an efficient Signal-Context Gated Fusion Network (SCGBPNet) for cuffless BP estimation from photoplethysmography (PPG) signals. SCGBPNet integrates signal-level representations through self-attention and further incorporates subject-specific contextual information via a compact gated fusion module. On Aurora-BP, SCGBPNet achieved SBP/DBP mean absolute errors (MAEs) of 7.08/4.90 mmHg, compared with 6.44/4.89 mmHg under within-dataset validation on the private smartwatch dataset, indicating a modest within-dataset discrepancy. Cross-dataset transfer from Aurora-BP to the smartwatch dataset increased the MAEs to 8.98/6.47 mmHg, demonstrating substantial cross-dataset degradation. For long-term stability, the proposed method showed low week-to-week performance variation and a low daily decay rate, indicating good stability over a follow-up period of more than one month. Nevertheless, estimation accuracy deteriorated when BP deviated substantially from an individual's baseline. These findings indicate that favorable aggregate MAE alone should not be interpreted as evidence of deployment-ready performance. More systematic and stratified evaluation across dataset settings, BP ranges, and baseline-deviation levels is needed to assess the practical reliability of smartwatch-based cuffless BP monitoring.

Verbatim from arXiv (opens in a new tab) · arXiv metadata (abstracts are released under CC0)

Results on ChatPPG leaderboards · 2

All leaderboards
LeaderboardMethodResultRank
aurora-bp MAE (mmHg)Cuffless blood pressure estimationSCGBPNetCaveat: QC subset and single baseline reading differ from PC-AVCT (3 readings, 653) and PulseAnchor; no code.7.08MAE (mmHg), lower is better#1 of 3
oppo-smartwatch-private-13 MAE (mmHg)Cuffless blood pressure estimationEvaluating Generalization and Long-Term…6.44MAE (mmHg), lower is better#1 of 1

2 rows are credited to this paper. Ranks apply within each leaderboard only, as reported by the source.

Tasks & signals

Tasks

Cuffless blood pressure estimationBlood pressure

Signals

PPG

Devices

Maxim MAX30101 (Aurora-BP optical unit)

Keywords

Cuffless BPWristInfrared PPGCross DatasetLong Term StabilityRecalibration IntervalBaseline CalibrationAurora BP

How it works

How Method works: Setup → Method → TargetSetup: Signals (PPG); Wavelengths (IR (private OPPO set; nm not stated)); Form factor (wrist). Method: Method. Target: Blood pressure.SetupSignals: PPGSignalsPPGWavelengths: IR (private OPPO set; nm not stated)WavelengthsIR (private OPPO set; nm not stated)Form factor: wristForm factorwristMethodMethodTargetBlood pressureBlood pressure
Wavelengths
IR (private OPPO set; nm not stated)

Cite this paper

Cite this paper with the fields recorded here. Check it against the publisher before submitting.

Huang, H., Peng, X., Li, X., Tang, S., Zhu, G., Yang, X., Li, H., Li, Y., & Zheng, Y. (2026). Evaluating Generalization and Long-Term Stability of Smartwatch-Based Cuffless Blood Pressure Monitoring. IEEE EMBS BHI 2026. https://doi.org/10.48550/arXiv.2610.39394
Huang, Hongda, Xiao Peng, Xiaoyu Li, Shuailong Tang, Guangpu Zhu, Xiajiao Yang, Hongwei Li, Yelei Li, and Yali Zheng. 2026. "Evaluating Generalization and Long-Term Stability of Smartwatch-Based Cuffless Blood Pressure Monitoring." IEEE EMBS BHI 2026. https://doi.org/10.48550/arXiv.2610.39394.
Huang, H., Peng, X., Li, X., Tang, S., Zhu, G., Yang, X., Li, H., Li, Y. and Zheng, Y. (2026) 'Evaluating Generalization and Long-Term Stability of Smartwatch-Based Cuffless Blood Pressure Monitoring', IEEE EMBS BHI 2026. doi: 10.48550/arXiv.2610.39394.
Huang, Hongda, et al. "Evaluating Generalization and Long-Term Stability of Smartwatch-Based Cuffless Blood Pressure Monitoring." IEEE EMBS BHI 2026, 2026. https://doi.org/10.48550/arXiv.2610.39394.
H. Huang et al., "Evaluating Generalization and Long-Term Stability of Smartwatch-Based Cuffless Blood Pressure Monitoring," IEEE EMBS BHI 2026, 2026, doi: 10.48550/arXiv.2610.39394.
@article{huang2026evaluating,
  title         = {{Evaluating Generalization and Long-Term Stability of Smartwatch-Based Cuffless Blood Pressure Monitoring}},
  author        = {Huang, Hongda and Peng, Xiao and Li, Xiaoyu and Tang, Shuailong and Zhu, Guangpu and Yang, Xiajiao and Li, Hongwei and Li, Yelei and Zheng, Yali},
  year          = {2026},
  journal       = {IEEE EMBS BHI 2026},
  doi           = {10.48550/arXiv.2610.39394},
  eprint        = {2610.39394},
  archivePrefix = {arXiv}
}

Added to the ChatPPG research hub