EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Nocturnal Blood Pressure Estimation from Sleep Plethysmography Using Machine Learning

Gizem Yilmaz iD, Xingyu Lyu, Ju Lynn Ong iD, Lieng Hsi Ling, Thomas Penzel iD, B T Thomas Yeo, Michael W L Chee iD

Sensors · 16.09.2023 · 23 (18) · 7931

DOI: 10.3390/s23187931 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Sensors, online erschienen am 16.09.2023. Verfasst von Gizem Yilmaz und 6 weiteren Autor:innen. Beteiligte Einrichtung: Centre for Sleep and Cognition, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 117549, Singapore. Hauptthemen laut MEDLINE: Blood Pressure Monitoring, Ambulatory. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 47 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIMH NIH HHS, National Medical Research Council Singapore, NUS Yong Loo Lin School of Medicine.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Elevated nocturnal blood pressure (BP) is a risk factor for cardiovascular disease (CVD) and mortality. Cuffless BP assessment aided by machine learning could be a desirable alternative to traditional cuff-based methods for monitoring BP during sleep. We describe a machine-learning-based algorithm for predicting nocturnal BP using single-channel fingertip plethysmography (PPG) in healthy adults.

Methods

Sixty-eight healthy adults with no apparent sleep or CVD (53% male), with a median (IQR) age of 29 (23–46 years), underwent overnight polysomnography (PSG) with fingertip PPG and ambulatory blood pressure monitoring (ABPM). Features based on pulse morphology were extracted from the PPG waveforms. Random forest models were used to predict night-time systolic blood pressure (SBP) and diastolic blood pressure (DBP).

Results

Our model achieved the highest out-of-sample performance with a window length of 7 s across window lengths explored (60 s, 30 s, 15 s, 7 s, and 3 s). The mean absolute error (MAE ± STD) was 5.72 ± 4.51 mmHg for SBP and 4.52 ± 3.60 mmHg for DBP. Similarly, the root mean square error (RMSE ± STD) was 6.47 ± 1.88 mmHg for SBP and 4.62 ± 1.17 mmHg for DBP. The mean correlation coefficient between measured and predicted values was 0.87 for SBP and 0.86 for DBP. Based on Shapley additive explanation (SHAP) values, the most important PPG waveform feature was the stiffness index, a marker that reflects the change in arterial stiffness.

Conclusion

Our results highlight the potential of machine learning-based nocturnal BP prediction using single-channel fingertip PPG in healthy adults. The accuracy of the predictions demonstrated that our cuffless method was able to capture the dynamic and complex relationship between PPG waveform characteristics and BP during sleep, which may provide a scalable, convenient, economical, and non-invasive means to continuously monitor blood pressure.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Blood Pressure Monitoring, AmbulatoryAdultFemaleHumansMaleMiddle AgedBlood PressureCardiovascular DiseasesHypertensionMachine LearningPlethysmographySleepYoung Adult

Stichwörter der Autor:innen

blood pressure estimationcardiovascular healthcuffless blood pressure measurementnocturnal blood pressurephotoplethysmographysleep

Autor:innen und Institutionen

  • Centre for Sleep and Cognition, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 117549, Singapore.
  • Centre for Translational Magnetic Resonance Research (TMR), Yong Loo Lin School of Medicine, National University of Singapore, Singapore 117549, Singapore.
  • Department of Cardiology, National University Heart Centre Singapore, Singapore 119074, Singapore.
  • Department of Medicine, Yong Loo Lin School of Medicine, National University of Singapore, Singapore 117549, Singapore.
  • Interdisciplinary Center of Sleep Medicine, Charité-Universitätsmedizin Berlin, 10117 Berlin, Germany.
  • Department of Electrical and Computer Engineering, National University of Singapore, Singapore 117549, Singapore.

ORCID-Profile: Gizem Yilmaz, Ju Lynn Ong, Thomas Penzel, Michael W L Chee

Förderung

  • NIMH NIH HHS
  • National Medical Research Council Singapore
  • NUS Yong Loo Lin School of Medicine
  • Singapore National Medical Research Council (NMRC) LCG
  • NMRC CTG-IIT
  • NMRC STaR
  • Singapore Ministry of Health (MOH) Centre Grant
  • Temasek Foundation

Zitieren

APA

Yilmaz, G., Lyu, X., Ong, J. L., Ling, L. H., Penzel, T., Yeo, B. T. T., & Chee, M. W. L. (2023). Nocturnal Blood Pressure Estimation from Sleep Plethysmography Using Machine Learning. Sensors, 23(18), 7931. https://doi.org/10.3390/s23187931

Vancouver

Yilmaz G, Lyu X, Ong JL, Ling LH, Penzel T, Yeo BTT, et al. Nocturnal Blood Pressure Estimation from Sleep Plethysmography Using Machine Learning. Sensors. 2023;23(18):7931. doi:10.3390/s23187931

BibTeX
@article{Yilmaz2023,
  author = {Yilmaz, Gizem and Lyu, Xingyu and Ong, Ju Lynn and Ling, Lieng Hsi and Penzel, Thomas and Yeo, B T Thomas and Chee, Michael W L},
  title = {Nocturnal Blood Pressure Estimation from Sleep Plethysmography Using Machine Learning},
  journal = {Sensors},
  year = {2023},
  volume = {23},
  number = {18},
  pages = {7931},
  doi = {10.3390/s23187931}
}
Kostenlos starten →