Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2023 Oct 9;23(19):8342.
doi: 10.3390/s23198342.

Non-Invasive Blood Pressure Sensing via Machine Learning

Filippo Attivissimo  1 , Vito Ivano D'Alessandro  1 , Luisa De Palma  1 , Anna Maria Lucia Lanzolla  1 , Attilio Di Nisio  1
Affiliations

Non-Invasive Blood Pressure Sensing via Machine Learning

Filippo Attivissimo et al. Sensors (Basel). .

Abstract

In this paper, a machine learning (ML) approach to estimate blood pressure (BP) using photoplethysmography (PPG) is presented. The final aim of this paper was to develop ML methods for estimating blood pressure (BP) in a non-invasive way that is suitable in a telemedicine health-care monitoring context. The training of regression models useful for estimating systolic blood pressure (SBP) and diastolic blood pressure (DBP) was conducted using new extracted features from PPG signals processed using the Maximal Overlap Discrete Wavelet Transform (MODWT). As a matter of fact, the interest was on the use of the most significant features obtained by the Minimum Redundancy Maximum Relevance (MRMR) selection algorithm to train eXtreme Gradient Boost (XGBoost) and Neural Network (NN) models. This aim was satisfactorily achieved by also comparing it with works in the literature; in fact, it was found that XGBoost models are more accurate than NN models in both systolic and diastolic blood pressure measurements, obtaining a Root Mean Square Error (RMSE) for SBP and DBP, respectively, of 5.67 mmHg and 3.95 mmHg. For SBP measurement, this result is an improvement compared to that reported in the literature. Furthermore, the trained XGBoost regression model fulfills the requirements of the Association for the Advancement of Medical Instrumentation (AAMI) as well as grade A of the British Hypertension Society (BHS) standard.

Keywords: blood pressure (BP); digital health; machine learning (ML); physiological monitoring.

PubMed Disclaimer

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
Workflow of the processing steps.
Figure 2
Figure 2
(a) Systolic and (b) diastolic blood pressure occurrences in 2 mmHg bins. Only the observations with 80 mmHg ≤ SBP ≤ 180 mmHg and 60 mmHg ≤ DBP ≤ 110 mmHg were considered since outside these ranges there were few observations and, also, DBP less than 60 mmHg corresponds to a severe hypertension condition.
Figure 3
Figure 3
NN with nine hidden layers with 1024, 1024, 1024, 512, 512, 512, 128, 64, and 64 neurons.
Figure 4
Figure 4
Error probability density of SBP, DBP, and MAP estimations. Errors were defined as the difference between the predicted pressures (using XGBoost model or NN model) and measured ones; then, their histograms were normalized to obtain the probability densities shown in the plot.
Figure 5
Figure 5
(a,c,e) Regression of the predicted output and true response for SBP, DBP, and MAP estimations using the XGBoost model; (b,d,f) Regression of the predicted output and true response for SBP, DBP, and MAP estimations using the NN model.
Figure 5
Figure 5
(a,c,e) Regression of the predicted output and true response for SBP, DBP, and MAP estimations using the XGBoost model; (b,d,f) Regression of the predicted output and true response for SBP, DBP, and MAP estimations using the NN model.
Figure 6
Figure 6
Confusion matrix for BP level classification according to ESH/ESC guidelines.
Figure 7
Figure 7
Bland–Altman plots for (a) SBP, (b) DBP, and (c) MAP.
Figure 7
Figure 7
Bland–Altman plots for (a) SBP, (b) DBP, and (c) MAP.
See this image and copyright information in PMC

References

    1. Fan Y., Xu P., Jin H., Ma J., Qin L. Vital Sign Measurement in Telemedicine Rehabilitation Based on Intelligent Wearable Medical Devices. IEEE Access. 2019;7:54819–54823. doi: 10.1109/ACCESS.2019.2913189. - DOI
    1. Pintavirooj C., Keatsamarn T., Treebupachatsakul T. Multi-Parameter Vital Sign Telemedicine System Using Web Socket for COVID-19 Pandemics. Healthcare. 2021;9:285. doi: 10.3390/healthcare9030285. - DOI - PMC - PubMed
    1. De Palma L., Attivissimo F., Di Nisio A., Lanzolla A.M.L., Ragolia M.A., Spadavecchia M. Development of a web-based system for interfacing a portable Bluetooth vital sign monitor; Proceedings of the 2022 IEEE International Symposium on Medical Measurements and Applications (MeMeA); Messina, Italy. 22–24 June 2022; pp. 1–6. - DOI
    1. Celler B.G., Sparks R.S. Home Telemonitoring of Vital Signs-Technical Challenges and Future Directions. IEEE J. Biomed. Health Inform. 2015;19:82–91. doi: 10.1109/JBHI.2014.2351413. - DOI - PubMed
    1. Scarpetta M., Spadavecchia M., Andria G., Ragolia M.A., Giaquinto N. Simultaneous Measurement of Heartbeat Intervals and Respiratory Signal using a Smartphone; Proceedings of the 2021 IEEE International Symposium on Medical Measurements and Applications (MeMeA); Lausanne, Switzerland. 23–25 June 2021; pp. 1–5. - DOI