Beat-to-Beat Blood Pressure Estimation by Photoplethysmography and Its Interpretation

10Citations
Citations of this article
31Readers
Mendeley users who have this article in their library.

Abstract

Blood pressure (BP) is among the most important vital signals. Estimation of absolute BP solely using photoplethysmography (PPG) has gained immense attention over the last years. Available works differ in terms of used features as well as classifiers and bear large differences in their results. This work aims to provide a machine learning method for absolute BP estimation, its interpretation using computational methods and its critical appraisal in face of the current literature. We used data from three different sources including 273 subjects and 259,986 single beats. We extracted multiple features from PPG signals and its derivatives. BP was estimated by xgboost regression. For interpretation we used Shapley additive values (SHAP). Absolute systolic BP estimation using a strict separation of subjects yielded a mean absolute error of (Formula presented.) and correlation of (Formula presented.). The results markedly improve if data separation is changed (MAE: (Formula presented.), r: (Formula presented.)). Interpretation by means of SHAP revealed four features from PPG, its derivation and its decomposition to be most relevant. The presented approach depicts a general way to interpret multivariate prediction algorithms and reveals certain features to be valuable for absolute BP estimation. Our work underlines the considerable impact of data selection and of training/testing separation, which must be considered in detail when algorithms are to be compared. In order to make our work traceable, we have made all methods available to the public.

References Powered by Scopus

XGBoost: A scalable tree boosting system

32570Citations
N/AReaders
Get full text

Explainable machine-learning predictions for the prevention of hypoxaemia during surgery

1237Citations
N/AReaders
Get full text

The use of photoplethysmography for assessing hypertension

427Citations
N/AReaders
Get full text

Cited by Powered by Scopus

Non-Invasive Blood Pressure Sensing via Machine Learning

13Citations
N/AReaders
Get full text

Photoplethysmography Driven Hypertension Identification: A Pilot Study

5Citations
N/AReaders
Get full text

Recent developments in machine learning modeling methods for hypertension treatment

4Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Fleischhauer, V., Feldheiser, A., & Zaunseder, S. (2022). Beat-to-Beat Blood Pressure Estimation by Photoplethysmography and Its Interpretation. Sensors, 22(18). https://doi.org/10.3390/s22187037

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 10

77%

Researcher 3

23%

Readers' Discipline

Tooltip

Engineering 8

67%

Medicine and Dentistry 2

17%

Computer Science 1

8%

Nursing and Health Professions 1

8%

Save time finding and organizing research with Mendeley

Sign up for free