Wearable Photoplethysmography for Cardiovascular Monitoring

Abstract

Smart wearables provide an opportunity to monitor health in daily life and are emerging as potential tools for detecting cardiovascular disease (CVD). Wearables such as fitness bands and smartwatches routinely monitor the photoplethysmogram signal, an optical measure of the arterial pulse wave that is strongly influenced by the heart and blood vessels. In this survey, we summarize the fundamentals of wearable photoplethysmography and its analysis, identify its potential clinical applications, and outline pressing directions for future research in order to realize its full potential for tackling CVD.

Keywords: Cardiovascular (CV); photoplethysmogram (PPG); pulse wave; sensor; signal processing; smartwatch.

Fig. 1.

Acquiring PPG signals. (a)–(c) Cross sections of the wrist and finger showing Typical configurations for acquiring PPG signals. (b) Wearable PPG sensors. (d) Physiological Origins of the PPG signal, showing attenuation of light due to pulsatile arterial blood, venous blood, and other tissues. (e) Comparison of PPG recordings (left) and their frequency spectra (right) with electrocardiogram (ECG) measurements during different activities, acquired using infrared reflectance photoplethysmography at the finger. (f)–(h) Key features of a PPG pulse wave and how they change with age and exercise. See the Supplementary Material for additional details and images. Sources: (a) and (c) are adapted from (public domain), (b) is adapted from https://freesvg.org/vector-drawing-of-outline-of-a-raised-hand (public domain), (d) is adapted from under CC BY 4.0, (e)–(h) data from the Vortal dataset, acquired at the finger , and (f) is adapted from under CC BY 4.0.

Fig. 2.

Preprocessing PPG signals. (a) Filtering to eliminate low-frequency content. (b) Filtering to eliminate high-frequency content. (c) Assessing PPG signal quality: segment of PPG signal containing a period of low-quality signal (red) from which pulse wave features cannot be reliably extracted. (d) Representing a PPG signal in phase space using symmetric projection attractor reconstruction. Sources: (a) and (b) data from the Vortal dataset, acquired using infrared reflectance photoplethysmography at the finger , (c) data from the PPG diary study , and (d) data from the Vortal dataset, acquired at the finger using a clinical monitor .

Fig. 3.

Processing PPG signals. (a) Two steps in extracting features from PPG pulse waves and their derivatives: (left) identifying fiducial points and (right) extracting feature measurements (extracting features from PPG pulse waves). (b) Typical process for detecting AF from PPG signals by quantifying IBI variability using the spread of points on a Poincaré plot (lowest plots, labeled IV.) with ECG signals shown for comparison—these plots all show data from the same subject with the left-hand plots showing data while in AF and the right-hand plots showing data while in normal sinus rhythm. (c) Typical processes for developing models to analyze PPG signals using statistical modeling or machine learning. Sources: (a) is adapted from under CC BY 3.0 (DOI: 10.1088/1361-6579/aabe6a), (b) is adapted from under CC BY 4.0, and (c) is produced using data from the Vortal dataset acquired at the finger using a clinical monitor , data from the PWDB Database , and C. Burnett’s Artificial neural network diagram (https://commons.wikimedia.org/wiki/File:Artificial_neural_network.svg) under CC BY-SA 3.0.

Fig. 4.

Determinants of PPG pulse wave features: Insights obtained using simulated PPG pulse waves. (a) Comparison of the changes in two pulse wave indices with age observed in simulated and clinical data. (b) Wrist PPG Pulse waves representative of a healthy 25-year old male in black and pulse waves under varying CV properties of ±1 standard deviation from the mean for a healthy individual in red and blue, respectively. (c) Influence of CV properties on two pulse wave features, expressed as the relative sensitivity index: the percentage change in a feature associated with a change in CV parameter of 1 standard deviation from baseline. Sources: data obtained from the PWDB database and analyzed using . Clinical data in (a) obtained from .