Evaluation of the signal quality of wrist-based photoplethysmography

Abstract

Objective: Wearable devices with embedded photoplethysmography (PPG) sensors enable continuous monitoring of cardiovascular activity, allowing for the detection cardiovascular problems, such as arrhythmias. However, the quality of wrist-based PPG is highly variable, and is subject to artifacts from motion and other interferences. The goal of this paper is to evaluate the signal quality obtained from wrist-based PPG when used in an ambulatory setting. Approach: Ambulatory data were collected over a 24-hour period for 10 elderly, and 16 non-elderly participants. Visual assessment is used as the gold standard for PPG signal quality, with interrater agreement evaluated using Fleiss' Kappa. With this gold standard, 5 classifiers were evaluated using a modified 13-fold cross-validation approach. Main results: A Random Forest quality classification algorithm showed the best performance, with an accuracy of 74.5%, and was then used to evaluate 24-hour long ambulatory wrist-based PPG measurements. Significance: In general, data quality was high at night, and low during the day. Our results suggest wrist-based PPG may be best for continuous cardiovascular monitoring applications during the night, but less useful during the day unless methods can be identified to improve low quality signal segments.

Photoplethysmogram Analysis and Applications: An Integrative Review

“…Our literature search found that most PPG pre-processing was dependent on frequency filtering to remove high-frequency or low-frequency noise. In frequency filtering, the lower bound of the passband in most studies is about 0.5 Hz ( Sukor et al, 2011 ; Papini et al, 2018 ; Canac et al, 2019 ; Pradhan et al, 2019 ) to remove the DC component below 0.1 Hz and respiratory component in the 0.1–0.5 Hz band while obtaining only the AC component of PPG. The upper bound of the bandpass filter is usually determined considering that the main frequency components of PPG are included within the fourth harmonics in the frequency domain.…”

“…Their study performed binary classification of “reliable or unreliable” for PPG quality using an entire 60-s PPG signal as a CNN input, not extracted features, showing a precision of 0.89, and a recall of 0.83. Pradhan et al (2019) conducted a study comparing the performance of five machine learning classifiers (k-nearest neighbor, multi-class support vector machine, naive Bayes, decision tree, and random forest) to evaluate the SQI of PPG using a wrist-wearable device. In their study, PPG quality was classified into five grades; it was found that the random forest SQI evaluation algorithm had the highest classification accuracy, with an accuracy of 74.5%.…”

Time Synchronization of Multimodal Physiological Signals through Alignment of Common Signal Types and Its Technical Considerations in Digital Health

“…Taking wrist-based PPG as an example, one study evaluated wrist-based PPG acquired over a 24 h period and found only 45% of the signals were of high quality [ 14 ]. The issue is largely contributed by the motion artifact that is pervasive in signals collected with wearables due to their ambulatory nature [ 36 , 37 ]. The two-step approach implemented in the present study demonstrates great efficacy in curbing the signal quality issue.…”

Application of a Machine Learning Algorithms in a Wrist-Wearable Sensor for Patient Health Monitoring during Autonomous Hospital Bed Transport

“…Third, unsupervised multi-feature anomaly detection [ 23 ] which could perform for different activities at cost of uncertainty due to several complex features driving a decision. Finally, an end-to-end deep learning [ 24 ] which showed exceptional quantified results at cost of inexplicability and patient relevancy by cross applying data from other subjects, application context or patients. Details of these various methods are covered in Section 2 of this paper.…”

“…PPG wristband sensors were used across a statistically significant population (N = 35) of 21 years and above, building upon our earlier pilot study [20] which showed up to 95% algorithm efficacy using a single subject's left middle finger PPG across statistically significant number of runs. Measurements were taken simultaneously on left and right wrists to determine past research observations of having better signal quality from non-dominant wrist [24]. Section 2 of this paper presents methods and materials detailing algorithm design followed by data collection procedures.…”