Real-Time Quality Index to Control Data Loss in Real-Life Cardiac Monitoring Applications

Abstract

Wearable cardiac sensors pave the way for advanced cardiac monitoring applications based on heart rate variability (HRV). In real-life settings, heart rate (HR) measurements are subject to motion artifacts that may lead to frequent data loss (missing samples in the HR signal), especially for commercial devices based on photoplethysmography (PPG). The current study had two main goals: (i) to provide a white-box quality index that estimates the amount of missing samples in any piece of HR signal; and (ii) to quantify the impact of data loss on feature extraction in a PPG-based HR signal. This was done by comparing real-life recordings from commercial sensors featuring both PPG (Empatica E4) and ECG (Zephyr BioHarness 3). After an outlier rejection process, our quality index was used to isolate portions of ECG-based HR signals that could be used as benchmark, to validate the output of Empatica E4 at the signal level and at the feature level. Our results showed high accuracy in estimating the mean HR (median error: 3.2%), poor accuracy for short-term HRV features (e.g., median error: 64% for high-frequency power), and mild accuracy for longer-term HRV features (e.g., median error: 25% for low-frequency power). These levels of errors could be reduced by using our quality index to identify time windows with few or no data loss (median errors: 0.0%, 27%, and 6.4% respectively, when no sample was missing). This quality index should be useful in future work to extract reliable cardiac features in real-life measurements, or to conduct a field validation study on wearable cardiac sensors.

Data quality evaluation in wearable monitoring

“…In another study assessing PPG as a measure for epileptic seizures, the data from three out of eleven patients wearing an Empatica E4 device was not usable, since no seizure periods without motion artifacts could be recorded 69 . The device has also been evaluated in general purpose real-world settings, with results indicating that the Empatica E4 may be unsuited for monitoring everyday activities 70 , 71 . Even so, it remains the only certified research-grade epilepsy monitoring device on the market that provides raw data for all of the modalities investigated here, relevant to epileptic seizure detection.…”

A Survey of Photoplethysmography and Imaging Photoplethysmography Quality Assessment Methods

“…These criteria are not applicable for smartwatches measuring PPG from green light. Area under pulse [44,45] Mean, std of pulse waveform [35,37] Temporal Pulse width [44,45] Pulse rate [36,70] Derivative Ratio of maximum positive slope over minimum negative slope [59] Spectral Entropy [51] Principal frequencies and residual noise [69] Statistical Skewness [37,50,51,57,69] Kurtosis [37,50,51,57,69] Inter-beat Temporal IBI [35,37,46,59,71] Successive IBI [59] Inter-foot interval [46] Amplitude difference between successive peaks (mean, std) [35,37,[44][45][46] Amplitude difference between successive feet [46,69] Difference between pulse widths [44,45] Difference between rising times [44,45] Signal Temporal Amplitude of the signal [48,72] Difference between autocorrelation of PPG from red and infrared [48] Ratio of oxygenated and deoxygenated blood measured [48] Ratio between systolic and diastolic time…”