Modeling of artifacts in the wrist photoplethysmogram: Application to the detection of life-threatening arrhythmias

Paliakaitė‬‬‬, Birutė; Petrėnas, Andrius; Sološenko, Andrius; Marozas, Vaidotas

doi:10.1016/j.bspc.2021.102421

Cited by 13 publications

(6 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Overall data quality is higher during nighttime compared to daytime. This finding in our large cohort is in line with findings in smaller samples specifically for PPG data 35 , 75 . Higher data completeness during the night likely results from fewer risks for the wearable device to be disconnected, such as moving away from the recording device in the outpatient setting, or otherwise stopping recording accidentally.…”

Section: Discussionsupporting

confidence: 92%

Data quality evaluation in wearable monitoring

Böttcher

Vieluf

Bruno

et al. 2022

Sci Rep

View full text Add to dashboard Cite

Wearable recordings of neurophysiological signals captured from the wrist offer enormous potential for seizure monitoring. Yet, data quality remains one of the most challenging factors that impact data reliability. We suggest a combined data quality assessment tool for the evaluation of multimodal wearable data. We analyzed data from patients with epilepsy from four epilepsy centers. Patients wore wristbands recording accelerometry, electrodermal activity, blood volume pulse, and skin temperature. We calculated data completeness and assessed the time the device was worn (on-body), and modality-specific signal quality scores. We included 37,166 h from 632 patients in the inpatient and 90,776 h from 39 patients in the outpatient setting. All modalities were affected by artifacts. Data loss was higher when using data streaming (up to 49% among inpatient cohorts, averaged across respective recordings) as compared to onboard device recording and storage (up to 9%). On-body scores, estimating the percentage of time a device was worn on the body, were consistently high across cohorts (more than 80%). Signal quality of some modalities, based on established indices, was higher at night than during the day. A uniformly reported data quality and multimodal signal quality index is feasible, makes study results more comparable, and contributes to the development of devices and evaluation routines necessary for seizure monitoring.

show abstract

Section: Discussionsupporting

confidence: 92%

Data quality evaluation in wearable monitoring

Böttcher

Vieluf

Bruno

et al. 2022

Sci Rep

View full text Add to dashboard Cite

show abstract

“…When reporting on detection performance, it is essential to state whether performance is computed using the annotations of all segments of the recordings or only the annotations of the segments which remain after signal quality assessment; the latter alternative tends to exaggerate the performance by ignoring false negatives corresponding to arrhythmia segments excluded due to poor quality Paliakaitė et al (2021) . In the present study, the performance measures are computed independently of segment exclusion since the annotations were determined from good-quality ECG signals, not from the PPG signals.…”

Section: Discussionmentioning

confidence: 99%

“…In the context of automated ECG analysis, various definitions can be found relating to the extreme manifestations of these two arrhythmias: extreme bradycardia is defined by a heart rate lower than 40 bpm with fewer than five beats within a period of 6 s, and extreme tachycardia is defined by a heart rate higher than 140 bpm with at least 18 beats within a period of 6.85 s Clifford et al (2016) . Yet another definition of extreme tachycardia can be found in Paliakaitė et al (2021) , replacing 18 with 5 beats, whereas the definition of extreme bradycardia remains unchanged; episodes has to be separated by at least 3 non-arrhythmic beats.…”

Section: Discussionmentioning

confidence: 99%

“…For comparison, the pulse-based bradycardia and tachycardia detector described in Paliakaitė et al (2021) was chosen. The PPG signal is bandpass filtered with cut-off frequencies at 0.5 and 6 Hz (instead of 40 Hz) to suppress high-frequency noise.…”

Section: Methodsmentioning

confidence: 99%

“…The signal quality of each pulse is assessed by correlating it to a pulse template using the sample correlation coefficient. The quality is assessed as acceptable when the maximum correlation coefficient exceeds the threshold η c = 0.6; for more details, see Sološenko et al (2019) ; Paliakaitė et al (2021) . An episode of bradycardia is detected if the heart rate drops below 40 bpm for at least 3 high-quality beats, and an episode of tachycardia is detected if pulse rate exceeds 120 bpm for at least 3 high-quality beats.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Training Convolutional Neural Networks on Simulated Photoplethysmography Data: Application to Bradycardia and Tachycardia Detection

et al. 2022

Self Cite

View full text Add to dashboard Cite

Objective: To develop a method for detection of bradycardia and ventricular tachycardia using the photoplethysmogram (PPG).Approach: The detector is based on a dual-branch convolutional neural network (CNN), whose input is the scalograms of the continuous wavelet transform computed in 5-s segments. Training and validation of the CNN is accomplished using simulated PPG signals generated from RR interval series extracted from public ECG databases. Manually annotated real PPG signals from the PhysioNet/CinC 2015 Challenge Database are used for performance evaluation. The performance is compared to that of a pulse-based reference detector.Results: The sensitivity/specificity were found to be 98.1%/97.9 and 76.6%/96.8% for the CNN-based detector, respectively, whereas the corresponding results for the pulse-based detector were 94.7%/99.8 and 67.1%/93.8%, respectively.Significance: The proposed detector may be useful for continuous, long-term monitoring of bradycardia and tachycardia using wearable devices, e.g., wrist-worn devices, especially in situations where sensitivity is favored over specificity. The study demonstrates that simulated PPG signals are suitable for training and validation of a CNN.

show abstract