Towards Long-term Monitoring of Atrial Fibrillation using Photoplethysmography

Paliakaitė‬‬‬, Birutė; Petrėnas, Andrius; Skibarkienė, Jurgita; Mickus, Tomas; Daukantas, Saulius; Kubilius, Raimondas; Marozas, Vaidotas

doi:10.5220/0006115601410146

Cited by 2 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The detector was tested on both clinical and simulated databases. The clinical database was collected at Kulautuva Rehabilitation Hospital of Kaunas Clinics, Lithuania, acquired using a wrist-worn device developed at the Biomedical Engineering Institute, Kaunas University of Technology, Lithuania (Paliakaitė et al 2017). This device, implementing the proposed detector D 1 , is based on a low-power ARM Cortex M4F MCU with 512 KB flash memory and 64 KB of RAM.…”

Section: Testing Databasesmentioning

confidence: 99%

“…The performance of D 1 is compared to that of D 0 supplemented with signal quality assessment based on accelerometer information; this detector is denoted D0 (Paliakaitė et al 2017). In particular, the amplitudeintegrated motion (Bouten et al 1994, Karantonis et al 2006 is taken as a measure of signal quality; signal segments are excluded whenever the measure exceeds a fixed threshold (the integration interval and the threshold are set to 5 s and 0.02 g units, respectively (Paliakaitė et al 2017)). The four different detectors used in the present study are listed in table 2.…”

Section: Detector For Comparisonmentioning

confidence: 99%

“…The results from analyzing the clinical database using D0 have been published in Paliakaitė et al (2017): the sensitivity and specificity were found to be 99.9% and 91.5%, with 65.4% of the database judged analyzable. The average number of false alarms per day was found to be 15, to be contrasted with 1.5 of D 1 ; see figure 8(d).…”

Section: Detection On the Clinical Databasementioning

confidence: 99%

“…However, the recent advancement of medical technology has led to more convenient and costeffective modalities which are suitable for AF detection (Steinhubl et al 2016, Steinberg et al 2017. One such technology is photoplethysmography (PPG) based on the built-in camera of a smartphone (Lee et al 2013, Chan et al 2016, Freedman 2016, McManus et al 2016, a web camera (Couderc et al 2015), an earlobe sensor (Conroy et al 2017), or a smart wristband (Nemati et al 2016, Corino et al 2017, Paliakaitė et al 2017, Fallet et al 2018.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Detection of atrial fibrillation using a wrist-worn device

et al. 2019

Self Cite

View full text Add to dashboard Cite

Objective: This study proposes an algorithm for the detection of atrial fibrillation (AF), designed to operate on extended photoplethysmographic (PPG) signals recorded using a wrist-worn device of own design. Approach: Robustness against false alarms is achieved by means of signal quality assessment and different techniques for suppression of ectopic beats, bigeminy, and respiratory sinus arrhythmia. The decision logic is based on our previously proposed RR interval-based AF detector, but modified to account for differences between interbeat intervals in the ECG and the PPG. The detector is evaluated on simulated PPG signals as well as on clinical PPG signals recorded during cardiac rehabilitation after myocardial infarction. Main results: Analysis of the clinical signals showed that 1.5 false alarms were on average produced per day with a sensitivity of 72.0% and a specificity of 99.7% when 89.2% of the database was available for analysis, whereas as many as 15 when the RR interval-based AF detector, boosted by accelerometer information for signal quality assessment, was used. However, a sensitivity of 97.2% and a specificity of 99.6% were achieved when increasing the demands on signal quality so that 50% was available for analysis. Significance: The proposed detector offers promising performance and is particularly well-suited for implementation in low-power wearable devices, e.g. wrist-worn devices, with significance in mass screening applications.

show abstract

Section: Testing Databasesmentioning

confidence: 99%