Wrist Band Photoplethysmography Autocorrelation Analysis Enables Detection of Atrial Fibrillation Without Pulse Detection.

Eemu-Samuli Väliaho,Jari Halonen,Helena Jäntti,Pekka Kuoppa,Hanna Pohjantähti-Maaroos,Onni E Santala,Juha E K Hartikainen,Tero J Martikainen,Maaret Castrén,Indrek Kolk,Mika P Tarvainen,Tuomas T Rissanen,Jukka A Lipponen

doi:10.3389/fphys.2021.654555

Abstract

Atrial fibrillation is often asymptomatic and intermittent making its detection challenging. A photoplethysmography (PPG) provides a promising option for atrial fibrillation detection. However, the shapes of pulse waves vary in atrial fibrillation decreasing pulse and atrial fibrillation detection accuracy. This study evaluated ten robust photoplethysmography features for detection of atrial fibrillation. The study was a national multi-center clinical study in Finland and the data were combined from two broader research projects (NCT03721601, URL: https://clinicaltrials.gov/ct2/show/NCT03721601 and NCT03753139, URL: https://clinicaltrials.gov/ct2/show/NCT03753139). A photoplethysmography signal was recorded with a wrist band. Five pulse interval variability, four amplitude features and a novel autocorrelation-based morphology feature were calculated and evaluated independently as predictors of atrial fibrillation. A multivariate predictor model including only the most significant features was established. The models were 10-fold cross-validated. 359 patients were included in the study (atrial fibrillation n = 169, sinus rhythm n = 190). The autocorrelation univariate predictor model detected atrial fibrillation with the highest area under receiver operating characteristic curve (AUC) value of 0.982 (sensitivity 95.1%, specificity 93.7%). Autocorrelation was also the most significant individual feature (p < 0.00001) in the multivariate predictor model, detecting atrial fibrillation with AUC of 0.993 (sensitivity 96.4%, specificity 96.3%). Our results demonstrated that the autocorrelation independently detects atrial fibrillation reliably without the need of pulse detection. Combining pulse wave morphology-based features such as autocorrelation with information from pulse-interval variability it is possible to detect atrial fibrillation with high accuracy with a commercial wrist band. Photoplethysmography wrist bands accompanied with atrial fibrillation detection algorithms utilizing autocorrelation could provide a computationally very effective and reliable wearable monitoring method in screening of atrial fibrillation.

Highlights

MATERIALS AND METHODSAtrial fibrillation (AF) is the most common tachyarrhythmia and it’s prevalence is increasing as the population ages (Morillo et al, 2017)
We demonstrated that the novel AC as a univariate predictor model detected AND METHODSAtrial fibrillation (AF) with high sensitivity (95.1%) and specificity (93.7%) from the PPG wrist band signal
Our study shows that combining pulse wave morphology-based AC with PIN and AMP-based features improves the diagnostic performance of PPG wrist bands

Summary

Introduction

MATERIALS AND METHODSAtrial fibrillation (AF) is the most common tachyarrhythmia and it’s prevalence is increasing as the population ages (Morillo et al, 2017). AF is associated with thromboembolic complications, such as stroke (Xiong et al, 2015; Morillo et al, 2017; Pereira et al, 2020). 25% of ischaemic strokes are of unknown cause and there is persuasive evidence that most of these are of thromboembolic origin (Hart et al, 2014). Up to two thirds of strokes can be prevented with anticoagulation (Saxena and Koudstaal, 2004; Hart et al, 2007). A clinical challenge is that AF is often asymptomatic or paroxysmal (Xiong et al, 2015) and difficult to be diagnosed. Continuous monitoring with automatic AF detection would improve AF screening detection allowing appropriate primary and secondary strategies for prevention of stroke (Pereira et al, 2020)

Methods

Results

Conclusion