Smart detection of atrial fibrillation†

Validation of a novel smartphone-based photoplethysmographic method for ambulatory heart rhythm diagnostics: the SMARTBEATS study

AIMS

In the current guidelines, smartphone photoplethysmography (PPG) is not recommended for diagnosis of atrial fibrillation (AF), without a confirmatory electrocardiogram (ECG) recording. Previous validation studies have been performed under supervision in healthcare settings, with limited generalizability of the results. We aim to investigate the diagnostic performance of a smartphone-PPG method in a real-world setting, with ambulatory unsupervised smartphone-PPG recordings, compared with simultaneous ECG recordings and including patients with atrial flutter (AFL).

METHODS AND RESULTS

Unselected patients undergoing direct current cardioversion for treatment of AF or AFL were asked to perform 1-min heart rhythm recordings post-treatment, at least twice daily for 30 days at home, using an iPhone 7 smartphone running the CORAI Heart Monitor PPG application simultaneously with a single-lead ECG recording (KardiaMobile). Photoplethysmography and ECG recordings were read independently by two experienced readers. In total, 280 patients recorded 18 005 simultaneous PPG and ECG recordings. Sufficient quality for diagnosis was seen in 96.9% (PPG) vs. 95.1% (ECG) of the recordings (P < 0.001). Manual reading of the PPG recordings, compared with manually interpreted ECG recordings, had a sensitivity, specificity, and overall accuracy of 97.7%, 99.4%, and 98.9% with AFL recordings included and 99.0%, 99.7%, and 99.5%, respectively, with AFL recordings excluded.

CONCLUSION

A novel smartphone-PPG method can be used by patients unsupervised at home to achieve accurate heart rhythm diagnostics of AF and AFL with very high sensitivity and specificity. This smartphone-PPG device can be used as an independent heart rhythm diagnostic device following cardioversion, without the requirement of confirmation with ECG.

Detection of heart rate using smartphone gyroscope data: a scoping review

Heart rate (HR) is closely related to heart rhythm patterns, and its irregularity can imply serious health problems. Therefore, HR is used in the diagnosis of many health conditions. Traditionally, HR has been measured through an electrocardiograph (ECG), which is subject to several practical limitations when applied in everyday settings. In recent years, the emergence of smartphones and microelectromechanical systems has allowed innovative solutions for conveniently measuring HR, such as smartphone ECG, smartphone photoplethysmography (PPG), and seismocardiography (SCG). However, these measurements generally rely on external sensor hardware or are highly susceptible to inaccuracies due to the presence of significant levels of motion artifact. Data from gyrocardiography (GCG), however, while largely overlooked for this application, has the potential to overcome the limitations of other forms of measurements. For this scoping review, we performed a literature search on HR measurement using smartphone gyroscope data. In this review, from among the 114 articles that we identified, we include seven relevant articles from the last decade (December 2012 to January 2023) for further analysis of their respective methods for data collection, signal pre-processing, and HR estimation. The seven selected articles' sample sizes varied from 11 to 435 participants. Two articles used a sample size of less than 40, and three articles used a sample size of 300 or more. We provide elaborations about the algorithms used in the studies and discuss the advantages and disadvantages of these methods. Across the articles, we noticed an inconsistency in the algorithms used and a lack of established standardization for performance evaluation for HR estimation using smartphone GCG data. Among the seven articles included, five did not perform any performance evaluation, while the other two used different reference signals (HR and PPG respectively) and metrics for accuracy evaluation. We conclude the review with a discussion of challenges and future directions for the application of GCG technology.

Photoplethysmography-Based Smart Devices for Detection of Atrial Fibrillation

Atrial fibrillation is the most commonly experienced type of cardiac arrhythmia and is the most associated with substantial clinical occurrences and expenses. This arrhythmia often occurs in its "silent" asymptomatic form, revealed only after complications such as a stroke or congestive heart failure have transpired. New smart devices confer effective advantages in the detection of this heart arrhythmia, of which photoplethysmography-based smart devices have shown great potential, according to previous research. However, the solution becomes a problem as widespread use and high availability of various applications and smart devices may lead to substantial amounts of false and misleading recordings and information, causing unnecessary anxiety regarding arrhythmic occurrences diagnosed by the devices but not professionally confirmed. Thus, with most of the devices being photoplethysmography based for detection of atrial fibrillation, it is important to research devices studied up to this point to find the best smart device to detect the aforementioned arrhythmias.

Quantitative Analysis Using Consecutive Time Window for Unobtrusive Atrial Fibrillation Detection Based on Ballistocardiogram Signal

Atrial fibrillation (AF) is the most common clinically significant arrhythmia; therefore, AF detection is crucial. Here, we propose a novel feature extraction method to improve AF detection performance using a ballistocardiogram (BCG), which is a weak vibration signal on the body surface transmitted by the cardiogenic force. In this paper, continuous time windows (CTWs) are added to each BCG segment and recurrence quantification analysis (RQA) features are extracted from each time window. Then, the number of CTWs is discussed and the combined features from multiple time windows are ranked, which finally constitute the CTW-RQA features. As validation, the CTW-RQA features are extracted from 4000 BCG segments of 59 subjects, which are compared with classical time and time-frequency features and up-to-date energy features. The accuracy of the proposed feature is superior, and three types of features are fused to obtain the highest accuracy of 95.63%. To evaluate the importance of the proposed feature, the fusion features are ranked using a chi-square test. CTW-RQA features account for 60% of the first 10 fusion features and 65% of the first 17 fusion features. It follows that the proposed CTW-RQA features effectively supplement the existing BCG features for AF detection.

Visual Reassessment with Flux-Interval Plot Configuration after Automatic Classification for Accurate Atrial Fibrillation Detection by Photoplethysmography

Atrial fibrillation (AFib) is a common type of arrhythmia that is often clinically asymptomatic, which increases the risk of stroke significantly but can be prevented with anticoagulation. The photoplethysmogram (PPG) has recently attracted a lot of attention as a surrogate for electrocardiography (ECG) on atrial fibrillation (AFib) detection, with its out-of-hospital usability for rapid screening or long-term monitoring. Previous studies on AFib detection via PPG signals have achieved good results, but were short of intuitive criteria like ECG p-wave absence or not, especially while using interval randomness to detect AFib suffering from conjunction with premature contractions (PAC/PVC). In this study, we newly developed a PPG flux (pulse amplitude) and interval plots-based methodology, simply comprising an irregularity index threshold of 20 and regression error threshold of 0.06 for the precise automatic detection of AFib. The proposed method with automated detection on AFib shows a combined sensitivity, specificity, accuracy, and precision of 1, 0.995, 0.995, and 0.952 across the 460 samples. Furthermore, the flux-interval plot configuration also acts as a very intuitive tool for visual reassessment to confirm the automatic detection of AFib by its distinctive plot pattern compared to other cardiac rhythms. The study demonstrated that exclusive 2 false-positive cases could be corrected after the reassessment. With the methodology’s background theory well established, the detection process automated and visualized, and the PPG sensors already extensively used, this technology is very user-friendly and convincing for promoted to in-house AFib diagnostics.

Analyzability of Photoplethysmographic Smartwatch Data by the Preventicus Heartbeats Algorithm During Everyday Life: Feasibility Study

BACKGROUND

Continuous heart rate monitoring via mobile health technologies based on photoplethysmography (PPG) has great potential for the early detection of sustained cardiac arrhythmias such as atrial fibrillation. However, PPG measurements are impaired by motion artifacts.

OBJECTIVE

The aim of this investigation was to evaluate the analyzability of smartwatch-derived PPG data during everyday life and to determine the relationship between the analyzability of the data and the activity level of the participant.

METHODS

A total of 41 (19 female and 22 male) adults in good cardiovascular health (aged 19-79 years) continuously wore a smartwatch equipped with a PPG sensor and a 3D accelerometer (Cardio Watch 287, Corsano Health BV) for a period of 24 hours that represented their individual daily routine. For each participant, smartwatch data were analyzed on a 1-minute basis by an algorithm designed for heart rhythm analysis (Preventicus Heartbeats, Preventicus GmbH). As outcomes, the percentage of analyzable data (PAD) and the mean acceleration (ACC) were calculated. To map changes of the ACC and PAD over the course of one day, the 24-hour period was divided into 8 subintervals comprising 3 hours each.

RESULTS

Univariate analysis of variance showed a large effect (η_p²> 0.6; P<.001) of time interval (phase) on the ACC and PAD. The PAD ranged between 34% and 100%, with an average of 71.5% for the whole day, which is equivalent to a period of 17.2 hours. Between midnight and 6 AM, the mean values were the highest for the PAD (>94%) and the lowest for the ACC (<6×10^-3 m/s²). Regardless of the time of the day, the correlation between the PAD and ACC was strong (r=-0.64). A linear regression analysis for the averaged data resulted in an almost perfect coefficient of determination (r²=0.99).

CONCLUSIONS

This study showed a large relationship between the activity level and the analyzability of smartwatch-derived PPG data. Given the high yield of analyzable data during the nighttime, continuous arrhythmia screening seems particularly effective during sleep phases.

mHealth Apps for Self-Management of Cardiovascular Diseases: A Scoping Review

The use of mHealth apps for the self-management of cardiovascular diseases (CVDs) is an increasing trend in patient-centered care. In this research, we conduct a scoping review of mHealth apps for CVD self-management within the period 2014 to 2021. Our review revolves around six main aspects of the current status of mHealth apps for CVD self-management: main CVDs managed, main app functionalities, disease stages managed, common approaches used for data extraction, analysis, management, common wearables used for CVD detection, monitoring and/or identification, and major challenges to overcome and future work remarks. Our review is based on Arksey and O’Malley’s methodological framework for conducting studies. Similarly, we adopted the PRISMA model for reporting systematic reviews and meta-analyses. Of the 442 works initially retrieved, the review comprised 38 primary studies. According to our results, the most common CVDs include arrhythmia (34%), heart failure (32%), and coronary heart disease (18%). Additionally, we found that the majority mHealth apps for CVD self-management can provide medical recommendations, medical appointments, reminders, and notifications for CVD monitoring. Main challenges in the use of mHealth apps for CVD self-management include overcoming patient reluctance to use the technology and achieving the interoperability of mHealth applications with other systems.

Contactless facial video recording with deep learning models for the detection of atrial fibrillation

Atrial fibrillation (AF) is often asymptomatic and paroxysmal. Screening and monitoring are needed especially for people at high risk. This study sought to use camera-based remote photoplethysmography (rPPG) with a deep convolutional neural network (DCNN) learning model for AF detection. All participants were classified into groups of AF, normal sinus rhythm (NSR) and other abnormality based on 12-lead ECG. They then underwent facial video recording for 10 min with rPPG signals extracted and segmented into 30-s clips as inputs of the training of DCNN models. Using voting algorithm, the participant would be predicted as AF if > 50% of their rPPG segments were determined as AF rhythm by the model. Of the 453 participants (mean age, 69.3 ± 13.0 years, women, 46%), a total of 7320 segments (1969 AF, 1604 NSR & 3747others) were analyzed by DCNN models. The accuracy rate of rPPG with deep learning model for discriminating AF from NSR and other abnormalities was 90.0% and 97.1% in 30-s and 10-min recording, respectively. This contactless, camera-based rPPG technique with a deep-learning model achieved significantly high accuracy to discriminate AF from non-AF and may enable a feasible way for a large-scale screening or monitoring in the future.

Detection of Common Arrhythmias by the Watch-PAT: Expression of Electrical Arrhythmias by Pulse Recording

BACKGROUND

The WatchPAT (WP) device was shown to be accurate for the diagnosis of sleep apnea and is widely used worldwide as an ambulatory diagnostic tool. While it records peripheral arterial tone (PAT) and not electrocardiogram (ECG), the ability of it to detect arrhythmias is unknown and was not studied previously. Common arrhythmias such as atrial fibrillation (AF) or premature beats may be uniquely presented while recording PAT/pulse wave.

PURPOSE

To examine the potential detection of common arrhythmias by analyzing the PAT amplitude and pulse rate/volume changes.

PATIENTS AND METHODS

Patients with suspected sleep disordered breathing (SDB) were recruited with preference for patients with previously diagnosed AF or congestive heart failure (CHF). They underwent simultaneous WP and PSG studies in 11 sleep centers. A novel algorithm was developed to detect arrhythmias while measuring PAT and was tested on these patients. Manual scoring of ECG channel (recorded as part of the PSG) was blinded to the automatically analyzed WP data.

RESULTS

A total of 84 patients aged 57±16 (54 males) participated in this study. Their BMI was 30±5.7Kg/m2. Of them, 41 had heart failure (49%) and 17 (20%) had AF. The sensitivity and specificity of the WP to detect AF segments (of at least 60 seconds) were 0.77 and 0.99, respectively. The correlation between the WP derived detection of premature beats (events/min) to that of the PSG one was 0.98 (p<0.001).

CONCLUSION

The novel automatic algorithm of the WP can reasonably detect AF and premature beats. We suggest that when the algorithm raises a flag for arrhythmia, the patients should shortly undergo ECG and/or Holter ECG study.

Diagnostic Utility of Smartwatch Technology for Atrial Fibrillation Detection - A Systematic Analysis

Background

Smartphone technologies have been recently developed to assess heart rate and rhythm, but their role in accurately detecting atrial fibrillation (AF) remains unknown.

Objective

We sought to perform a meta-analysis using prospective studies comparing Smartwatch technology with current monitoring standards for AF detection (ECG, Holter, Patch Monitor, ILR).

Methods

We performed a comprehensive literature search for prospective studies comparing Smartwatch technology simultaneously with current monitoring standards (ECG, Holter, and Patch monitor) for AF detection since inception to November 25th, 2019. The outcome studied was the accuracy of AF detection. Accuracy was determined with concomitant usage of ECG monitoring, Holter monitoring, loop recorder, or patch monitoring.

Results

A total of 9 observational studies were included comparing smartwatch technology, 3 using single-lead ECG monitoring, and six studies using photoplethysmography with routine AF monitoring strategies. A total of 1559 patients were enrolled (mean age 63.5 years, 39.5% had an AF history). The mean monitoring time was 75.6 days. Smartwatch was non-inferior to composite ECG monitoring strategies (OR 1.06, 95% CI 0.93 - 1.21, p=0.37), composite 12 lead ECG/Holter monitoring (OR 0.90, 95% CI 0.62 - 1.30, p=0.57) and patch monitoring (OR 1.28, 95% CI 0.84 - 1.94, p=0.24) for AF detection. The sensitivity and specificity for AF detection using a smartwatch was 95% and 94%, respectively.

Conclusions

Smartwatch based single-lead ECG and photoplethysmography appear to be reasonable alternatives for AF monitoring.

Mobile health solutions for atrial fibrillation detection and management: a systematic review

Aim

We aimed to systematically review the available literature on mobile Health (mHealth) solutions, including handheld and wearable devices, implantable loop recorders (ILRs), as well as mobile platforms and support systems in atrial fibrillation (AF) detection and management.

Methods

This systematic review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) guidelines. The electronic databases PubMed (NCBI), Embase (Ovid), and Cochrane were searched for articles published until 10 February 2021, inclusive. Given that the included studies varied widely in their design, interventions, comparators, and outcomes, no synthesis was undertaken, and we undertook a narrative review.

Results

We found 208 studies, which were deemed potentially relevant. Of these studies included, 82, 46, and 49 studies aimed at validating handheld devices, wearables, and ILRs for AF detection and/or management, respectively, while 34 studies assessed mobile platforms/support systems. The diagnostic accuracy of mHealth solutions differs with respect to the type (handheld devices vs wearables vs ILRs) and technology used (electrocardiography vs photoplethysmography), as well as application setting (intermittent vs continuous, spot vs longitudinal assessment), and study population.

Conclusion

While the use of mHealth solutions in the detection and management of AF is becoming increasingly popular, its clinical implications merit further investigation and several barriers to widespread mHealth adaption in healthcare systems need to be overcome.

Graphic abstract

Mobile health solutions for atrial fibrillation detection and management: a systematic review.

Supplementary Information

The online version contains supplementary material available at 10.1007/s00392-021-01941-9.

Enhancing Healthcare Access-Smartphone Apps in Arrhythmia Screening: Viewpoint

Atrial fibrillation is the most commonly reported arrhythmia and, if undiagnosed or untreated, may lead to thromboembolic events. It is therefore desirable to provide screening to patients in order to detect atrial arrhythmias. Specific mobile apps and accessory devices, such as smartphones and smartwatches, may play a significant role in monitoring heart rhythm in populations at high risk of arrhythmia. These apps are becoming increasingly common among patients and professionals as a part of mobile health. The rapid development of mobile health solutions may revolutionize approaches to arrhythmia screening. In this viewpoint paper, we assess the availability of smartphone and smartwatch apps and evaluate their efficacy for monitoring heart rhythm and arrhythmia detection. The findings obtained so far suggest they are on the right track to improving the efficacy of early detection of atrial fibrillation, thus lowering the risk of stroke and reducing the economic burden placed on public health.

Recent Research for Unobtrusive Atrial Fibrillation Detection Methods Based on Cardiac Dynamics Signals: A Survey

Atrial fibrillation (AF) is the most common cardiac arrhythmia. It tends to cause multiple cardiac conditions, such as cerebral artery blockage, stroke, and heart failure. The morbidity and mortality of AF have been progressively increasing over the past few decades, which has raised widespread concern about unobtrusive AF detection in routine life. The up-to-date non-invasive AF detection methods include electrocardiogram (ECG) signals and cardiac dynamics signals, such as the ballistocardiogram (BCG) signal, the seismocardiogram (SCG) signal and the photoplethysmogram (PPG) signal. Cardiac dynamics signals can be collected by cushions, mattresses, fabrics, or even cameras, which is more suitable for long-term monitoring. Therefore, methods for AF detection by cardiac dynamics signals bring about extensive attention for recent research. This paper reviews the current unobtrusive AF detection methods based on the three cardiac dynamics signals, summarized as data acquisition and preprocessing, feature extraction and selection, classification and diagnosis. In addition, the drawbacks and limitations of the existing methods are analyzed, and the challenges in future work are discussed.

A New Measure of Pulse Rate Variability and Detection of Atrial Fibrillation Based on Improved Time Synchronous Averaging

Background

Pulse rate variability monitoring and atrial fibrillation detection algorithms have been widely used in wearable devices, but the accuracies of these algorithms are restricted by the signal quality of pulse wave. Time synchronous averaging is a powerful noise reduction method for periodic and approximately periodic signals. It is usually used to extract single-period pulse waveforms, but has nothing to do with pulse rate variability monitoring and atrial fibrillation detection traditionally. If this method is improved properly, it may provide a new way to measure pulse rate variability and to detect atrial fibrillation, which may have some potential advantages under the condition of poor signal quality.

Objective

The objective of this paper was to develop a new measure of pulse rate variability by improving existing time synchronous averaging and to detect atrial fibrillation by the new measure of pulse rate variability.

Methods

During time synchronous averaging, two adjacent periods were regarded as the basic unit to calculate the average signal, and the difference between waveforms of the two adjacent periods was the new measure of pulse rate variability. 3 types of distance measures (Euclidean distance, Manhattan distance, and cosine distance) were tested to measure this difference on a simulated training set with a capacity of 1000. The distance measure, which can accurately distinguish regular pulse rate and irregular pulse rate, was used to detect atrial fibrillation on the testing set with a capacity of 62 (11 with atrial fibrillation, 8 with premature contraction, and 43 with sinus rhythm). The receiver operating characteristic curve was used to evaluate the performance of the indexes.

Results

The Euclidean distance between waveforms of the two adjacent periods performs best on the training set. On the testing set, the Euclidean distance in atrial fibrillation group is significantly higher than that of the other two groups. The area under receiver operating characteristic curve to identify atrial fibrillation was 0.998. With the threshold of 2.1, the accuracy, sensitivity, and specificity were 98.39%, 100%, and 98.04%, respectively. This new index can detect atrial fibrillation from pulse wave signal.

Conclusion

This algorithm not only provides a new perspective to detect AF but also accomplishes the monitoring of PRV and the extraction of single-period pulse wave through the same technical route, which may promote the popularization and application of pulse wave.

Visualizing and Quantifying Irregular Heart Rate Irregularities to Identify Atrial Fibrillation Events

Background

Screening the general public for atrial fibrillation (AF) may enable early detection and timely intervention, which could potentially decrease the incidence of stroke. Existing screening methods require professional monitoring and involve high costs. AF is characterized by an irregular irregularity of the cardiac rhythm, which may be detectable using an index quantifying and visualizing this type of irregularity, motivating wide screening programs and promoting the research of AF patient subgroups and clinical impact of AF burden.

Methods

We calculated variability, normality and mean of the difference between consecutive RR interval series (denoted as modified entropy scale—MESC) to quantify irregular irregularities. Based on the variability and normality indices calculated for long 1-lead ECG records, we created a plot termed a regularogram (RGG), which provides a visual presentation of irregularly irregular rates and their burden in a given record. To inspect the potency of these indices, they were applied to train and test a machine learning classifier to identify AF episodes in gold-standard, publicly available databases (PhysioNet) that include recordings from both patients with AF and/or other rhythm disturbances, and from healthy volunteers. The classifier was trained and validated on one database and tested on three other databases.

Results

Irregular irregularities were identified using normality, variability and mean MESC indices. The RGG displayed visually distinct differences between patients with vs. without AF and between patients with different levels of AF burden. Training a simple, explainable machine learning tool integrating these three indices enabled AF detection with 99.9% accuracy, when trained on the same person, and 97.8%, when trained on patients from a different database. Comparison to other RR interval-based AF detection methods that utilize signal processing, classic machine learning and deep learning techniques, showed superiority of our suggested method.

Conclusion

Visualizing and quantifying irregular irregularities will be of value for both rapid visual inspection of long Holter recordings for the presence and the burden of AF, and for machine learning classification to identify AF episodes. A free online tool for calculating the indices, drawing RGGs and estimating AF burden, is available.

Prediction of vascular aging based on smartphone acquired PPG signals

Photoplethysmography (PPG) measured by smartphone has the potential for a large scale, non-invasive, and easy-to-use screening tool. Vascular aging is linked to increased arterial stiffness, which can be measured by PPG. We investigate the feasibility of using PPG to predict healthy vascular aging (HVA) based on two approaches: machine learning (ML) and deep learning (DL). We performed data preprocessing, including detrending, demodulating, and denoising on the raw PPG signals. For ML, ridge penalized regression has been applied to 38 features extracted from PPG, whereas for DL several convolutional neural networks (CNNs) have been applied to the whole PPG signals as input. The analysis has been conducted using the crowd-sourced Heart for Heart data. The prediction performance of ML using two features (AUC of 94.7%) – the a wave of the second derivative PPG and tpr, including four covariates, sex, height, weight, and smoking – was similar to that of the best performing CNN, 12-layer ResNet (AUC of 95.3%). Without having the heavy computational cost of DL, ML might be advantageous in finding potential biomarkers for HVA prediction. The whole workflow of the procedure is clearly described, and open software has been made available to facilitate replication of the results.

Atrial Fibrillation Detection During Sepsis: Study on MIMIC III ICU Data

Sepsis is defined by life-threatening organ dysfunction during infection and is one of the leading causes of critical illness. During sepsis, there is high risk that new-onset of atrial fibrillation (AF) can occur, which is associated with significant morbidity and mortality. As a result, computer aided automated and reliable detection of new-onset AF during sepsis is crucial, especially for the critically ill patients in the intensive care unit (ICU). In this paper, a novel automated and robust two-step algorithm to detect AF from ICU patients using electrocardiogram (ECG) signals is presented. First, several statistical parameters including root mean square of successive differences, Shannon entropy, and sample entropy were calculated from the heart rate for the screening of possible AF segments. Next, Poincaré plot-based features along with P-wave characteristics were used to reduce false positive detection of AF, caused by the premature atrial and ventricular beats. A subset of the Medical Information Mart for Intensive Care (MIMIC) III database containing 198 subjects was used in this study. During the training and validation phases, both the simple thresholding as well as machine learning classifiers achieved very high segment-wise AF classification performance. Finally, we tested the performance of our proposed algorithm using two independent test data sets and compared the performance with two state-of-the-art methods. The algorithm achieved an overall 100% sensitivity, 98% specificity, 98.99% accuracy, 98% positive predictive value, and 100% negative predictive value on the subject-wise AF detection, thus showing the efficacy of our proposed algorithm in critically ill sepsis patients. The annotations of the data have been made publicly available for other investigators.

Reliable Detection of Atrial Fibrillation with a Medical Wearable during Inpatient Conditions

Atrial fibrillation (AF) is the most common arrhythmia and has a major impact on morbidity and mortality; however, detection of asymptomatic AF is challenging. This study sims to evaluate the sensitivity and specificity of non-invasive AF detection by a medical wearable. In this observational trial, patients with AF admitted to a hospital carried the wearable and an ECG Holter (control) in parallel over a period of 24 h, while not in a physically restricted condition. The wearable with a tight-fit upper armband employs a photoplethysmography technology to determine pulse rates and inter-beat intervals. Different algorithms (including a deep neural network) were applied to five-minute periods photoplethysmography datasets for the detection of AF. A total of 2306 h of parallel recording time could be obtained in 102 patients; 1781 h (77.2%) were automatically interpretable by an algorithm. Sensitivity to detect AF was 95.2% and specificity 92.5% (area under the receiver operating characteristics curve (AUC) 0.97). Usage of deep neural network improved the sensitivity of AF detection by 0.8% (96.0%) and specificity by 6.5% (99.0%) (AUC 0.98). Detection of AF by means of a wearable is feasible in hospitalized but physically active patients. Employing a deep neural network enables reliable and continuous monitoring of AF.

Multi-task deep learning for cardiac rhythm detection in wearable devices

Wearable devices enable theoretically continuous, longitudinal monitoring of physiological measurements such as step count, energy expenditure, and heart rate. Although the classification of abnormal cardiac rhythms such as atrial fibrillation from wearable devices has great potential, commercial algorithms remain proprietary and tend to focus on heart rate variability derived from green spectrum LED sensors placed on the wrist, where noise remains an unsolved problem. Here we develop DeepBeat, a multitask deep learning method to jointly assess signal quality and arrhythmia event detection in wearable photoplethysmography devices for real-time detection of atrial fibrillation. The model is trained on approximately one million simulated unlabeled physiological signals and fine-tuned on a curated dataset of over 500 K labeled signals from over 100 individuals from 3 different wearable devices. We demonstrate that, in comparison with a single-task model, our architecture using unsupervised transfer learning through convolutional denoising autoencoders dramatically improves the performance of atrial fibrillation detection from a F1 score of 0.54 to 0.96. We also include in our evaluation a prospectively derived replication cohort of ambulatory participants where the algorithm performed with high sensitivity (0.98), specificity (0.99), and F1 score (0.93). We show that two-stage training can help address the unbalanced data problem common to biomedical applications, where large-scale well-annotated datasets are hard to generate due to the expense of manual annotation, data acquisition, and participant privacy.

Detection of atrial fibrillation with a smartphone camera: first prospective, international, two-centre, clinical validation study (DETECT AF PRO)

Aims

Early detection of atrial fibrillation (AF) is essential for stroke prevention. Emerging technologies such as smartphone cameras using photoplethysmography (PPG) and mobile, internet-enabled electrocardiography (iECG) are effective for AF screening. This study compared a PPG-based algorithm against a cardiologist’s iECG diagnosis to distinguish between AF and sinus rhythm (SR).

Methods and results

In this prospective, two-centre, international, clinical validation study, we recruited in-house patients with presumed AF and matched controls in SR at two university hospitals in Switzerland and Germany. In each patient, a PPG recording on the index fingertip using a regular smartphone camera followed by iECG was obtained. Photoplethysmography recordings were analysed using an automated algorithm and compared with the blinded cardiologist’s iECG diagnosis. Of 672 patients recruited, 80 were excluded mainly due to insufficient PPG/iECG quality, leaving 592 patients (SR: n = 344, AF: n = 248). Based on 5 min of PPG heart rhythm analysis, the algorithm detected AF with a sensitivity of 91.5% (95% confidence interval 85.9–95.4) and specificity of 99.6% (97.8–100). By reducing analysis time to 1 min, sensitivity was reduced to 89.9% (85.5–93.4) and specificity to 99.1% (97.5–99.8). Correctly classified rate was 88.8% for 1-min PPG analysis and dropped to 60.9% when the threshold for the analysed file was set to 5 min of good signal quality.

Conclusion

This is the first prospective clinical two-centre study to demonstrate that detection of AF by using a smartphone camera alone is feasible, with high specificity and sensitivity. Photoplethysmography signal analysis appears to be suitable for extended AF screening.

Clinical trial registration

ClinicalTrials.gov, number NCT02949180, https://clinicaltrials.gov/ct2/show/NCT02949180.

A simple model to detect atrial fibrillation via visual imaging

Automatic detection of atrial fibrillation (AF) is a challenging issue. In this study we proposed and validated a model to identify AF by using facial video recordings. We analyzed photoplethysmographic imaging (PPGi) signals, extracted from video of a subject's face. Sixty-eight patients were included: 30 in sinus rhythm (SR), 25 in AF and 13 presenting with atrial flutter or frequent ectopic beats (ARR). Twenty-six indexes were computed. The dataset was divided in three subsets: the training, validation, and test set, containing, respectively, 58, 29, and 13% of the data. Mean of inter-systolic interval series (M), Local Maxima Similarity (LMS), and pulse harmonic strength (PHS) indexes were significantly different among all groups. Variability and irregularity parameters had the lowest values in SR, the highest in AF, with intermediate values in ARR. The PHS was higher in SR than in ARR, and higher in ARR than in AF. The LMS index was the highest in SR, intermediate in ARR and the lowest in AF. Similarity indexes were higher in SR than in AF and ARR. A model with three features, namely M, Similarity1 and LMS was chosen. With this model, the accuracy for the validation set was 0.947±0.007 for SR, 0.954±0.004 for AF and 0.919±0.006 for ARR; for the test set (never-seen data), accuracy was 0.876±0.021 for SR, 0.870±0.030 for AF and 0.863±0.029 for ARR. A contactless video-based monitoring can be used to detect AF, differentiating it from SR and from frequent ectopies.

Artificial Neural Network for Atrial Fibrillation Identification in Portable Devices

Atrial fibrillation (AF) is a common cardiac disorder that can cause severe complications. AF diagnosis is typically based on the electrocardiogram (ECG) evaluation in hospitals or in clinical facilities. The aim of the present work is to propose a new artificial neural network for reliable AF identification in ECGs acquired through portable devices. A supervised fully connected artificial neural network (RSL_ANN), receiving 19 ECG features (11 morphological, 4 on F waves and 4 on heart-rate variability (HRV)) in input and discriminating between AF and non-AF classes in output, was created using the repeated structuring and learning (RSL) procedure. RSL_ANN was created and tested on 8028 (training: 4493; validation: 1125; testing: 2410) annotated ECGs belonging to the "AF Classification from a Short Single Lead ECG Recording" database and acquired with the portable KARDIA device by AliveCor. RSL_ANN performance was evaluated in terms of area under the curve (AUC) and confidence intervals (CIs) of the received operating characteristic. RSL_ANN performance was very good and very similar in training, validation and testing datasets. AUC was 91.1% (CI: 89.1-93.0%), 90.2% (CI: 86.2-94.3%) and 90.8% (CI: 88.1-93.5%) for the training, validation and testing datasets, respectively. Thus, RSL_ANN is a promising tool for reliable identification of AF in ECGs acquired by portable devices.

Emerging Technologies for Identifying Atrial Fibrillation

Atrial fibrillation (AF) is a major cause of morbidity and mortality globally, and much of this is driven by challenges in its timely diagnosis and treatment. Existing and emerging mobile technologies have been used to successfully identify AF in a variety of clinical and community settings, and while these technologies offer great promise for revolutionizing AF detection and screening, several major barriers may impede their effectiveness. The unclear clinical significance of device-detected AF, potential challenges in integrating patient-generated data into existing healthcare systems and clinical workflows, harm resulting from potential false positives, and identifying the appropriate scope of population-based screening efforts are all potential concerns that warrant further investigation. It is crucial for stakeholders such as healthcare providers, researchers, funding agencies, insurers, and engineers to actively work together in fulfilling the tremendous potential of mobile technologies to improve AF identification and management on a population level.

Review of mobile applications for the detection and management of atrial fibrillation

BACKGROUND

Free mobile applications (apps) that use photoplethysmography (PPG) waveforms may extend atrial fibrillation (AF) detection to underserved populations, but they have not been rigorously evaluated.

OBJECTIVE

The purpose of this study was to systematically review and evaluate the quality, functionality, and adherence to self-management behaviors of existing mobile apps for AF.

METHODS

We systematically searched 3 app stores for apps that were free, available in English, and intended for use by patients to detect and manage AF. A minimum of 2 reviewers evaluated (1) app quality, using the Mobile Application Rating Scale (MARS); (2) functionality using published criteria; and (3) features that support 4 self-management behaviors (including PPG waveform monitoring) identified using evidence-based guidelines. Interrater reliability between the reviewers was calculated.

RESULTS

Of 12 included apps, 5 (42%) scored above average for quality (MARS score ≥3.0). App quality was highest for their ease of use, navigation, layout, and visual appeal (eg, functionality and aesthetics) and lowest for their behavioral change support and subjective impressions of quality. The most common app functionalities were capturing and graphically displaying user-entered data (n = 9 [75%]). Nearly all apps (n = 11 [92%]) supported PPG waveform monitoring, but only 2 (17%) supported all 4 self-management behaviors. Interrater reliability was high (0.75-0.83).

CONCLUSION

The reviewed apps had wide variability in quality, functionality, and adherence to self-management behaviors. Given the accessibility of these apps to underserved populations and the tremendous potential they hold for improving AF detection and management, high priority should be given to improving app quality and functionality.

Accuracy of Smartphone Camera Applications for Detecting Atrial Fibrillation: A Systematic Review and Meta-analysis

Importance

Atrial fibrillation (AF) affects more than 6 million people in the United States; however, much AF remains undiagnosed. Given that more than 265 million people in the United States own smartphones (>80% of the population), smartphone applications have been proposed for detecting AF, but the accuracy of these applications remains unclear.

Objective

To determine the accuracy of smartphone camera applications that diagnose AF.

Data Sources and Study Selection

MEDLINE and Embase were searched until January 2019 for studies that assessed the accuracy of any smartphone applications that use the smartphone's camera to measure the amplitude and frequency of the user's fingertip pulse to diagnose AF.

Data Extraction and Synthesis

Bivariate random-effects meta-analyses were constructed to synthesize data. The study followed the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA) of Diagnostic Test Accuracy Studies reporting guideline.

Main Outcomes and Measures

Sensitivity and specificity were measured with bivariate random-effects meta-analysis. To simulate the use of these applications as a screening tool, the positive predictive value (PPV) and negative predictive value (NPV) for different population groups (ie, age ≥65 years and age ≥65 years with hypertension) were modeled. Lastly, the association of methodological limitations with outcomes were analyzed with sensitivity analyses and metaregressions.

Results

A total of 10 primary diagnostic accuracy studies, with 3852 participants and 4 applications, were included. The oldest studies were published in 2016 (2 studies [20.0%]), while most studies (4 [40.0%]) were published in 2018. The applications analyzed the pulsewave signal for a mean (range) of 2 (1-5) minutes. The meta-analyzed sensitivity and specificity for all applications combined were 94.2% (95% CI, 92.2%-95.7%) and 95.8% (95% CI, 92.4%-97.7%), respectively. The PPV for smartphone camera applications detecting AF in an asymptomatic population aged 65 years and older was between 19.3% (95% CI, 19.2%-19.4%) and 37.5% (95% CI, 37.4%-37.6%), and the NPV was between 99.8% (95% CI, 99.83%-99.84%) and 99.9% (95% CI, 99.94%-99.95%). The PPV and NPV increased for individuals aged 65 years and older with hypertension (PPV, 20.5% [95% CI, 20.4%-20.6%] to 39.2% [95% CI, 39.1%-39.3%]; NPV, 99.8% [95% CI, 99.8%-99.8%] to 99.9% [95% CI, 99.9%-99.9%]). There were methodological limitations in a number of studies that did not appear to be associated with diagnostic performance, but this could not be definitively excluded given the sparsity of the data.

Conclusions and Relevance

In this study, all smartphone camera applications had relatively high sensitivity and specificity. The modeled NPV was high for all analyses, but the PPV was modest, suggesting that using these applications in an asymptomatic population may generate a higher number of false-positive than true-positive results. Future research should address the accuracy of these applications when screening other high-risk population groups, their ability to help monitor chronic AF, and, ultimately, their associations with patient-important outcomes.

Analysis of Relevant Features from Photoplethysmographic Signals for Atrial Fibrillation Classification

Atrial Fibrillation (AF) is the most common cardiac arrhythmia found in clinical practice. It affects an estimated 33.5 million people, representing approximately 0.5% of the world's population. Electrocardiogram (ECG) is the main diagnostic criterion for AF. Recently, photoplethysmography (PPG) has emerged as a simple and portable alternative for AF detection. However, it is not completely clear which are the most important features of the PPG signal to perform this process. The objective of this paper is to determine which are the most relevant features for PPG signal analysis in the detection of AF. This study is divided into two stages: (a) a systematic review carried out following the Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies (PRISMA-DTA) statement in six databases, in order to identify the features of the PPG signal reported in the literature for the detection of AF, and (b) an experimental evaluation of them, using machine learning, in order to determine which have the greatest influence on the process of detecting AF. Forty-four features were found when analyzing the signal in the time, frequency, or time-frequency domains. From those 44 features, 27 were implemented, and through machine learning, it was found that only 11 are relevant in the detection process. An algorithm was developed for the detection of AF based on these 11 features, which obtained an optimal performance in terms of sensitivity (98.43%), specificity (99.52%), and accuracy (98.97%).

Photoplethysmography based atrial fibrillation detection: a review

Atrial fibrillation (AF) is a cardiac rhythm disorder associated with increased morbidity and mortality. It is the leading risk factor for cardioembolic stroke and its early detection is crucial in both primary and secondary stroke prevention. Continuous monitoring of cardiac rhythm is today possible thanks to consumer-grade wearable devices, enabling transformative diagnostic and patient management tools. Such monitoring is possible using low-cost easy-to-implement optical sensors that today equip the majority of wearables. These sensors record blood volume variations-a technology known as photoplethysmography (PPG)-from which the heart rate and other physiological parameters can be extracted to inform about user activity, fitness, sleep, and health. Recently, new wearable devices were introduced as being capable of AF detection, evidenced by large prospective trials in some cases. Such devices would allow for early screening of AF and initiation of therapy to prevent stroke. This review is a summary of a body of work on AF detection using PPG. A thorough account of the signal processing, machine learning, and deep learning approaches used in these studies is presented, followed by a discussion of their limitations and challenges towards clinical applications.

Increasing and Evolving Role of Smart Devices in Modern Medicine

Today is an age of rapid digital integration, yet the capabilities of modern-day smartphones and smartwatches are underappreciated in daily clinical practice. Smartphones are ubiquitous, and smartwatches are very common and on the rise. This creates a wealth of information simply waiting to be accessed, studied and applied clinically, ranging from activity level to various heart rate metrics. This review considers commonly used devices, the validity and accuracy of the data they obtain and potential clinical application of the data.

Validation of Single Centre Pre-Mobile Atrial Fibrillation Apps for Continuous Monitoring of Atrial Fibrillation in a Real-World Setting: Pilot Cohort Study

Background

Atrial fibrillation is the most common recurrent arrhythmia in clinical practice, with most clinical events occurring outside the hospital. Low detection and nonadherence to guidelines are the primary obstacles to atrial fibrillation management. Photoplethysmography is a novel technology developed for atrial fibrillation screening. However, there has been limited validation of photoplethysmography-based smart devices for the detection of atrial fibrillation and its underlying clinical factors impacting detection.

Objective

This study aimed to explore the feasibility of photoplethysmography-based smart devices for the detection of atrial fibrillation in real-world settings.

Methods

Subjects aged ≥18 years (n=361) were recruited from September 14 to October 16, 2018, for screening of atrial fibrillation with active measurement, initiated by the users, using photoplethysmography-based smart wearable devices (ie, a smart band or smart watches). Of these, 200 subjects were also automatically and periodically monitored for 14 days with a smart band. The baseline diagnosis of “suspected” atrial fibrillation was confirmed by electrocardiogram and physical examination. The sensitivity and accuracy of photoplethysmography-based smart devices for monitoring atrial fibrillation were evaluated.

Results

A total of 2353 active measurement signals and 23,864 periodic measurement signals were recorded. Eleven subjects were confirmed to have persistent atrial fibrillation, and 20 were confirmed to have paroxysmal atrial fibrillation. Smart devices demonstrated >91% predictive ability for atrial fibrillation. The sensitivity and specificity of devices in detecting atrial fibrillation among active recording of the 361 subjects were 100% and about 99%, respectively. For subjects with persistent atrial fibrillation, 127 (97.0%) active measurements and 2240 (99.2%) periodic measurements were identified as atrial fibrillation by the algorithm. For subjects with paroxysmal atrial fibrillation, 36 (17%) active measurements and 717 (19.8%) periodic measurements were identified as atrial fibrillation by the algorithm. All persistent atrial fibrillation cases could be detected as “atrial fibrillation episodes” by the photoplethysmography algorithm on the first monitoring day, while 14 (70%) patients with paroxysmal atrial fibrillation demonstrated “atrial fibrillation episodes” within the first 6 days. The average time to detect paroxysmal atrial fibrillation was 2 days (interquartile range: 1.25-5.75) by active measurement and 1 day (interquartile range: 1.00-2.00) by periodic measurement (P=.10). The first detection time of atrial fibrillation burden of <50% per 24 hours was 4 days by active measurement and 2 days by periodic measurementThe first detection time of atrial fibrillation burden of >50% per 24 hours was 1 day for both active and periodic measurements (active measurement: P=.02, periodic measurement: P=.03).

Conclusions

Photoplethysmography-based smart devices demonstrated good atrial fibrillation predictive ability in both active and periodic measurements. However, atrial fibrillation type could impact detection, resulting in increased monitoring time.

Trial Registration

Chinese Clinical Trial Registry of the International Clinical Trials Registry Platform of the World Health Organization ChiCTR-OOC-17014138; http://www.chictr.org.cn/showprojen.aspx?proj=24191.

Accuracy of mHealth Devices for Atrial Fibrillation Screening: Systematic Review

BACKGROUND

Mobile health (mHealth) devices can be used for the diagnosis of atrial fibrillation. Early diagnosis allows better treatment and prevention of secondary diseases like stroke. Although there are many different mHealth devices to screen for atrial fibrillation, their accuracy varies due to different technological approaches.

OBJECTIVE

We aimed to systematically review available studies that assessed the accuracy of mHealth devices in screening for atrial fibrillation. The goal of this review was to provide a comprehensive overview of available technologies, specific characteristics, and accuracy of all relevant studies.

METHODS

PubMed and Web of Science databases were searched from January 2014 until January 2019. Our systematic review was performed according to the Preferred Reporting Items for Systematic Review and Meta-Analyses. We restricted the search by year of publication, language, noninvasive methods, and focus on diagnosis of atrial fibrillation. Articles not including information about the accuracy of devices were excluded.

RESULTS

We found 467 relevant studies. After removing duplicates and excluding ineligible records, 22 studies were included. The accuracy of mHealth devices varied among different technologies, their application settings, and study populations. We described and summarized the eligible studies.

CONCLUSIONS

Our systematic review identifies different technologies for screening for atrial fibrillation with mHealth devices. A specific technology's suitability depends on the underlying form of atrial fibrillation to be diagnosed. With the suitable use of mHealth, early diagnosis and treatment of atrial fibrillation are possible. Successful application of mHealth technologies could contribute to significantly reducing the cost of illness of atrial fibrillation.

A Novel CNN-Based Framework for Classification of Signal Quality and Sleep Position from a Capacitive ECG Measurement

The further exploration of the capacitive ECG (cECG) is hindered by frequent fluctuations in signal quality from body movement and changes in sleep position. The processing framework must be fundamentally adapted to make full use of this signal. Therefore, we propose a new signal-processing framework that determines the signal quality for short signal segments (2 and 4 seconds) using a multi-class classification model (qua_model) based on a convolutional neural network (CNN). We built another independent deep CNN classifier (pos_model) to classify the sleep position. In the validation, 12 subjects were recruited for a 30-minute experiment, which required the subjects to lie on a bed in different sleeping positions. The short segments, classified as clear (C1 class) by the qua_model, were used to determine sleep positions with the pos_model. In 10-fold cross-validation, the qua_model for signals of 4-second length could recognize the signal of the C1 class at a 0.99 precision and a 0.99 recall; the pos_model could recognize the supine sleep position, the left, and right lateral sleep positions at a 0.99 averaged precision and a 0.99 averaged recall. Given the amount of data accumulated per night and the instability in the signal quality, this fully automatic processing framework is indispensable for a personal healthcare system. Therefore, this study could serve as an important step for cECG technique trying to explore the cECG for unconstrained heart monitoring.

Diagnostic Performance of a Smart Device With Photoplethysmography Technology for Atrial Fibrillation Detection: Pilot Study (Pre-mAFA II Registry)

Background

Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia. The asymptomatic nature and paroxysmal frequency of AF lead to suboptimal early detection. A novel technology, photoplethysmography (PPG), has been developed for AF screening. However, there has been limited validation of mobile phone and smart band apps with PPG compared to 12-lead electrocardiograms (ECG).

Objective

We investigated the feasibility and accuracy of a mobile phone and smart band for AF detection using pulse data measured by PPG.

Methods

A total of 112 consecutive inpatients were recruited from the Chinese PLA General Hospital from March 15 to April 1, 2018. Participants were simultaneously tested with mobile phones (HUAWEI Mate 9, HUAWEI Honor 7X), smart bands (HUAWEI Band 2), and 12-lead ECG for 3 minutes.

Results

In all, 108 patients (56 with normal sinus rhythm, 52 with persistent AF) were enrolled in the final analysis after excluding four patients with unclear cardiac rhythms. The corresponding sensitivity and specificity of the smart band PPG were 95.36% (95% CI 92.00%-97.40%) and 99.70% (95% CI 98.08%-99.98%), respectively. The positive predictive value of the smart band PPG was 99.63% (95% CI 97.61%-99.98%), the negative predictive value was 96.24% (95% CI 93.50%-97.90%), and the accuracy was 97.72% (95% CI 96.11%-98.70%). Moreover, the diagnostic sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of mobile phones with PPG for AF detection were over 94%. There was no significant difference after further statistical analysis of the results from the different smart devices compared with the gold-standard ECG (P>.99).

Conclusions

The algorithm based on mobile phones and smart bands with PPG demonstrated good performance in detecting AF and may represent a convenient tool for AF detection in at-risk individuals, allowing widespread screening of AF in the population.

Trial Registration

Chinese Clinical Trial Registry ChiCTR-OOC-17014138; http://www.chictr.org.cn/showproj.aspx?proj=24191 (Archived by WebCite at http://www.webcitation/76WXknvE6)

The Current State of Mobile Phone Apps for Monitoring Heart Rate, Heart Rate Variability, and Atrial Fibrillation: Narrative Review

Background

Mobile phone apps capable of monitoring arrhythmias and heart rate (HR) are increasingly used for screening, diagnosis, and monitoring of HR and rhythm disorders such as atrial fibrillation (AF). These apps involve either the use of (1) photoplethysmographic recording or (2) a handheld external electrocardiographic recording device attached to the mobile phone or wristband.

Objective

This review seeks to explore the current state of mobile phone apps in cardiac rhythmology while highlighting shortcomings for further research.

Methods

We conducted a narrative review of the use of mobile phone devices by searching PubMed and EMBASE from their inception to October 2018. Potentially relevant papers were then compared against a checklist for relevance and reviewed independently for inclusion, with focus on 4 allocated topics of (1) mobile phone monitoring, (2) AF, (3) HR, and (4) HR variability (HRV).

Results

The findings of this narrative review suggest that there is a role for mobile phone apps in the diagnosis, monitoring, and screening for arrhythmias and HR. Photoplethysmography and handheld electrocardiograph recorders are the 2 main techniques adopted in monitoring HR, HRV, and AF.

Conclusions

A number of studies have demonstrated high accuracy of a number of different mobile devices for the detection of AF. However, further studies are warranted to validate their use for large scale AF screening.

Can one detect atrial fibrillation using a wrist-type photoplethysmographic device?

This study aims at evaluating the potential of a wrist-type photoplethysmographic (PPG) device to discriminate between atrial fibrillation (AF) and other types of rhythm. Data from 17 patients undergoing catheter ablation of various arrhythmias were processed. ECGs were used as ground truth and annotated for the following types of rhythm: sinus rhythm (SR), AF, and ventricular arrhythmias (VA). A total of 381/1370/415 10-s epochs were obtained for the three categories, respectively. After pre-processing and removal of segments corresponding to motion artifacts, two different types of feature were derived from the PPG signals: the interbeat interval-based features and the wave-based features, consisting of complexity/organization measures that were computed either from the PPG waveform itself or from its power spectral density. Decision trees were used to assess the discriminative capacity of the proposed features. Three classification schemes were investigated: AF against SR, AF against VA, and AF against (SR&VA). The best results were achieved by combining all features. Accuracies of 98.1/95.9/95.0 %, specificities of 92.4/88.7/92.8 %, and sensitivities of 99.7/98.1/96.2 % were obtained for the three aforementioned classification schemes, respectively. Graphical Abstract Atrial fibrillation detection using PPG signals.

Diagnostic assessment of a deep learning system for detecting atrial fibrillation in pulse waveforms

OBJECTIVE

To evaluate the diagnostic performance of a deep learning system for automated detection of atrial fibrillation (AF) in photoplethysmographic (PPG) pulse waveforms.

METHODS

We trained a deep convolutional neural network (DCNN) to detect AF in 17 s PPG waveforms using a training data set of 149 048 PPG waveforms constructed from several publicly available PPG databases. The DCNN was validated using an independent test data set of 3039 smartphone-acquired PPG waveforms from adults at high risk of AF at a general outpatient clinic against ECG tracings reviewed by two cardiologists. Six established AF detectors based on handcrafted features were evaluated on the same test data set for performance comparison.

RESULTS

In the validation data set (3039 PPG waveforms) consisting of three sequential PPG waveforms from 1013 participants (mean (SD) age, 68.4 (12.2) years; 46.8% men), the prevalence of AF was 2.8%. The area under the receiver operating characteristic curve (AUC) of the DCNN for AF detection was 0.997 (95% CI 0.996 to 0.999) and was significantly higher than all the other AF detectors (AUC range: 0.924-0.985). The sensitivity of the DCNN was 95.2% (95% CI 88.3% to 98.7%), specificity was 99.0% (95% CI 98.6% to 99.3%), positive predictive value (PPV) was 72.7% (95% CI 65.1% to 79.3%) and negative predictive value (NPV) was 99.9% (95% CI 99.7% to 100%) using a single 17 s PPG waveform. Using the three sequential PPG waveforms in combination (<1 min in total), the sensitivity was 100.0% (95% CI 87.7% to 100%), specificity was 99.6% (95% CI 99.0% to 99.9%), PPV was 87.5% (95% CI 72.5% to 94.9%) and NPV was 100% (95% CI 99.4% to 100%).

CONCLUSIONS

In this evaluation of PPG waveforms from adults screened for AF in a real-world primary care setting, the DCNN had high sensitivity, specificity, PPV and NPV for detecting AF, outperforming other state-of-the-art methods based on handcrafted features.

Contact-Free Screening of Atrial Fibrillation by a Smartphone Using Facial Pulsatile Photoplethysmographic Signals

BACKGROUND

We aimed to evaluate a novel method of atrial fibrillation (AF) screening using an iPhone camera to detect and analyze photoplethysmographic signals from the face without physical contact by extracting subtle beat-to-beat variations of skin color that reflect the cardiac pulsatile signal.

METHODS AND RESULTS

Patients admitted to the cardiology ward of the hospital for clinical reasons were recruited. Simultaneous facial and fingertip photoplethysmographic measurements were obtained from 217 hospital inpatients (mean age, 70.3±13.9 years; 71.4% men) facing the front camera and with an index finger covering the back camera of 2 independent iPhones before a 12-lead ECG was recorded. Backdrop and background light intensity was monitored during signal acquisition. Three successive 20-second (total, 60 seconds) recordings were acquired per patient and analyzed for heart rate regularity by Cardiio Rhythm (Cardiio Inc, Cambridge, MA) smartphone application. Pulse irregularity in ≥1 photoplethysmographic readings or 3 uninterpretable photoplethysmographic readings were considered a positive AF screening result. AF was present on 12-lead ECG in 34.6% (n=75/217) patients. The Cardiio Rhythm facial photoplethysmographic application demonstrated high sensitivity (95%; 95% confidence interval, 87%-98%) and specificity (96%; 95% confidence interval, 91%-98%) in discriminating AF from sinus rhythm compared with 12-lead ECG. The positive and negative predictive values were 92% (95% confidence interval, 84%-96%) and 97% (95% confidence interval, 93%-99%), respectively.

CONCLUSIONS

Detection of a facial photoplethysmographic signal to determine pulse irregularity attributable to AF is feasible. The Cardiio Rhythm smartphone application showed high sensitivity and specificity, with low negative likelihood ratio for AF from facial photoplethysmographic signals. The convenience of a contact-free approach is attractive for community screening and has the potential to be useful for distant AF screening.

Computationally efficient algorithm for photoplethysmography-based atrial fibrillation detection using smartphones

Atrial fibrillation (AF) is one of the major causes of stroke, heart failure, sudden death, and cardiovascular morbidity and the most common type of arrhythmia. Its diagnosis and the initiation of treatment, however, currently requires electrocardiogram (ECG)-based heart rhythm monitoring. The photoplethysmogram (PPG) offers an alternative method, which is convenient in terms of its recording and allows for self-monitoring, thus relieving clinical staff and enabling early AF diagnosis. We introduce a PPG-based AF detection algorithm using smartphones that has a low computational cost and low memory requirements. In particular, we propose a modified PPG signal acquisition, explore new statistical discriminating features and propose simple classification equations by using sequential forward selection (SFS) and support vector machines (SVM). The algorithm is applied to clinical data and evaluated in terms of receiver operating characteristic (ROC) curve and statistical measures. The combination of Shannon entropy and the median of the peak rise height achieves perfect detection of AF on the recorded data, highlighting the potential of PPG for reliable AF detection.

[Device-based remote monitoring : Current evidence]

Telemedicine is increasingly used in clinical cardiology. It offers early detection of arrhythmias, technical device follow-up and support of heart failure management. Regarding technical device follow-up, remote monitoring significantly reduces usage of the health care system. Furthermore, remote monitoring is associated with a significantly reduced time from device malfunction to physician's perception of the event. Using remote monitoring, inappropriate ICD (implantable cardioverter defibrillator) shocks can be significantly reduced compared to routine in-office follow-up. In retrospective studies and meta-analyses a prognostic benefit with respect to mortality has been shown. Device-based detection of atrial fibrillation and atrial high rate episodes is feasible. However, clinical relevance is currently studied in prospective randomized clinical trials. Heart failure management based on surrogate parameters has not been shown to significantly improve outcome. However, therapeutic management based on pulmonary artery pressure has been shown to significantly reduce morbidity and mortality. This review offers a comprehensive overview on the role of remote monitoring in heart failure management, technical device follow-up and detection of atrial fibrillation and atrial high rate episodes.