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

Ambulatory monitoring promises equitable personalized healthcare delivery in underrepresented patients

The pandemic has brought to everybody's attention the apparent need of remote monitoring, highlighting hitherto unseen challenges in healthcare. Today, mobile monitoring and real-time data collection, processing and decision-making, can drastically improve the cardiorespiratory-haemodynamic health diagnosis and care, not only in the rural communities, but urban ones with limited healthcare access as well. Disparities in socioeconomic status and geographic variances resulting in regional inequity in access to healthcare delivery, and significant differences in mortality rates between rural and urban communities have been a growing concern. Evolution of wireless devices and smartphones has initiated a new era in medicine. Mobile health technologies have a promising role in equitable delivery of personalized medicine and are becoming essential components in the delivery of healthcare to patients with limited access to in-hospital services. Yet, the utility of portable health monitoring devices has been suboptimal due to the lack of user-friendly and computationally efficient physiological data collection and analysis platforms. We present a comprehensive review of the current cardiac, pulmonary, and haemodynamic telemonitoring technologies. We also propose a novel low-cost smartphone-based system capable of providing complete cardiorespiratory assessment using a single platform for arrhythmia prediction along with detection of underlying ischaemia and sleep apnoea; we believe this system holds significant potential in aiding the diagnosis and treatment of cardiorespiratory diseases, particularly in underserved populations.

New Technologies for Detection and Management of Atrial Fibrillation

Atrial fibrillation (AF) is a common and prevalent form of arrhythmia. It is associated with various morbidities with stroke being the major hazard. Since AF is often reported to be asymptomatic, many individuals remain unaware of their condition and may not receive the requisite treatment. Hence, screening for AF has gained substantial attention recently. Growing advancement in technology has paved way for numerous approaches for AF screening using medical-prescribed devices as well as consumer electronic devices. However, there still lies scope for large-scale randomized trials which would explore additional aspects associated with AF. This review very concisely summarizes AF, screening, present technology, current literature and clinical studies associated with it.

The photoplethysmography dictionary: practical guidance on signal interpretation and clinical scenarios from TeleCheck-AF

Aims

Within the TeleCheck-AF project, numerous centres in Europe used on-demand photoplethysmography (PPG) technology to remotely assess heart rate and rhythm in conjunction with teleconsultations. Based on the TeleCheck-AF investigator experiences, we aimed to develop an educational structured stepwise practical guide on how to interpret PPG signals and to introduce typical clinical scenarios how on-demand PPG was used.

Methods and results

During an online conference, the structured stepwise practical guide on how to interpret PPG signals was discussed and further refined during an internal review process. We provide the number of respective PPG recordings (FibriCheck^®) and number of patients managed within a clinical scenario during the TeleCheck-AF project. To interpret PPG recordings, we introduce a structured stepwise practical guide and provide representative PPG recordings. In the TeleCheck-AF project, 2522 subjects collected 90 616 recordings in total. The majority of these recordings were classified by the PPG algorithm as sinus rhythm (57.6%), followed by AF (23.6%). In 9.7% of recordings, the quality was too low to interpret. The most frequent clinical scenarios where PPG technology was used in the TeleCheck-AF project was a follow-up after AF ablation (1110 patients) followed by heart rate and rhythm assessment around (tele)consultation (966 patients).

Conclusion

We introduce a newly developed structured stepwise practical guide on PPG signal interpretation developed based on presented experiences from TeleCheck-AF. The present clinical scenarios for the use of on-demand PPG technology derived from the TeleCheck-AF project will help to implement PPG technology in the management of AF patients.

Digital health solutions in the screening of subclinical atrial fibrillation

Atrial fibrillation (AF) will become one of the biggest challenges in cardiovascular medicine in the near future. Attempting an improvement in future patient care calls explicitly for the screening of subclinical AF. Digital health solutions implementing communication technologies for the collection and analysis of digitally assessable data will most likely serve this need. Several new rapidly developing methods were introduced in the past decade. Although the vast majority still require scientific validation, the body of evidence is growing and several randomized controlled trials are planned. This review aims to give an overview of current technologies with a specific focus on mobile health (mHealth) and appraise their value with regard to the available scientific data.

World Heart Federation Roadmap on Atrial Fibrillation - A 2020 Update

The World Heart Federation (WHF) commenced a Roadmap initiative in 2015 to reduce the global burden of cardiovascular disease and resultant burgeoning of healthcare costs. Roadmaps provide a blueprint for implementation of priority solutions for the principal cardiovascular diseases leading to death and disability. Atrial fibrillation (AF) is one of these conditions and is an increasing problem due to ageing of the world's population and an increase in cardiovascular risk factors that predispose to AF. The goal of the AF roadmap was to provide guidance on priority interventions that are feasible in multiple countries, and to identify roadblocks and potential strategies to overcome them. Since publication of the AF Roadmap in 2017, there have been many technological advances including devices and artificial intelligence for identification and prediction of unknown AF, better methods to achieve rhythm control, and widespread uptake of smartphones and apps that could facilitate new approaches to healthcare delivery and increasing community AF awareness. In addition, the World Health Organisation added the non-vitamin K antagonist oral anticoagulants (NOACs) to the Essential Medicines List, making it possible to increase advocacy for their widespread adoption as therapy to prevent stroke. These advances motivated the WHF to commission a 2020 AF Roadmap update. Three years after the original Roadmap publication, the identified barriers and solutions were judged still relevant, and progress has been slow. This 2020 Roadmap update reviews the significant changes since 2017 and identifies priority areas for achieving the goals of reducing death and disability related to AF, particularly targeted at low-middle income countries. These include advocacy to increase appreciation of the scope of the problem; plugging gaps in guideline management and prevention through physician education, increasing patient health literacy, and novel ways to increase access to integrated healthcare including mHealth and digital transformations; and greater emphasis on achieving practical solutions to national and regional entrenched barriers. Despite the advances reviewed in this update, the task will not be easy, but the health rewards of implementing solutions that are both innovative and practical will be great.

EVIDENCE Publication Checklist for Studies Evaluating Connected Sensor Technologies: Explanation and Elaboration

The EVIDENCE (EValuatIng connecteD sENsor teChnologiEs) checklist was developed by a multidisciplinary group of content experts convened by the Digital Medicine Society, representing the clinical sciences, data management, technology development, and biostatistics. The aim of EVIDENCE is to promote high quality reporting in studies where the primary objective is an evaluation of a digital measurement product or its constituent parts. Here we use the terms digital measurement product and connected sensor technology interchangeably to refer to tools that process data captured by mobile sensors using algorithms to generate measures of behavioral and/or physiological function. EVIDENCE is applicable to 5 types of evaluations: (1) proof of concept; (2) verification, (3) analytical validation, and (4) clinical validation as defined by the V3 framework; and (5) utility and usability assessments. Using EVIDENCE, those preparing, reading, or reviewing studies evaluating digital measurement products will be better equipped to distinguish necessary reporting requirements to drive high-quality research. With broad adoption, the EVIDENCE checklist will serve as a much-needed guide to raise the bar for quality reporting in published literature evaluating digital measurements products.

Necklace-embedded electrocardiogram for the detection and diagnosis of atrial fibrillation

BACKGROUND

Atrial fibrillation (AF) is the major cause of stroke since approximately 25% of all strokes are of cardioembolic-origin. The detection and diagnosis of AF are often challenging due to the asymptomatic and intermittent nature of AF.

HYPOTHESIS

A wearable electrocardiogram (ECG)-device could increase the likelihood of AF detection. The aim of this study was to evaluate the feasibility and reliability of a novel, consumer-grade, single-lead ECG recording device (Necklace-ECG) for screening, identifying and diagnosing of AF both by a cardiologist and automated AF-detection algorithms.

METHODS

A thirty-second ECG was recorded with the Necklace-ECG device from two positions; between the palms (palm) and between the palm and the chest (chest). Simultaneously registered 3-lead ECGs (Holter) served as a golden standard for the final rhythm diagnosis. Two cardiologists interpreted independently in a blinded fashion the Necklace-ECG recordings from 145 patients (66 AF and 79 sinus rhythm, SR). In addition, the Necklace-ECG recordings were analyzed with an automatic AF detection algorithm.

RESULTS

Two cardiologists diagnosed the correct rhythm of the interpretable Necklace-ECG with a mean sensitivity of 97.2% and 99.1% (palm and chest, respectively) and specificity of 100% and 98.5%. The automatic arrhythmia algorithm detected the correct rhythm with a sensitivity of 94.7% and 98.3% (palm and chest) and specificity of 100% of the interpretable measurements.

CONCLUSIONS

The novel Necklace-ECG device is able to detect AF with high sensitivity and specificity as evaluated both by cardiologists and an automated AF-detection algorithm. Thus, the wearable Necklace-ECG is a new, promising method for AF screening.

CLINICAL TRIAL REGISTRATION

Study was registered in the ClinicalTrials.gov database (NCT03753139).

Validation of an algorithm for continuous monitoring of atrial fibrillation using a consumer smartwatch

BACKGROUND

Consumer devices with broad reach may be useful in screening for atrial fibrillation (AF) in appropriate populations. However, currently no consumer devices are capable of continuous monitoring for AF.

OBJECTIVE

The purpose of this study was to estimate the sensitivity and specificity of a smartwatch algorithm for continuous detection of AF from sinus rhythm in a free-living setting.

METHODS

We studied a commercially available smartwatch with photoplethysmography (W-PPG) and electrocardiogram (W-ECG) capabilities. We validated a novel W-PPG algorithm combined with a W-ECG algorithm in a free-living setting, and compared the results to those of a 28-day continuous ECG patch (P-ECG).

RESULTS

A total of 204 participants completed the free-living study, recording 81,944 hours with both P-ECG and smartwatch measurements. We found sensitivity of 87.8% (95% confidence interval [CI] 83.6%-91.0%) and specificity of 97.4% (95% CI 97.1%-97.7%) for the W-PPG algorithm (every 5-minute classification); sensitivity of 98.9% (95% CI 98.1%-99.4%) and specificity of 99.3% (95% CI 99.1%-99.5%) for the W-ECG algorithm; and sensitivity of 96.9% (95% CI 93.7%-98.5%) and specificity of 99.3% (95% CI 98.4%-99.7%) for W-PPG triggered W-ECG with a single W-ECG required for confirmation of AF. We found a very strong correlation of W-PPG in quantifying AF burden compared to P-ECG (r = 0.98).

CONCLUSION

Our findings demonstrate that a novel algorithm using a commercially available smartwatch can continuously detect AF with excellent performance and that confirmation with W-ECG further enhances specificity. In addition, our W-PPG algorithm can estimate AF burden. Further research is needed to determine whether this algorithm is useful in screening for AF in select at-risk patients.

Stroke and digital technology: a wake-up call from COVID-19 pandemic

Introduction

The pandemic has implemented the need for new digital technologies as useful tools during the emergency and the long recovery phase that will follow. SARS-CoV-2 has strongly impacted stroke care with significant contraction in a number of patients treated.

Methods

This mini-review is an initiative of the “Digital Technologies, Web and Social Media Study Group” of the Italian Society of Neurology and briefly discusses digital tools for managing the acute phase and the rehabilitation after stroke, even considering the new apps that will improve the process of remote monitoring of patients after discharge at home.

Results

Telemedicine and digital technologies could play a role in each of the three stroke-belt stages: hyperacute treatment and reperfusion, acute care, etiological classification and secondary prevention and rehabilitation.

Conclusion

The global emergency represented by the COVID-19 pandemic can be the stimulus to accelerate the digitalization process in the field of stroke for the use of new methods on a large scale.

Challenges in the Management of Atrial Fibrillation With Subclinical Hyperthyroidism

Subclinical thyroid disorders have a high prevalence among older individuals and women. Subclinical hypothyroidism is diagnosed by elevated serum levels of thyroid-stimulating hormone (TSH) with thyroxine levels within the reference range, and subclinical hyperthyroidism is diagnosed by low TSH in conjunction with thyroxine and triiodothyronine levels within reference ranges. Atrial fibrillation is the most commonly diagnosed cardiac arrhythmia and has been associated with an increased risk of mortality, heart failure, stroke, and depression. Mechanistic data from animal and human physiology studies as well as observational data in humans support an association of subclinical hyperthyroidism with atrial fibrillation. Guidelines recommend the measurement of TSH in the evaluation of new-onset atrial fibrillation. All patients with overt hyperthyroidism should be treated, and treatment of subclinical hyperthyroidism should be considered in patients older than 65 years with TSH < 0.4 mlU/L, or in younger patients with TSH < 0.1 mlU/L. Guidelines also recommend screening for AF in patients with known hyperthyroidism. Wearable devices that measure the heart electrical activity continuously may be a novel strategy to detect atrial fibrillation in patients at risk. In this review, we explore the interplay between thyroid hormones and atrial fibrillation, management controversies in subclinical hyperthyroidism, and potential strategies to improve the management of atrial fibrillation in patients with subclinical hyperthyroidism.

Consumer-led screening for atrial fibrillation using consumer-facing wearables, devices and apps: A survey of health care professionals by AF-SCREEN international collaboration

AIM

A variety of consumer-facing wearables, devices and apps are marketed directly to consumers to detect atrial fibrillation (AF). However, their management is not defined. Our aim was to explore their role for AF screening via a survey.

METHODS AND RESULTS

An anonymous web-based survey was undertaken by 588 health care professionals (HCPs) (response rate 23.7%). Overall, 57% HCPs currently advise wearables/apps for AF detection in their patients: this was much higher for electrophysiologists and nurses/allied health professionals (74-75%) than cardiologists (57%) or other physicians (34-38%). Approximately 46% recommended handheld (portable) single-lead dedicated ECG devices, or, less frequently, wristband ECG monitors with similar differentials between HCPs . Only 10-15% HCPs advised photoplethysmographic wristband monitors or smartphone apps. In over half of the HCP consultations for AF detected by wearables/apps, the decision to screen was entirely the patient's. About 45% of HCPs perceive a potential role for AF screening in people aged >65 years or in those with risk factors. Almost 70% of HCPs believed we are not yet ready for mass consumer-initiated screening for AF using wearable devices/apps, with patient anxiety, risk of false positives and negatives, and risk of anticoagulant-related bleeding perceived as potential disadvantages, and perceived need for appropriate management pathways.

CONCLUSIONS

There is a great potential for appropriate use of consumer-facing wearables/apps for AF screening. However, it appears that there is a need to better define suitable individuals for screening and an appropriate mechanism for managing positive results before they can be recommended by HCPs.

Big Data and Artificial Intelligence: Opportunities and Threats in Electrophysiology

The combination of big data and artificial intelligence (AI) is having an increasing impact on the field of electrophysiology. Algorithms are created to improve the automated diagnosis of clinical ECGs or ambulatory rhythm devices. Furthermore, the use of AI during invasive electrophysiological studies or combining several diagnostic modalities into AI algorithms to aid diagnostics are being investigated. However, the clinical performance and applicability of created algorithms are yet unknown. In this narrative review, opportunities and threats of AI in the field of electrophysiology are described, mainly focusing on ECGs. Current opportunities are discussed with their potential clinical benefits as well as the challenges. Challenges in data acquisition, model performance, (external) validity, clinical implementation, algorithm interpretation as well as the ethical aspects of AI research are discussed. This article aims to guide clinicians in the evaluation of new AI applications for electrophysiology before their clinical implementation.

Device- and Analytics-Agnostic Infrastructure for Continuous Inpatient Monitoring: A Technical Note

The internet of healthcare things aims at connecting biosensors, clinical information systems and electronic health dossiers. The resulting data expands traditionally available diagnostics with digital biomarkers. In this technical note, we report the implementation and pilot operation of a device- and analytics-agnostic automated monitoring platform for in-house patients at hospitals. Any available sensor, as well as any analytics tool can be integrated if the application programming interface is made available. The platform consists of a network of Bluetooth gateways communicating via the hospital's secure Wi-Fi network, a server application (Device Hub) and associated databases. Already existing access points or low-cost hardware can be used to run the gateway software. The platform can be extended to a remote patient monitoring solution to close the gap between in-house treatments and follow-up patient monitoring.

Integration of novel monitoring devices with machine learning technology for scalable cardiovascular management

Ambulatory monitoring is increasingly important for cardiovascular care but is often limited by the unpredictability of cardiovascular events, the intermittent nature of ambulatory monitors and the variable clinical significance of recorded data in patients. Technological advances in computing have led to the introduction of novel physiological biosignals that can increase the frequency at which abnormalities in cardiovascular parameters can be detected, making expert-level, automated diagnosis a reality. However, use of these biosignals for diagnosis also raises numerous concerns related to accuracy and actionability within clinical guidelines, in addition to medico-legal and ethical issues. Analytical methods such as machine learning can potentially increase the accuracy and improve the actionability of device-based diagnoses. Coupled with interoperability of data to widen access to all stakeholders, seamless connectivity (an internet of things) and maintenance of anonymity, this approach could ultimately facilitate near-real-time diagnosis and therapy. These tools are increasingly recognized by regulatory agencies and professional medical societies, but several technical and ethical issues remain. In this Review, we describe the current state of cardiovascular monitoring along the continuum from biosignal acquisition to the identification of novel biosensors and the development of analytical techniques and ultimately to regulatory and ethical issues. Furthermore, we outline new paradigms for cardiovascular monitoring.

Advances in cardiovascular monitoring technologies have resulted in an influx of consumer-targeted wearable sensors that have the potential to detect numerous heart conditions. In this Review, Krittanawong and colleagues describe processes involved in biosignal acquisition and analysis of cardiovascular monitors, as well as their associated ethical, regulatory and legal challenges.

Advances in the use of cardiovascular monitoring technologies, such as the development of novel portable sensors and machine learning algorithms that can provide near-real-time diagnosis, have the potential to provide personalized care.

Wearable sensor technologies can detect numerous biosignals, such as cardiac output, blood-pressure levels and heart rhythm, and can integrate multiple modalities.

The use of novel biosignals for diagnosis raises concerns regarding accuracy and actionability within clinical guidelines, in addition to medical, legal and ethical issues.

Machine learning-based interpretation of biosensor data can facilitate rapid evaluation of the haemodynamic consequences of heart failure or arrhythmias, but is limited by the presence of noise and training data that might not be representative of the real-world clinical setting.

The use of data derived from cardiovascular monitoring devices is associated with numerous challenges, such as data security, accessibility and ownership, in addition to other ethical and regulatory concerns.

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.

Artificial Intelligence and Machine Learning in Arrhythmias and Cardiac Electrophysiology

Artificial intelligence (AI) and machine learning (ML) in medicine are currently areas of intense exploration, showing potential to automate human tasks and even perform tasks beyond human capabilities. Literacy and understanding of AI/ML methods are becoming increasingly important to researchers and clinicians. The first objective of this review is to provide the novice reader with literacy of AI/ML methods and provide a foundation for how one might conduct an ML study. We provide a technical overview of some of the most commonly used terms, techniques, and challenges in AI/ML studies, with reference to recent studies in cardiac electrophysiology to illustrate key points. The second objective of this review is to use examples from recent literature to discuss how AI and ML are changing clinical practice and research in cardiac electrophysiology, with emphasis on disease detection and diagnosis, prediction of patient outcomes, and novel characterization of disease. The final objective is to highlight important considerations and challenges for appropriate validation, adoption, and deployment of AI technologies into clinical practice.

Effectiveness of a single lead AliveCor electrocardiogram application for the screening of atrial fibrillation: A systematic review

BACKGROUND

Increasing prevalence of atrial fibrillation has a significant impact on health, society, and healthcare resource utilization, due to increased morbidity, mortality, risk of stroke, and reduction in quality of life. Early diagnosis allows for treatment initiation, a reduction in complications and associated costs, and so innovation to improve screening and enable easy access are needed Developments in digital technology have significantly contributed to the availability of screening tools. The single-lead electrocardiogram AliveCor (Mountainview, CA) device offers the opportunity to provide heart rhythm screening and has been used extensively in clinical practice and research studies.

METHODS

This review investigates the feasibility, validity, and utility of the AliveCor device as a tool for atrial fibrillation detection in clinical practice and in wider research. Databases searched included PUBMED, CINAHL, MEDLINE, and World of Science, plus grey literature search. Search terms related to atrial fibrillation, screening, and AliveCor with adults >18 years. Feasibility metrics were applied including process, resource, management, and scientific outcomes. Studies not written in the English language were excluded. Validity of AliveCor was explored by extracting sensitivity and specificity data from eligible studies and overall effectiveness analyzed by incorporating the above, with wider issues surrounding screening approaches, cost effectiveness and appropriateness of AliveCor as a screening tool.

RESULTS

The AliveCor device screening was reviewed in 11 studies matching inclusion criteria. Atrial fibrillation detection rates ranged from 0.8% to 36% and this largely correlated to the study population, where wider age inclusion and mass/population screening represented lower atrial fibrillation detection. Recruitment from higher-risk groups (older age, targeted localities, chronic disease) identified higher numbers with atrial fibrillation. Feasibility metrics demonstrated AliveCor as an effective tool of choice in terms of process, resources, and management. Duration of screening time had an impact on rates of atrial fibrillation detection. There was however significant heterogeneity between studies reviewed.

CONCLUSION

The AliveCor device offers a convenient, valid, and feasible means of monitoring for atrial fibrillation. Further analysis of electrocardiograms produced by AliveCor may be necessary in some circumstances. The AliveCor electrocardiogram device can be successfully implemented into both opportunistic and systematic screening strategies for atrial fibrillation.

Role of wearable rhythm recordings in clinical decision making-The wEHRAbles project

Background

Multiple wearable devices for rhythm analysis have been developed using either photoplethysmography (PPG) or handheld ECG.

Hypothesis

The aim of this survey was to assess impact of these technologies on physicians' clinical decision‐making regarding initiation of diagnostic steps, drug therapy, and invasive strategies.

Methods

The online survey included 10 questions on types of devices, advantages, and disadvantages of wearable devices as well as case scenarios for patients with supraventricular arrhythmias and atrial fibrillation (AF).

Results

A total of 417 physicians (median age 37 [IQR 32‐43] years) from 42 countries world‐wide completed the survey.

When presented a tracing of a regular tachycardia by a symptomatic patient, most participants would trigger further diagnostic steps (90% for single‐lead ECG vs 83% for PPG, P < .001), while a single‐lead ECG would be sufficient to perform an invasive EP study in approximately half of participants (51% vs 22% for PPG, P < .001).

When presented with a single‐lead ECG tracing suggesting AF, most participants (90%) would trigger further diagnostic steps. A symptomatic AF patient would trigger anticoagulation treatment to a higher extent as an asymptomatic patient (59% vs 21%, P < .001). PPG tracings would only rarely lead to therapeutic steps regardless of symptoms.

Most participants would like scientific society recommendations on the use of wearable devices (62%).

Conclusions

Tracings from wearable rhythm devices suggestive of arrhythmias are most likely to trigger further diagnostic steps, and in the case of PPG recordings rarely therapeutic interventions. A majority of participants expect these devices to facilitate diagnostics and arrhythmia screening but fear data overload and expect scientific society recommendations on the use of wearables.

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.

How Will Machine Learning Inform the Clinical Care of Atrial Fibrillation?

Machine learning applications in cardiology have rapidly evolved in the past decade. With the availability of machine learning tools coupled with vast data sources, the management of atrial fibrillation (AF), a common chronic disease with significant associated morbidity and socioeconomic impact, is undergoing a knowledge and practice transformation in the increasingly complex healthcare environment. Among other advances, deep-learning machine learning methods, including convolutional neural networks, have enabled the development of AF screening pathways using the ubiquitous 12-lead ECG to detect asymptomatic paroxysmal AF in at-risk populations (such as those with cryptogenic stroke), the refinement of AF and stroke prediction schemes through comprehensive digital phenotyping using structured and unstructured data abstraction from the electronic health record or wearable monitoring technologies, and the optimization of treatment strategies, ranging from stroke prophylaxis to monitoring of antiarrhythmic drug (AAD) therapy. Although the clinical and population-wide impact of these tools continues to be elucidated, such transformative progress does not come without challenges, such as the concerns about adopting black box technologies, assessing input data quality for training such models, and the risk of perpetuating rather than alleviating health disparities. This review critically appraises the advances of machine learning related to the care of AF thus far, their potential future directions, and its potential limitations and challenges.

A cost-effectiveness analysis model of Preventicus atrial fibrillation screening from the point of view of statutory health insurance in Germany

BACKGROUND

With atrial fibrillation (AF) the risk of stroke is 4.2-fold increased to a comparable population without AF. This risk decreases by up to 70% if AF is detected early enough and effective stroke preventive measures are taken as recommended by international guidelines. Long-term studies found large number of subjects with undiagnosed AF. Preventicus Heartbeats" is a hands-on screening tool for use on smartphone to diagnose AF with high sensitivity and specificity. The aim of this study is to research the cost-effectiveness of systematic screening for AF with this smartphone application.

METHOD

Employing a Markov model we analysed the cost-effectiveness of the "Preventicus Heartbeats" screening for Germany, i.e. from the perspective of German statutory sick funds.

RESULTS

For a cohort of 10,000 insured 75-year-old the use of the diagnostic app could avoid 60 strokes in the remaining lifetime thereof 32 strokes in the next four years. Former models have applied similar cohorts. The same cohort showed an increase in quality-adjusted life years (QALY) in the remaining lifetime of 165 QALYs in the scenario with screening versus. without screening and a decrease in discounted lifetime costs (including risk compensation effects) of €129 per participant (€148 for male, €114 for female participants).

CONCLUSIONS

The modelling demonstrates the health benefits and economic effects of an implementation of a systematic screening on AF with "Preventicus Heartbeats", given the perspective of the German payer, the statutory health care system.

Machine Learning in Cardiology-Ensuring Clinical Impact Lives Up to the Hype

Despite substantial advances in the study, treatment, and prevention of cardiovascular disease, numerous challenges relating to optimally screening, diagnosing, and managing patients remain. Simultaneous improvements in computing power, data storage, and data analytics have led to the development of new techniques to address these challenges. One powerful tool to this end is machine learning (ML), which aims to algorithmically identify and represent structure within data. Machine learning's ability to efficiently analyze large and highly complex data sets make it a desirable investigative approach in modern biomedical research. Despite this potential and enormous public and private sector investment, few prospective studies have demonstrated improved clinical outcomes from this technology. This is particularly true in cardiology, despite its emphasis on objective, data-driven results. This threatens to stifle ML's growth and use in mainstream medicine. We outline the current state of ML in cardiology and outline methods through which impactful and sustainable ML research can occur. Following these steps can ensure ML reaches its potential as a transformative technology in medicine.

Comparison and Combination of Single-Lead ECG and Photoplethysmography Algorithms for Wearable-Based Atrial Fibrillation Screening

Background: Atrial fibrillation (AF), the most common cardiac arrhythmia, can be detected by smartphones and smartwatches. Introduction: Single-lead ECGs (iECGs) and photoplethysmography (PPG) sensors provide the opportunity for a broad, simple, and easily repeatable cardiac rhythm analysis. To reduce unnecessary medical follow-up testing due to false positive results, our aim was to find a screening approach applicable on smart devices with a focus on high specificity. Methods: We used PPG measurements from smartphones and smartwatches and iECG data from two previous validation trials. Two AF detection algorithms (A and B) were applied on the iECG dataset and compared directly. Further, we used 1-min PPG measurements as a first-pass filter for arrhythmia detection and simulated a sequential testing: Once an arrhythmia was detected in the PPG, the iECG counterpart of the patient was analyzed by algorithm A, B, or A + B combined although algorithm B was primarily designed for PPG analysis. Results: The iECGs from 1,288 participants were analyzed. Algorithm A did not show a diagnosis in 16.1%. In the remaining, sensitivity and specificity were 99.6%, and 97.4% respectively. Accuracy was 98.5%, and correct classification rate (CCR) was 82.7%. Algorithm B always differentiated between normal and arrhythmic and reached an overall sensitivity of 95.4%, a specificity of 91.6%, and an accuracy and CCR of 93.3%. Sequential testing by combining both algorithms into a three-phase test (Test positive PPG, then iECG analysis by A and B combined) resulted in a 100% specificity. Conclusion: Algorithm B performed strongly in PPG analysis as well as iECG analysis. PPG signals and consecutive iECG combined when an arrhythmia was detected by PPG resulted in a specificity that was higher than 99%. Discussion: The analysis allows a direct comparison of iECG algorithms without possible dilution by different measurement procedures or recording-devices. We improved specificity in AF-screening approaches with wearables by simulating a novel approach. Results rely on signal quality.

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.

Screening for atrial fibrillation: a call for evidence

Atrial fibrillation (AF) is the most common cardiac arrhythmia and prevalence is predicted to double over the next 30 years due to changing demographics and the rise in prevalence of risk factors such as hypertension and diabetes. Atrial fibrillation is associated with a five-fold increased stroke risk, but anticoagulation in eligible patients can reduce this risk by around 65%. Many people with AF currently go undetected and therefore untreated, either because they are asymptomatic or because they have paroxysmal AF. Screening has been suggested as one approach to increase AF detection rates and reduce the incidence of ischaemic stroke by earlier initiation of anticoagulation therapy. However, international taskforces currently recommend against screening, citing the cost implications and uncertainty over the benefits of a systematic screening programme compared to usual care. A number of large randomized controlled trials have commenced to determine the cost-effectiveness and clinical benefit of screening using a range of devices and across different populations. The recent AppleWatch study demonstrates how advances in technology are providing the public with self-screening devices that are increasingly affordable and accessible. Health care professionals should be aware of the implications of these emerging data for diagnostic pathways and treatment. This review provides an overview of the gaps in the current evidence and a summary of the arguments for and against screening.

Non-contact and real-time measurement of heart rate and heart rate variability using microwave reflectometry

In this paper, we present noncontact and noninvasive vital signal detection using a microwave reflectometer. Elimination of noise components due to random movement of human subjects has been the biggest issue for microwave measurement. Appropriate filtering, amplitude control of the reflectometer signal, and cross correlation among multiple reflectometers together with new algorithms have enabled motion artifact elimination, signal peak detection, and data processing for various parameters related to heart rate (HR) and heart rate variability (HRV). We focus here on the real time measurements of instantaneous HR and HRV for practical use. The evaluation by microwave reflectometry is completely noninvasive and feasible even through clothing, which is extremely effective for health maintenance in daily life as well as for preventing sudden death related to, for example, coronary heart disease and ventricular arrhythmia.

Impact of monitoring on detection of arrhythmia recurrences in the ESC-EHRA EORP atrial fibrillation ablation long-term registry

AIMS

Monitoring of patients after ablation had wide variations in the ESC-EHRA atrial fibrillation ablation long-term (AFA-LT) registry. We aimed to compare four different monitoring strategies after catheter AF ablation.

METHODS AND RESULTS

The ESC-EHRA AFA-LT registry included 3593 patients who underwent ablation. Arrhythmia monitoring during follow-up was performed by 12-lead electrocardiogram (ECG), Holter ECG, trans-telephonic ECG monitoring (TTMON), or an implanted cardiac monitoring (ICM) system. Patients were selected to a given monitoring group according to the most extensive ECG tool used in each of them. Comparison of the probability of freedom from recurrences was performed by censored log-rank test and presented by Kaplan-Meier curves. The rhythm monitoring methods were used among 2658 patients: ECG (N = 578), Holter ECG (N = 1874), TTMON (N = 101), and ICM (N = 105). A total of 767 of 2658 patients (28.9%) had AF recurrences during follow-up. Censored log-rank test discovered a lower probability of freedom from relapses, which was detected with ICM compared to TTMON, ECG, and Holter ECG (P < 0.001). The rate of freedom from AF recurrences was 50.5% among patients using the ICM while it was 65.4%, 70.6%, and 72.8% using the TTMON, ECG, and Holter ECG, respectively.

CONCLUSION

Comparing all main electrocardiographic monitoring methods in a large patient sample, our results suggest that post-ablation recurrences of AF are significantly underreported by TTMON, ECG, and Holter ECG. The ICM estimates AF ablation recurrences most reliably and should be a preferred mode of monitoring for trials evaluating novel AF ablation techniques.

Wearing Your Heart on Your Sleeve: the Future of Cardiac Rhythm Monitoring

PURPOSE OF REVIEW

This review describes the novel category of wearable ECG monitors and identifies where patients, healthcare providers, and device manufacturers should focus efforts to maximize the clinical benefit of these devices.

RECENT FINDINGS

Notable wearable ECG monitors include the AliveCor Kardia devices, Apple Watch Series 4, and several others. The most common use case is monitoring for atrial fibrillation. The available evidence validates the ability of the Kardia devices and Apple Watch to distinguish atrial fibrillation from sinus rhythm. Key questions for manufacturers include how to calibrate each device's algorithms and streamline workflows for healthcare providers. Wearable ECG monitors are currently most useful to detect atrial fibrillation. Further study is needed to demonstrate whether wearable ECG monitors improve patient outcomes, and to expand their use into other indications. Device manufacturers and healthcare providers must work together to establish new workflows to process and act on wearable ECG data.

Sweat as a Source of Next-Generation Digital Biomarkers

Sweat has been associated with health and disease ever since it was linked to high body temperature and exercise. It contains a broad range of electrolytes, proteins, and lipids, and therefore hosts a broad panel of potential noninvasive biomarkers. The development of novel smartphone-based biosensors will enable a more sophisticated, patient-driven sweat analysis. This will provide a broad range of novel digital biomarkers. Digital biomarkers are of increasing interest because they deliver various relevant longitudinal health data. To date, investigations on digital biomarkers have focused on creating objective measurements of function. Sweat analysis using smartphone-based biosensors has the potential to provide initial noninvasive metabolic feedback and therefore represents a promising complement and a source for next-generation digital biomarkers. From this viewpoint, we discuss state-of-the-art sweat research, focusing on the clinical implementation of sweat in medicine. Sweat provides biomarkers that represent direct metabolic feedback and is therefore expected to be the next generation of digital biomarkers. With regard to its broad application in various fields of medicine, we see a clear need to evolve the internet-enabled field of sweat expertise: iSudorology.

Diagnostic Accuracy of a Smartphone-Operated, Single-Lead Electrocardiography Device for Detection of Rhythm and Conduction Abnormalities in Primary Care

PURPOSE

To validate a smartphone-operated, single-lead electrocardiography (1L-ECG) device (AliveCor KardiaMobile) with an integrated algorithm for atrial fibrillation (AF) against 12-lead ECG (12L-ECG) in a primary care population.

METHODS

We recruited consecutive patients who underwent 12L-ECG for any nonacute indication. Patients held a smartphone with connected 1L-ECG while local personnel simultaneously performed 12L-ECG. All 1L-ECG recordings were assessed by blinded cardiologists as well as by the smartphone-integrated algorithm. The study cardiologists also assessed all 12L-recordings in random order as the reference standard. We determined the diagnostic accuracy of the 1L-ECG in detecting AF or atrial flutter (AFL) as well as any rhythm abnormality and any conduction abnormality with the simultaneously performed 12L-ECG as the reference standard.

RESULTS

We included 214 patients from 10 Dutch general practices. Mean ± SD age was 64.1 ± 14.7 years, and 53.7% of the patients were male. The 12L-ECG diagnosed AF/AFL, any rhythm abnormality, and any conduction abnormality in 23, 44, and 28 patients, respectively. The 1L-ECG as assessed by cardiologists had a sensitivity and specificity for AF/AFL of 100% (95% CI, 85.2%-100%) and 100% (95% CI, 98.1%-100%). The AF detection algorithm had a sensitivity and specificity of 87.0% (95% CI, 66.4%-97.2%) and 97.9% (95% CI, 94.7%-99.4%). The 1L-ECG as assessed by cardiologists had a sensitivity and specificity for any rhythm abnormality of 90.9% (95% CI, 78.3%-97.5%) and 93.5% (95% CI, 88.7%-96.7%) and for any conduction abnormality of 46.4% (95% CI, 27.5%-66.1%) and 100% (95% CI, 98.0%-100%).

CONCLUSIONS

In a primary care population, a smartphone-operated, 1L-ECG device showed excellent diagnostic accuracy for AF/AFL and good diagnostic accuracy for other rhythm abnormalities. The 1L-ECG device was less sensitive for conduction abnormalities.

Assessment of Ultra-Short Heart Variability Indices Derived by Smartphone Accelerometers for Stress Detection

Body acceleration due to heartbeat-induced reaction forces can be measured as mobile phone accelerometer (m-ACC) signals. Our aim was to test the feasibility of using m-ACC to detect changes induced by stress by ultra-short heart rate variability (USV) indices (standard deviation of normal-to-normal interval—SDNN and root mean square of successive differences—RMSSD). Sixteen healthy volunteers were recruited; m-ACC was recorded while in supine position, during spontaneous breathing at rest conditions (REST) and during one minute of mental stress (MS) induced by arithmetic serial subtraction task, simultaneous with conventional electrocardiogram (ECG). Beat occurrences were extracted from both ECG and m-ACC and used to compute USV indices using 60, 30 and 10 s durations, both for REST and MS. A feasibility of 93.8% in the beat-to-beat m-ACC heart rate series extraction was reached. In both ECG and m-ACC series, compared to REST, in MS the mean beat duration was reduced by 15% and RMSSD decreased by 38%. These results show that short term recordings (up to 10 s) of cardiac activity using smartphone’s accelerometers are able to capture the decrease in parasympathetic tone, in agreement with the induced stimulus.

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.

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.

Windows Into Human Health Through Wearables Data Analytics

Background

Wearable sensors (wearables) have been commonly integrated into a wide variety of commercial products and are increasingly being used to collect and process raw physiological parameters into salient digital health information. The data collected by wearables are currently being investigated across a broad set of clinical domains and patient populations. There is significant research occurring in the domain of algorithm development, with the aim of translating raw sensor data into fitness- or health-related outcomes of interest for users, patients, and health care providers.

Objectives

The aim of this review is to highlight a selected group of fitness- and health-related indicators from wearables data and to describe several algorithmic approaches used to generate these higher order indicators.

Methods

A systematic search of the Pubmed database was performed with the following search terms (number of records in parentheses): Fitbit algorithm (18), Apple Watch algorithm (3), Garmin algorithm (5), Microsoft Band algorithm (8), Samsung Gear algorithm (2), Xiaomi MiBand algorithm (1), Huawei Band (Watch) algorithm (2), photoplethysmography algorithm (465), accelerometry algorithm (966), ECG algorithm (8287), continuous glucose monitor algorithm (343). The search terms chosen for this review are focused on algorithms for wearable devices that dominated the commercial wearables market between 2014-2017 and that were highly represented in the biomedical literature. A second set of search terms included categories of algorithms for fitness-related and health-related indicators that are commonly used in wearable devices (e.g. accelerometry, PPG, ECG). These papers covered the following domain areas: fitness; exercise; movement; physical activity; step count; walking; running; swimming; energy expenditure; atrial fibrillation; arrhythmia; cardiovascular; autonomic nervous system; neuropathy; heart rate variability; fall detection; trauma; behavior change; diet; eating; stress detection; serum glucose monitoring; continuous glucose monitoring; diabetes mellitus type 1; diabetes mellitus type 2. All studies uncovered through this search on commercially available device algorithms and pivotal studies on sensor algorithm development were summarized, and a summary table was constructed using references generated by the literature review as described (Table 1).

Conclusions

Wearable health technologies aim to collect and process raw physiological or environmental parameters into salient digital health information. Much of the current and future utility of wearables lies in the signal processing steps and algorithms used to analyze large volumes of data. Continued algorithmic development and advances in machine learning techniques will further increase analytic capabilities. In the context of these advances, our review aims to highlight a range of advances in fitness- and other health-related indicators provided by current wearable technologies.