2021 ISHNE/HRS/EHRA/APHRS collaborative statement on mHealth in Arrhythmia Management: Digital Medical Tools for Heart Rhythm Professionals: From the International Society for Holter and Noninvasive Electrocardiology/Heart Rhythm Society/European Heart Rhythm Association/Asia Pacific Heart Rhythm Society

Novel application of convolutional neural networks for artificial intelligence-enabled modified moving average analysis of P-, R-, and T-wave alternans for detection of risk for atrial and ventricular arrhythmias

BACKGROUND

T-wave alternans (TWA) analysis was shown in >14,000 individuals studied worldwide over the past two decades to be a useful tool to assess risk for cardiovascular mortality and sudden arrhythmic death. TWA analysis by the modified moving average (MMA) method is FDA-cleared and CMS-reimbursed (CAG-00293R2).

OBJECTIVE

Because the MMA technique is inherently suitable for dynamic tracking of alternans levels, it was selected for development of artificial intelligence (AI)-enabled algorithms using convolutional neural networks (CNN) to achieve rapid, efficient, and accurate assessment of P-wave alternans (PWA), R-wave alternans (RWA), and TWA.

METHODS

The novel application of CNN algorithms to enhance MMA analysis generated efficient and powerful pattern-recognition algorithms for highly accurate alternans quantification. Algorithm reliability and accuracy were verified using simulated ECGs achieving R2 ≥ 0.99 (p < 0.01) in response to noise inputs and artifacts that emulate real-life conditions.

RESULTS

Accuracy of the new AI-MMA algorithms in TWA analysis (n = 5) was significantly improved over unsupervised, automated MMA output (p = 0.036) and did not differ from conventional MMA analysis with expert overreading (p = 0.21). Accuracy of AI-MMA in PWA analysis (n = 45) was significantly improved over unsupervised, automated MMA output (p < 0.005) and did not differ from conventional MMA analysis with expert overreading (p = 0.89). TWA and PWA by AI-MMA were correlated with conventional MMA output over-read by an expert reader (R2 = 0.7765, R2 = 0.9504, respectively).

CONCLUSION

This novel technique for AI-MMA analysis could be suitable for use in diverse in-hospital and out-of-hospital monitoring systems, including cardiac implantable electronic devices and smartwatches, for tracking atrial and ventricular arrhythmia risk.

Characterizing Real-World Implementation of Consumer Wearables for the Detection of Undiagnosed Atrial Fibrillation in Clinical Practice: Targeted Literature Review

BACKGROUND

Atrial fibrillation (AF), the most common cardiac arrhythmia, is often undiagnosed because of lack of awareness and frequent asymptomatic presentation. As AF is associated with increased risk of stroke, early detection is clinically relevant. Several consumer wearable devices (CWDs) have been cleared by the US Food and Drug Administration for irregular heart rhythm detection suggestive of AF. However, recommendations for the use of CWDs for AF detection in clinical practice, especially with regard to pathways for workflows and clinical decisions, remain lacking.

OBJECTIVE

We conducted a targeted literature review to identify articles on CWDs characterizing the current state of wearable technology for AF detection, identifying approaches to implementing CWDs into the clinical workflow, and characterizing provider and patient perspectives on CWDs for patients at risk of AF.

METHODS

PubMed, ClinicalTrials.gov, UpToDate Clinical Reference, and DynaMed were searched for articles in English published between January 2016 and July 2023. The searches used predefined Medical Subject Headings (MeSH) terms, keywords, and search strings. Articles of interest were specifically on CWDs; articles on ambulatory monitoring tools, tools available by prescription, or handheld devices were excluded. Search results were reviewed for relevancy and discussed among the authors for inclusion. A qualitative analysis was conducted and themes relevant to our study objectives were identified.

RESULTS

A total of 31 articles met inclusion criteria: 7 (23%) medical society reports or guidelines, 4 (13%) general reviews, 5 (16%) systematic reviews, 5 (16%) health care provider surveys, 7 (23%) consumer or patient surveys or interviews, and 3 (10%) analytical reports. Despite recognition of CWDs by medical societies, detailed guidelines regarding CWDs for AF detection were limited, as was the availability of clinical tools. A main theme was the lack of pragmatic studies assessing real-world implementation of CWDs for AF detection. Clinicians expressed concerns about data overload; potential for false positives; reimbursement issues; and the need for clinical tools such as care pathways and guidelines, preferably developed or endorsed by professional organizations. Patient-facing challenges included device costs and variability in digital literacy or technology acceptance.

CONCLUSIONS

This targeted literature review highlights the lack of a comprehensive body of literature guiding real-world implementation of CWDs for AF detection and provides insights for informing additional research and developing appropriate tools and resources for incorporating these devices into clinical practice. The results should also provide an impetus for the active involvement of medical societies and other health care stakeholders in developing appropriate tools and resources for guiding the real-world use of CWDs for AF detection. These resources should target clinicians, patients, and health care systems with the goal of facilitating clinician or patient engagement and using an evidence-based approach for establishing guidelines or frameworks for administrative workflows and patient care pathways.

Risk factor profile for newly diagnosed atrial fibrillation: 4-year follow-up of annual health examinations in a Japanese Adult Cohort

BACKGROUND

Detecting unknown atrial fibrillation (AF) would provide an opportunity to prevent ischemic stroke by instituting appropriate anticoagulation. Although opportunistic screening of older patients is recommended in current guidelines, which patients may benefit from intensive AF screening remains unclear. We sought to clarify the risk factor profile for newly diagnosed AF in annual health examinations of a Japanese adult cohort.

METHODS

Among 141 441 Japanese patients who underwent annual health examinations in 2014, 87 872 patients aged ≥20 years without known AF who had undergone electrocardiography were analyzed (mean age: 47 ± 12 years; 64% men). The absence of known AF was confirmed by prior electrocardiography in 2012 and/or 2013. Newly diagnosed AF was observed in 244 patients in 2014-2017 (mean age: 62 ± 12 years; 83% men).

RESULTS

In the multivariable analysis, waist circumference obesity (hazard ratio [HR], 1.5; 95% confidence interval [CI], 1.13-1.99; p = .005) high blood pressure (HR, 1.9; 95% CI, 1.01-3.59; p = .047), on-treatment hypertension (HR, 1.53; 95% CI, 1.01-2.31; p = .046), and daily alcohol drinking (HR, 2.18; 95% CI, 1.52-3.12; p < .001) were significantly associated with newly diagnosed AF.

CONCLUSIONS

In this Japanese cohort, waist circumference obesity, hypertension, and alcohol drinking were independent predictors of newly diagnosed AF in annual medical examinations. This finding encourages further evaluation of systematic AF screening programs in at-risk populations.

Prediction of the Presence of Ventricular Fibrillation From a Brugada Electrocardiogram Using Artificial Intelligence

BACKGROUND

Brugada syndrome is a potential cause of sudden cardiac death (SCD) and is characterized by a distinct ECG, but not all patients with A Brugada ECG develop SCD. In this study we sought to examine if an artificial intelligence (AI) model can predict a previous or future ventricular fibrillation (VF) episode from a Brugada ECG.Methods and Results: We developed an AI-enabled algorithm using a convolutional neural network. From 157 patients with suspected Brugada syndrome, 2,053 ECGs were obtained, and the dataset was divided into 5 datasets for cross-validation. In the ECG-based evaluation, the precision, recall, and F1score were 0.79±0.09, 0.73±0.09, and 0.75±0.09, respectively. The average area under the receiver-operating characteristic curve (AUROC) was 0.81±0.09. On per-patient evaluation, the AUROC was 0.80±0.07. This model predicted the presence of VF with a precision of 0.93±0.02, recall of 0.77±0.14, and F1score of 0.81±0.11. The negative predictive value was 0.94±0.11 while its positive predictive value was 0.44±0.29.

CONCLUSIONS

This proof-of-concept study showed that an AI-enabled algorithm can predict the presence of VF with a substantial performance. It implies that the AI model may detect a subtle ECG change that is undetectable by humans.

Smartphone and wearable detected atrial arrhythmias in Older Adults: Results of a fully digital European Case finding study

Aims

Simplified detection of atrial arrhythmias via consumer-electronics would enable earlier therapy in at-risk populations. Whether this is feasible and effective in older populations is not known.

Methods and results

The fully remote, investigator-initiated Smartphone and wearable detected atrial arrhythmia in Older Adults Case finding study (Smart in OAC-AFNET 9) digitally enrolled participants ≥65 years without known atrial fibrillation, not receiving oral anticoagulation in Germany, Poland, and Spain for 8 weeks. Participants were invited by media communications and direct contacts. Study procedures adhered to European data protection. Consenting participants received a wristband with a photoplethysmography sensor to be coupled to their smartphone. The primary outcome was the detection of atrial arrhythmias lasting 6 min or longer in the first 4 weeks of monitoring. Eight hundred and eighty-two older persons (age 71 ± 5 years, range 65-90, 500 (57%) women, 414 (47%) hypertension, and 97 (11%) diabetes) recorded signals. Most participants (72%) responded to adverts or word of mouth, leaflets (11%) or general practitioners (9%). Participation was completely remote in 469/882 persons (53%). During the first 4 weeks, participants transmitted PPG signals for 533/696 h (77% of the maximum possible time). Atrial arrhythmias were detected in 44 participants (5%) within 28 days, and in 53 (6%) within 8 weeks. Detection was highest in the first monitoring week [incidence rates: 1st week: 3.4% (95% confidence interval 2.4-4.9); 2nd-4th week: 0.55% (0.33-0.93)].

Conclusion

Remote, digitally supported consumer-electronics-based screening is feasible in older European adults and identifies atrial arrhythmias in 5% of participants within 4 weeks of monitoring (NCT04579159).

Patient-initiated cardiovascular monitoring with commercially available devices: How useful is it in a cardiology outpatient setting? Mixed methods, observational study

Background

The availability, affordability and utilisation of commercially available self-monitoring devices is increasing, but their impact on routine clinical decision-making remains little explored. We sought to examine how patient-generated cardiovascular data influenced clinical evaluation in UK cardiology outpatient clinics and to understand clinical attitudes and experiences with using data from commercially available self-monitoring devices.

Methods

Mixed methods study combining: a) quantitative and qualitative content analysis of 1373 community cardiology clinic letters, recording consultations between January–September 2020 including periods with different Covid-19 related restrictions, and b) semi-structured qualitative interviews and group discussions with 20 cardiology-affiliated clinicians at the same NHS Trust.

Results

Patient-generated cardiovascular data were described in 185/1373 (13.5%) clinic letters overall, with the proportion doubling following onset of the first Covid-19 lockdown in England, from 8.3% to 16.6% (p < 0.001). In 127/185 (69%) cases self-monitored data were found to: provide or facilitate cardiac diagnoses (34/127); assist management of previously diagnosed cardiac conditions (55/127); be deployed for cardiovascular prevention (16/127); or be recommended for heart rhythm evaluation (10/127). In 58/185 (31%) cases clinicians did not put the self-monitored data to any evident use and in 12/185 (6.5%) cases patient-generated data prompted an unnecessary referral. In interviews and discussions, clinicians expressed mixed views on patient-generated data but foresaw a need to embrace and plan for this information flow, and proactively address challenges with integration into traditional care pathways.

Conclusions

This study suggests patient-generated data are being used for clinical decision-making in ad hoc and opportunistic ways. Given shifts towards remote monitoring in clinical care, accelerated by the pandemic, there is a need to consider how best to incorporate patient-generated data in clinical processes, introduce relevant training, pathways and governance frameworks, and manage associated risks.

Prospects for developing and implementing remote blood pressure monitoring in patients under dispensary follow-up

Recently, the use of telemedicine technologies (TMT) in the healthcare has gained great importance. TMT is one of the ways to increase the healthcare availability, including in patients with high blood pressure (BP). Office BP measurement and 24-hour BP monitoring are not accurate enough to study natural or induced BP changes over long periods of time. For the selection of antihypertensive drugs and the diagnosis of hypertension (HTN) in patients with an emotionally unstable personality type, as well as in the differential diagnosis of normotension, preHTN, BP selfmonitoring comes first. The use of BP self-monitoring for the diagnosis, selection of therapy, assessment of adherence and effectiveness of treatment of HTN is more effective with remote, socalled telemetric, dynamic BP monitoring. The article presents world experience in the effective use of dynamic remote BP monitoring using TMT.

 

Artificial intelligence and cardiology: Current status and perspective: Artificial Intelligence and Cardiology

The development of artificial intelligence (AI) began in the mid-20th century but has been rapidly accelerating in the past decade. Reflecting the development of digital health over the past few years, this trend is also seen in medicine. The field of cardiovascular medicine uses a wide variety and a large amount of biosignals, so there are many situations where AI can contribute. The development of AI is in progress for all aspects of the healthcare system, including the prevention, screening, and treatment of diseases and the prediction of the prognosis. AI is expected to be used to provide specialist-level medical care, even in a situation where medical resources are scarce. However, like other medical devices, the concept and mechanism of AI must be fully understood when used; otherwise, it may be used inappropriately, resulting in detriment to the patient. Therefore, it is important to understand what we need to know as a cardiologist handling AI. This review introduces the basics and principles of AI, then shows how far the current development of AI has come, and finally gives a brief introduction of how to start the AI development for those who want to develop their own AI.

Inherited and Acquired Rhythm Disturbances in Sick Sinus Syndrome, Brugada Syndrome, and Atrial Fibrillation: Lessons from Preclinical Modeling

Rhythm disturbances are life-threatening cardiovascular diseases, accounting for many deaths annually worldwide. Abnormal electrical activity might arise in a structurally normal heart in response to specific triggers or as a consequence of cardiac tissue alterations, in both cases with catastrophic consequences on heart global functioning. Preclinical modeling by recapitulating human pathophysiology of rhythm disturbances is fundamental to increase the comprehension of these diseases and propose effective strategies for their prevention, diagnosis, and clinical management. In silico, in vivo, and in vitro models found variable application to dissect many congenital and acquired rhythm disturbances. In the copious list of rhythm disturbances, diseases of the conduction system, as sick sinus syndrome, Brugada syndrome, and atrial fibrillation, have found extensive preclinical modeling. In addition, the electrical remodeling as a result of other cardiovascular diseases has also been investigated in models of hypertrophic cardiomyopathy, cardiac fibrosis, as well as arrhythmias induced by other non-cardiac pathologies, stress, and drug cardiotoxicity. This review aims to offer a critical overview on the effective ability of in silico bioinformatic tools, in vivo animal studies, in vitro models to provide insights on human heart rhythm pathophysiology in case of sick sinus syndrome, Brugada syndrome, and atrial fibrillation and advance their safe and successful translation into the cardiology arena.