Atrial fibrillation (AF) is the most common sustained cardiac arrhythmia characterized by consistently irregular atrial and ventricular contractions. Heart rate variability (HRV) refers to the changes in the intervals between consecutive ventricular heartbeats. In sinus rhythm, HRV may be subtle and is quantitatively reflecting the dynamic interplay of the cardiac autonomic nervous system, which plays a crucial role in the onset, development, and maintenance of AF. HRV metrics, consisting of time-domain, frequency-domain, and nonlinear parameters, have been verified to vary significantly before and after AF episodes, and AF treatment-related procedures such as electrical cardioversion, ablation, and surgery of AF. Therefore, HRV may serve as a digital biomarker in predicting AF risk in long-term and acute risk period, identification of patients with AF risk in sinus rhythm and recurrence risk stratification after procedures. HRV in AF rhythm, predominantly influenced by dynamic atrioventricular node conduction under the onslaught of irregular atrial impulses, shows a huge disparity compared to that in sinus rhythm. Despite this, HRV in AF rhythm still provides valuable prognostic information, as reduced HRV may indicate a poor heart function and outcomes in patients with AF. Despite being influenced by lots of variables, HRV can still serve as an independent digital biomarker in the clinical management of AF throughout its entire lifecycle.

Insertable cardiac monitors (ICMs) are valuable diagnostic tools for detecting cardiac arrhythmias, yet their nationwide implications remain underreported. We aimed to assess comprehensive outcome data for the Korean population receiving ICM insertions.

Using a Korean nationwide claims database, patients who underwent ICM insertion from 2010 to 2021 (N = 3152) were selected. The subjects were divided into three groups based on the indication of the procedure: recurrent syncope (n = 1389), palpitation (n = 146), cryptogenic stroke (n = 994) and unidentifiable (n = 623). The clinical outcomes, including new diagnoses of arrhythmias and therapeutic interventions following ICM insertion, were evaluated in each group.

Median follow-up duration was 18.5 months (interquartile range: 7.3-33.7). In the syncope group, pacemaker and implantable cardioverter defibrillator were implanted in 396 (28.5 %) and 27 (1.9 %) patients following ICM insertion. Age (≥70 vs. <60, Hazard ratio [HR]: 2.090, p < 0.001) and prevalent atrial fibrillation (AF) or flutter (AFL)(HR: 1.891, p < 0.001) were independent risk factors for the cardiac device therapy. In the palpitation group, various arrhythmias, including AF/AFL (n = 7), supraventricular tachycardia (n = 2), and other arrhythmias (n = 13), were identified in 19 (13.6 %) patients. In the cryptogenic stroke group, new-onset AF/AFLs occurred in 91 (9.7 %) patients. The initiation of direct oral anticoagulants was noted in 8.9 % of anticoagulation-naïve cryptogenic stroke patients during follow-up.

ICM insertion led to significant diagnostic and therapeutic interventions across all indication groups, with notable rates of device implantation and arrhythmia detection. These findings underscore the clinical value of ICMs in guiding patient management and improving outcomes across various cardiac conditions.

Systematic screening individuals with non-invasive devices may improve diagnosis of atrial fibrillation (AF) and reduce adverse clinical events. We systematically reviewed the existing literature to determine the yield of new AF diagnosis associated with systematic AF screening, the relative increase in yield of new AF diagnosis with systematic screening compared to usual care, and the effect of systematic AF screening on clinical outcomes compared with usual care.

The Medline, Embase, Web of Science and Cochrane Library databases were searched from inception through 1st February 2025 for prospective cohort studies or randomised clinical trials (RCTs) of systematic AF screening with the outcome of incidence of previously undiagnosed AF from screening. Incidence rates (IR) and relative risks were calculated and random effects meta-analysis performed to synthesise rates of AF in prospective cohort studies and RCTs, as well as outcomes in RCTs.

From 3806 unique records we included 32 studies representing 735,542 participants from 8 RCTs and 24 prospective cohorts. The diagnosis rate for incident AF in prospective cohorts was 2.75% (95% CI 1.87-3.62), and the pooled relative risk in RCTs was 2.22 (95% CI 1.41-3.50). The use of age and NT-proBNP (IR 4.36%, 95% CI 3.77-5.08) or AF risk score classification (4.79%, 95% CI 3.62-6.29) led to higher new AF diagnosis yields than age alone (0.93%, 95% CI 0.28-2.99). Pooled data from RCTs did not demonstrate an effect of screening on death (RR 1.01, 95% CI 0.97-1.05), cardiovascular hospitalisation (1.00, 95% CI 0.97-1.03), stroke (0.95, 95% CI 0.87-1.04) or bleeding (1.08, 95% CI 0.91-1.29).

Systematic screening for AF using non-invasive devices is associated with increased diagnosis of AF, but not reduced adverse clinical events. Screening studies of AF utilising alternative risk stratifications and outcome measures are required.

British Heart Foundation (grant reference CC/22/250026) and National Institute for Health and Care Research.

A limited number of studies with smartwatches (SWs) investigated their potential in the field of heart failure (HF). The aim of this scoping review is to understand the extent of current literature on SWs in the HF population and the device's potential to improve disease management. The literature search was performed on PubMed and Embase in March 2024. Inclusion criteria included the use of commercialized SWs, HF diagnosis and peer-reviewed publications. Articles were excluded if the SW was not the study intervention or was part of a broader intervention programme. Reviews, case reports and study protocols were excluded. Of 1200 identified articles, 13 were included in the scoping review, encompassing 1171 patients with HF, and findings were presented in a descriptive summary table. Validity of several SW-collected physiological metrics was assessed against established technologies. Heart rate and step count measures were deemed moderately accurate in the HF population with Fitbit trackers (n = 5 patients, r = 0.54) and Garmin watches [n = 15 patients (mean age: 65.5 ± 12.6 years), concordance correlation coefficient (CCC) = 0.89 for Vivofit 1 and CCC = 0.92 for Vivofit 3], respectively, while calorimetry was the least reliable measurement [n = 19 patients (mean age: 65.1 ± 6.6 years), mean difference to indirect calorimeter: P = 0.01 for Fitbit Charge 2, P = 0.02 for Mio Slice]. Wrist-worn activity trackers were positively received by patients with HF [91.3% of adherence in research setting (n = 70 patients, median age (IQR): 79 years (76-82)), and 64% in real-world environment (n = 14 patients)] and their health-care providers (six cardiologists out of six acknowledged the data's usefulness), although device ownership ranged from 10 to 50% among the HF population. Physical activity information collected from SWs was found to be valuable in assisting cardiologists with their New York Heart Association (NYHA) functional class assessment, which is known for its limited objectivity and reproducibility. Multiple studies found that SWs, especially Fitbit devices, successfully identified a pattern where the degree of exercise intolerance increased with higher NYHA classes. These findings suggested that activity trackers can objectively evaluate the severity of physical activity limitations. As the functional classification of patients influences treatment strategies, SWs could serve as a valuable tool to facilitate and optimize outpatient disease management. SWs could be used as a complement to standard monitoring in HF. With continuous technological advances, it will be valuable to follow the deployment of SWs and to investigate their contribution to increased patient safety and consequently to health care cost reductions.

The aging of society drives a rising demand for geriatric healthcare due to increased care needs and extended hospital stays in old age. Despite strained social security systems, ensuring high-quality medical care requires innovative solutions. Digitalization could be one of them, however older people, who are less digitally active, may not fully recognize its benefits. This study aims to assess digital participation among geriatric hospital patients and their views on continuous vital sign monitoring using wearables.

The survey was conducted at the geriatric hospital "Krankenhaus Rotes Kreuz Lübeck - Geriatriezentrum" to assess the digital participation of higher frailty patients requiring increased care. The questioning occurred between February 13th and March 10th, 2023. The questionnaire included demographic questions, questions about digital participation and digital skills, opinions on continuous monitoring, and a reflection on the impact of the coronavirus pandemic on internet use.

Of the 201 consecutively admitted patients, 52 were excluded from participation in the study based on the inclusion/exclusion criteria, mostly due to illness. Of the remaining 149 invited patients, 66 (44.2%) agreed to be interviewed, mostly females (76%) with an average age of 81.2 years (SD = 7.1). As a result, 68.2% of participants reported online activity, whereby females and those with low education or high age (p = 0.027) were offline more often. On average, 1-2 internet-enabled devices were used. Continuous vital sign monitoring was favoured by 32 participants and 61 expressed no concerns.

Our findings align with previous studies involving participants of comparable age, indicating comparable results, apart from disease-related participation restrictions. However, the significant proportion of patients who did not want to participate (55.7%) and the analysis of the reasons for nonparticipation suggest that the actual number of geriatric patients who do not engage online is higher. While this does not necessarily imply a complete rejection of digital products by this demographic, it highlights the need for greater emphasis on usability, feasibility, and clarification in future endeavors.

Frequent premature ventricular complexes (PVCs) can lead to adverse health conditions such as cardiomyopathy. The linear correlation between PVC frequency and heart rate (as positive, negative, or neutral) on a 24-hour Holter recording has been proposed as a way to classify patients and guide treatment with beta-blockers. Our objective was to evaluate the robustness of this classification to measurement methodology, different 24-hour periods, and nonlinear dependencies of PVCs on heart rate.

We analyzed 82 multi-day Holter recordings (1-7 days) collected from 48 patients with frequent PVCs (burden 1%-44%). For each record, linear correlation between PVC frequency and heart rate was computed for different 24-hour periods and using different length intervals to determine PVC frequency.

Using a 1-hour interval, the correlation between PVC frequency and heart rate was consistently positive, negative, or neutral on different days in only 36.6% of patients. Using shorter time intervals, the correlation was consistent in 56.1% of patients. Shorter time intervals revealed nonlinear and piecewise linear relationships between PVC frequency and heart rate in many patients.

The variability of the correlation between PVC frequency and heart rate across different 24-hour periods and interval durations suggests that the relationship is neither strictly linear nor stationary. A better understanding of the mechanism driving the PVCs, combined with computational and biological models that represent these mechanisms, may provide insight into the observed nonlinear behavior and guide more robust classification strategies.

Linear correlation as a tool to classify patients with frequent PVCs should be used with caution. It is sensitive to the specific 24-hour period analyzed and the methodology used to segment the data. More sophisticated classification approaches that can capture nonlinear and time-varying dependencies should be developed and considered in clinical practice.

Current guidelines require physician confirmation for smartwatch-diagnosed atrial fibrillation (AF), increasing telemedicine workloads. The newest ChatGPT-4o (GPT-4o) incorporates advanced image input capabilities.

To assess GPT-4o's performance in identifying AF from smartwatch recordings.

Consecutive 120 patients with AF and 60 controls with sinus rhythm (SR), confirmed by conventional 12-lead ECG, recorded single-lead ECGs using an Apple Watch (AW) Series 6®. Two blinded cardiologists independently classified the smartwatch recordings as AF, SR, or undetermined. GPT-4o was subsequently prompted to analyze all smartwatch ECGs.

Six AF cases were excluded due to undetermined AW-ECG recordings, leaving 114 AF patients (mean age: 73.4 ± 10.4 years) and 60 controls. The AW algorithm achieved 97.3 % and 100 % accuracy for AF and SR, respectively, while GPT-4o correctly analyzed 47.3 % of AF and 71.6 % of SR tracings. None of the AF characteristics-chronicity, heart rate, QRS width, fibrillatory wave amplitude, or R-wave amplitude and polarity-were predictive of GPT-4o's diagnostic accuracy.

The current capabilities of GPT-4o are insufficient to make a reliable diagnosis of AF from smartwatch ECGs. Despite the theoretical appeal of leveraging this innovative technology for such purpose, the findings highlight that human expertise remains indispensable. Consumers must remain aware of the current limitations of this technology.

Wearable devices are increasingly used to detect arrhythmias, including life-threatening ventricular tachycardia (VT). This case highlights their role in clinical settings. A patient with prior surgical aortic valve replacement because of a bicuspid valve experienced symptomatic palpitations, and his smartwatch recorded a wide complex tachycardia at 165 beats/min. His presentation led to intensive care admission and later to a diagnosis of VT successfully treated with an implantable defibrillator and ultimately requiring radiofrequency ablation. Smartwatches provide a noninvasive tool for detecting arrhythmias like VT, using photoplethysmography and single-lead ECG. Limitations include validation gaps, false positives, and user activation. Integration into clinical practice requires updated guidelines, structured reimbursement, and legal clarity. This case demonstrates the critical role of smartwatch data in VT detection and management.

This review explores the role and impact of digital technology in cardiac rehabilitation (CR), assessing its potential to enhance patient outcomes and address barriers to CR delivery.

A comprehensive literature search was conducted using curated search terms to target CR studies using digital technologies as an adjunct to in-person CR or as part of remote (ie, asynchronous) or virtual (ie, synchronous audiovisual communication) formats. The literature search focused on studies that evaluated the implementation and efficacy of using digital technologies within CR.

Digital technology offers significant opportunities to improve CR by providing flexible and scalable solutions that can overcome traditional barriers to CR such as accessibility and capacity constraints. Remote or virtual CR delivery that incorporates digital technologies improves CR adherence and achieves similar improvements in exercise capacity when compared to in-person CR. While the majority of studies have focused on exercise, digital technologies are increasingly used to deliver comprehensive CR solutions as part of remote and virtual CR programs. However, challenges and gaps in the literature remain, such as the impact of digital literacy and promoting equitable CR access, particularly in high-risk and vulnerable populations. Further research needs to focus on longer term outcomes to evaluate the safety, efficacy, and cost-effectiveness of digital CR interventions. The potential of digital health to transform CR and reduce the burden of cardiovascular disease is substantial and warrants further investigation.

The use of wearable devices for remote health monitoring is a rapidly expanding field. These devices might benefit patients and providers; however, they are not yet widely used in healthcare. This scoping review assesses the current state of the literature on wearable devices for remote health monitoring in non-hospital settings.

CINAHL, Scopus, Embase and MEDLINE were searched until August 5, 2024. We performed citation searching and searched Google Scholar. Studies on wearable devices in an outpatient setting with a clinically relevant, measurable outcome were included and were categorized according to intended use of data: monitoring of existing disease vs. diagnosis of new disease.

Eighty studies met eligibility criteria. Most studies used device data to monitor a chronic disease (68/80, 85%), most often neurodegenerative (22/68, 32%). Twelve studies (12/80, 15%) used device data to diagnose new disease, majority being cardiovascular (9/12, 75%). A range of wearable devices were studied with watches and bracelets being most common (50/80, 63%). Only six studies (8%) were randomized controlled trials, four of which (67%) showed evidence of positive clinical impact. Feasibility determinants were inconsistently reported, including compliance (51/80, 64%), patient-reported useability (13/80, 16%), and participant technology literacy (1/80, 1%).

Evidence for clinical effectiveness of wearable devices remains scant. Heterogeneity across studies in terms of devices, disease targets and monitoring protocols makes data synthesis challenging, especially given the rapid pace of technical innovation. These findings provide direction for future research and implementation of wearable devices in healthcare.

Cardiac arrhythmias are a growing global health concern, and the need for accessible, continuous monitoring has driven rapid advancements in wearable technologies. This review explores the evolution, capabilities, and clinical impact of modern wearables for arrhythmia detection, including smartwatches, smart rings, ECG patches, and smart textiles. In light of the recent surge in commercially available wearables across all categories, this review offers a detailed comparative analysis of leading devices, evaluating cost, regulatory approval, model specifications, and system compatibility. Smartwatches and patches, in particular, show a strong performance in atrial fibrillation detection, with patches outperforming Holter monitors in long-term monitoring and diagnostic yield. This review highlights a paradigm shift toward patient-initiated diagnostics but also discusses challenges such as false positives, regulatory gaps, and healthcare integration. Overall, wearable devices hold significant promise for reshaping arrhythmia management through early detection and remote monitoring.

Ischemic heart disease (IHD) impacts the quality of life and has the highest mortality rate of cardiovascular diseases globally.

To compare variations in the parameters of the single-lead electrocardiogram (ECG) during resting conditions and physical exertion in individuals diagnosed with IHD and those without the condition using vasodilator-induced stress computed tomography (CT) myocardial perfusion imaging as the diagnostic reference standard.

This single center observational study included 80 participants. The participants were aged ≥ 40 years and given an informed written consent to participate in the study. Both groups, G1 (n = 31) with and G2 (n = 49) without post stress induced myocardial perfusion defect, passed cardiologist consultation, anthropometric measurements, blood pressure and pulse rate measurement, echocardiography, cardio-ankle vascular index, bicycle ergometry, recording 3-min single-lead ECG (Cardio-Qvark) before and just after bicycle ergometry followed by performing CT myocardial perfusion. The LASSO regression with nested cross-validation was used to find the association between Cardio-Qvark parameters and the existence of the perfusion defect. Statistical processing was performed with the R programming language v4.2, Python v.3.10 [^R], and Statistica 12 program.

Bicycle ergometry yielded an area under the receiver operating characteristic curve of 50.7% [95% confidence interval (CI): 0.388-0.625], specificity of 53.1% (95%CI: 0.392-0.673), and sensitivity of 48.4% (95%CI: 0.306-0.657). In contrast, the Cardio-Qvark test performed notably better with an area under the receiver operating characteristic curve of 67% (95%CI: 0.530-0.801), specificity of 75.5% (95%CI: 0.628-0.88), and sensitivity of 51.6% (95%CI: 0.333-0.695).

The single-lead ECG has a relatively higher diagnostic accuracy compared with bicycle ergometry by using machine learning models, but the difference was not statistically significant. However, further investigations are required to uncover the hidden capabilities of single-lead ECG in IHD diagnosis.

Embarking on a journey into the future of health care shaped by technological advances and the impact of the COVID-19 pandemic, we delve into the transformative landscape shaped by the integration of wearable technology, medically regulated devices, and advanced software. The ability to offer consumers unprecedented access to vital signs, advanced biomarkers, and environmental data enables a host of new capabilities to fill gaps in existing knowledge and permit individualized insights and education. Continuous monitoring enables individualized insights, emphasizing the need for a redefinition of health and human performance that is decentralized, dynamic, and personalized. The challenge lies in managing the massive amounts of continuous wearable data, necessitating new definitions of health data and secure practices. The COVID-19 pandemic has accelerated the adoption of digitalized consumer-facing diagnostics and software, transforming the traditional patient role. Consumers now have the tools to identify and understand an impending or existing disease state before they encounter traditional health care delivery health systems, making self-diagnosis commonplace. This shift empowers consumers to actively participate in their health, contributing to a new era where patients are in control of their well-being, from wellness to disease. Physicians in 2025 will engage with more informed and educated consumers, leveraging advanced analytic tools for diagnostics and streamlined patient management. Wearable devices play a pivotal role in enhancing patient engagement, while virtual reality and tailored software can be used by physicians to offer immersive learning experiences about conditions or upcoming procedures. Clinician decision support models and virtual care solutions will contribute to recruiting and maintaining health care providers amid a growing workforce shortage. Health care delivery organizations are transforming to improve outcomes at a lower cost, with partnerships with digital technology companies enabling innovative care models. This marks a historic moment where digital health and human performance solutions empower consumers to actively participate in their care. Physicians embrace digital tools, fostering richer patient partnerships, while health care organizations seize unprecedented opportunities for multilocation care delivery, addressing cost, workforce, and outcome challenges.

Early detection of obstructive sleep apnea (OSA) is critical due to its link to cardiovascular diseases. Our previous study validated an algorithm-based photoplethysmography (PPG) smartwatch for OSA risk detection.

This study aimed to characterize OSA features and assess its association with arrhythmia risk among smart wearable device (SWD) consumers in China in a real-world setting.

Between December 15, 2019, and January 31, 2022, SWD consumers across China were screened for OSA risk using HUAWEI devices. OSA diagnosis was confirmed via telecare follow-ups, including clinical evaluations and sleep test records. Disease characteristics and arrhythmia risks were analyzed.

In a large cohort of 1,056,494 participants, smart wearable devices (SWDs) effectively identified 19,563 individuals at high risk for OSA, with 1054 confirmed cases. OSA patients demonstrated high prevalence of obesity (46.8%), hypertension (19.8%), and arrhythmia (17.17%). SWDs detected abnormal heart rhythms or suspected arrhythmia in 95.9% of confirmed OSA cases. Age emerged as an independent predictor of arrhythmia risk, while hypertensive OSA patients were older, more obese, and experienced prolonged nocturnal hypoxia (Time length of SpO2<90%, P=0.020). These findings underscore the utility of SWDs in OSA screening and highlight the significant cardiovascular risks associated with OSA.

PPG-based SWD effectively screened for OSA and identified elevated arrhythmia risks. These findings support their utility for large-scale OSA screening and highlight cardiovascular risks management.

Mobile Health (mHealth) technology for improved screening, patient involvement and optimizing integrated care in atrial fibrillation.

ChiCTR-OOC-17014138.

2017-12-26.

2018-11-18.

Atrial fibrillation (AF) is a common complication after cardiothoracic surgery, affecting up to 50 % of patients. It can develop after discharge, leading to frequent hospital readmissions. There is a growing need for effective monitoring strategies to detect AF in the post-discharge period.

To synthesis the available literature on various mobile monitoring devices used to detect AF in adult cardiac surgery patients post-discharge from the hospital.

Following Arksey and O'Malley's framework and the PRISMA-ScR guidelines. A comprehensive search of six databases (PubMed; MEDLINE; CINAHL; Scopus; ProQuest; and Web of Science) was performed, including studies published between 2009 and 2024. The risk of bias was assessed using the Newcastle-Ottawa Scale (NOS).

A total of 1256 de-duplicated studies were screened, and 102 studies underwent full-text review. Five studies were included: four prospective cohort studies, and one randomised clinical trial. Samples sizes ranged from 23 to 730 adults undergoing cardiac surgery, with follow-up between four weeks to three months post-discharge. Handheld and wearable ECG-based devices were the most used tools for AF detection, demonstrating high sensitivity and specificity. Their use effectively reduced unplanned hospital visits and improved clinical outcomes. Patient adherence to monitoring protocols was generally high, though variability in engagement was noted.

Handheld and wearable ECG- based devices, are effective for post-discharge AF detection in cardiac surgery patients. Integrating these tools into routine post-discharge care can improve patient outcomes. Future research should focus on long-term effectiveness and strategies to optimise patient engagement and implementation in clinical practice.

Chronic non-communicable diseases (NCDs) pose a significant global health burden, exacerbated by aging populations and fragmented healthcare systems. This study employs a comprehensive literature review method to systematically evaluate the integration of medical and preventive services for chronic disease management in the context of big data, focusing on pre-hospital risk prediction, in-hospital clinical prevention, and post-hospital follow-up optimization. Through synthesizing existing research, we propose a novel framework that includes the development of machine learning models and interoperable health information platforms for real-time data sharing. The analysis reveals significant regional disparities in implementation efficacy, with developed eastern regions demonstrating advanced closed-loop management via unified platforms, while western rural areas struggle with manual workflows and data fragmentation. The integration of explainable AI (XAI) and blockchain-secured care pathways enhances clinical decision-making while ensuring GDPR-compliant data governance. The study advocates for phased implementation strategies prioritizing data standardization, federated learning architectures, and community-based health literacy programs to bridge existing disparities. Results show a 30-35% reduction in redundant diagnostics and a 15-20% risk mitigation for cardiometabolic disorders through precision interventions, providing a scalable roadmap for resilient public health systems aligned with the "Healthy China" initiative.

Atrial fibrillation (AF), the most common cardiac arrhythmia globally, contributes significantly to morbidity and mortality. With advancements in implantable devices like pacemakers, defibrillators, and loop recorders, incidental detection of AF as device-detected AF (DDAF) or subclinical AF (SCAF) has become common. This asymptomatic AF presents unique management challenges, particularly in anticoagulation decisions for stroke prevention. Evidence from recent trials, notably NOAH-AFNET 6 and ARTESiA, indicates a complex risk-benefit profile for anticoagulation in DDAF. In ARTESiA, anticoagulation modestly reduced stroke and systemic embolism rates, though this effect did not reach statistical significance. The NOAH-AFNET 6 trial found no significant reduction in a composite of cardiovascular death, stroke, or systemic embolism with anticoagulation compared to placebo. Both trials revealed an increased bleeding risk, underscoring the need to carefully weigh stroke prevention against bleeding risks in DDAF. The 2024 European Society of Cardiology guidelines reflect this nuanced approach by advocating a tailored, risk-based strategy. Emerging evidence also shows that AF burden impacts heart failure (HF) outcomes, with a five-fold increase in HF hospitalizations associated with higher AF burden. This highlights the importance of rhythm or rate control to reduce HF progression, particularly in patients with both AF and HF, where reducing AF burden is associated with better prognosis and fewer hospitalizations. Future research should focus on refining anticoagulation strategies, especially for patients with low AF burden, and exploring novel approaches like intermittent anticoagulation and advanced monitoring to support personalized DDAF management.

Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia, associated with significant morbidity, mortality, and healthcare burden. Despite advances in AF management, challenges persist in early detection, risk stratification, and treatment optimization, necessitating innovative solutions. Artificial intelligence (AI) has emerged as a transformative tool in AF care, leveraging machine learning and deep learning algorithms to enhance diagnostic accuracy, improve risk prediction, and guide therapeutic interventions. AI-powered electrocardiographic screening has demonstrated the ability to detect asymptomatic AF, while wearable photoplethysmography-based technologies have expanded real-time rhythm monitoring beyond clinical settings. AI-driven predictive models integrate electronic health records and multimodal physiological data to refine AF risk stratification, stroke prediction, and anticoagulation decision making. In the realm of treatment, AI is revolutionizing individualized therapy and optimizing anticoagulation management and catheter ablation strategies. Notably, AI-enhanced electroanatomic mapping and real-time procedural guidance hold promise for improving ablation success rates and reducing AF recurrence. Despite these advancements, the clinical integration of AI in AF management remains an evolving field. Future research should focus on large-scale validation, model interpretability, and regulatory frameworks to ensure widespread adoption. This review explores the current and emerging applications of AI in AF, highlighting its potential to enhance precision medicine and patient outcomes.

Neurocardiology is an evolving field focusing on the interplay between the nervous system and cardiovascular system that can be used to describe and understand many pathologies. Acute ischemic stroke can be understood through this framework of an interconnected, reciprocal relationship such that ischemic stroke occurs secondary to cardiac pathology (the Heart-Brain axis), and cardiac injury secondary to various neurological disease processes (the Brain-Heart axis). The timely assessment, diagnosis, and subsequent management of cerebrovascular and cardiac diseases is an essential part of bettering patient outcomes and the progression of medicine. Artificial intelligence (AI) and machine learning (ML) are robust areas of research that can aid diagnostic accuracy and clinical decision making to better understand and manage the disease of neurocardiology. In this review, we identify some of the widely utilized and upcoming AI/ML algorithms for some of the most common cardiac sources of stroke, strokes of undetermined etiology, and cardiac disease secondary to stroke. We found numerous highly accurate and efficient AI/ML products that, when integrated, provided improved efficacy for disease prediction, identification, prognosis, and management within the sphere of stroke and neurocardiology. In the focus of cryptogenic strokes, there is promising research elucidating likely underlying cardiac causes and thus, improved treatment options and secondary stroke prevention. While many algorithms still require a larger knowledge base or manual algorithmic training, AI/ML in neurocardiology has the potential to provide more comprehensive healthcare treatment, increase access to equitable healthcare, and improve patient outcomes. Our review shows an evident interest and exciting new frontier for neurocardiology with artificial intelligence and machine learning.

We evaluated validity, reliability, and effect of user expertise of "HaemoCalc", a mobile phone application for hematocrit (Hct) measurement from fingerpick blood samples, compared to a traditional Hawksley microhaematocrit reader (MHR). Experiment 1 examined the effect pitch angle during image capture exerted on the validity of Hct values. Twenty participants' samples were analyzed at 0°, 10°, and 20° directly over the sample, and 33° with a 10 cm setback. Analysis of variance (ANOVA) revealed a significant effect of angle on Hct values (p < 0.01). Measurements at 33° pitch differed from other angles and the MHR (p < 0.001, d = 2.31-3.06). Bland-Altman analysis showed good agreement at 0°, 10°, and 20° (mean differences: -0.4% to 1.0%) but poor agreement at 33° (mean difference: -4.4%, LOA: -0.7% to 8.4%). Experiment 2 assessed inter- and intra-rater reliability of expert and novice users (n = 12). Participants performed three trials each. HaemoCalc and MHR showed excellent reliability (ICC = 0.95-1.00). No differences were observed between experts and novices (p = 1.000, d = 0.01-0.39). HaemoCalc is a valid and reliable tool for Hct measurement at small pitch angles and in expert and novice users. The HaemoCalc app offers scalability, repeatability, health and safety benefits, and potential applications in medical education and remote learning.

Telehealth consultation with a physician can be an attractive option for eligible patients. In this pilot study, we evaluate the feasibility and efficiency of an FDA approved 12-lead electrocardiogram (ECG) device, Smeartheart, that can be used remotely in the patients' home before telehealth appointments with a cardiac electrophysiologist. We scheduled a phone call with 10 patients who used this device as part of their care. Eight patients were able to obtain a diagnostic quality ECG. Telephone call appointments with ECG technicians took a median of 51 minutes, and it took patients an average of 2.2 attempts to record a usable ECG. We also identified barriers to the use of the Smartheart device, including internet accessibility, training material, patient functional status, and motion artifact that may inform more widespread study and utilization of remote-recorded 12-lead ECGs. We conclude that the Smartheart device may have clinical use with remote use in routine clinical care, although the best use of this technology requires further study.

Artificial intelligence (AI) and machine learning (ML) are transforming the field of medicine. Health care organizations are now starting to establish management strategies for integrating such platforms (AI-ML toolsets) that leverage the computational power of advanced algorithms to analyze data and to provide better insights that ultimately translate to enhanced clinical decision-making and improved patient outcomes. Emerging AI-ML platforms and trends in pathology and medicine are reshaping the field by offering innovative solutions to enhance diagnostic accuracy, operational workflows, clinical decision support, and clinical outcomes. These tools are also increasingly valuable in pathology research in which they contribute to automated image analysis, biomarker discovery, drug development, clinical trials, and productive analytics. Other related trends include the adoption of ML operations for managing models in clinical settings, the application of multimodal and multiagent AI to utilize diverse data sources, expedited translational research, and virtualized education for training and simulation. As the final chapter of our AI educational series, this review article delves into the current adoption, future directions, and transformative potential of AI-ML platforms in pathology and medicine, discussing their applications, benefits, challenges, and future perspectives.

Atrial fibrillation (AF) is a common but often undiagnosed condition, increasing the risk of stroke and heart failure. Early detection is crucial, yet traditional methods struggle with AF's transient nature. This study investigates how augmenting ECG data with heart rate variability (HRV) and demographic data (age and sex) can improve AF detection.

We analysed 35 634 12-lead ECG recordings from three public databases (China Physiological Signal Challenge-Extra, PTB-XL and Georgia), each with physician-validated AF labels. A range of convolutional neural network models, including AlexNet, VGG-16, ResNet and transformers, were tested for AF prediction, enriched with HRV and demographic data to explore the effectiveness of the multimodal approach. Each data modality (ECG, HRV and demographic) was assessed for its contribution to model performance using fivefold cross-validation. Performance improvements were evaluated across key metrics, and saliency maps were generated to provide further insights into model behaviour and identify critical features in AF detection.

Integrating HRV and demographic data with ECG substantially improved performance. AlexNet and VGG-16 outperformed more complex models, achieving AUROC of 0.9617 (95% CI 0.95 to 0.97) and 0.9668 (95% CI 0.96 to 0.97), respectively. Adding HRV data showed the most significant improvement in sensitivity, with AlexNet increasing from 0.9117 to 0.9225 and VGG-16 from 0.9216 to 0.9225. Combining both HRV and demographic data led to further improvements, with AlexNet achieving a sensitivity of 0.9225 (up from 0.9192 with HRV) and VGG-16 reaching 0.9113 (up from 0.9097 with HRV). The combination of HRV and demographic data resulted in the highest gains in sensitivity and area under the receiver operating characteristic curve. Saliency maps confirmed the models identified key AF features, such as the absence of the P-wave, validating the multimodal approach.

AlexNet and VGG-16 excelled in AF detection, with HRV data improving sensitivity, and demographic data providing additional benefits. These results highlight the potential of multimodal approaches, pending further clinical validation.

Alpha-1 antitrypsin deficiency (AATD) is underdiagnosed, with a significant gap between documented cases and estimated prevalence. Attempts to bridge this gap include published guidelines emphasising the importance of screening for AATD and educational campaigns directed to the public. Early detection has clinical ramifications for optimal management of the patient with AATD, as well as for prevention of clinical disease in affected family members through early modification of environmental factors. Our case report describes a patient with minimally symptomatic chronic obstructive pulmonary disease with AATD, diagnosed in large part due to the patient detecting nocturnal hypoxaemia on her smartwatch. This highlights the emerging role of patient-initiated wearable health technology in diagnosing clinical conditions before traditional symptoms are significant, thus opening another potential avenue for bridging the gap between documented cases of AATD and the estimated prevalence.

The electrocardiogram (ECG) is one of the widespread diagnostic methods used in telemedicine. However, in the telemedicine systems, the data transfer process to the end user may suffer from security risks. Reversible watermarking can preserve the security of electrocardiograms and keep their original precision for correct diagnostics. In this paper, we present an extensive investigation of four reversible watermarking methods: prediction error expansion (PEE), reversible contrast mapping difference expansion (RCM), integer transform-based difference expansion (ITB), and compression-based watermarking. We discover new facets of the existing ECG watermarking methods (PEE and compression-based watermarking) and adapt image watermarking methods (RCM and ITB) to ECG signal. We compare different kinds of prediction and compression methods used in the studied methods and provide a watermark capacity comparison for different methods' implementations. The research results will help in watermarking method selection in practice.

Sports cardiology focuses on athletes' cardiovascular health, yet sudden cardiac death remains a significant concern despite preventative measures. Prolonged physical activity leads to notable cardiovascular adaptations, known as the athlete's heart, which can resemble certain pathological conditions, complicating accurate diagnoses and potentially leading to serious consequences such as unnecessary exclusion from sports or missed treatment opportunities. Wearable devices, including smartwatches and smart glasses, have become prevalent for monitoring health metrics, offering potential clinical applications for sports cardiologists. These gadgets are capable of spotting exercise-induced arrhythmias, uncovering hidden heart problems, and offering crucial information for training and recovery, to minimize exercise-related cardiac incidents and enhance heart health care. However, concerns about data accuracy and the actionable value of the obtained information persist. A major challenge lies in the integration of artificial intelligence with wearables, research gaps remain regarding their ability to provide real-time, reliable, and clinically relevant insights. Combining artificial intelligence with wearable devices can improve how data is managed and used in sports cardiology. Artificial intelligence, particularly machine learning, can classify, predict, and draw inferences from the data collected by wearables, revolutionizing patient data usage. Despite artificial intelligence's proven effectiveness in managing chronic conditions, the limited research on its application in sports cardiology, particularly regarding wearables, creates a critical gap that needs to be addressed. This review examines commercially available wearables and their applications in sports cardiology, exploring how artificial intelligence can be integrated into wearable technology to advance the field.

Atrial fibrillation (AF) is the most common arrhythmia. It increases the risk of hospitalization, heart failure, cognitive decline and mortality. It is the first cause of ischemic stroke. These are largely preventable if AF is diagnosed. It is essential to estimate the patient's embolic risk using the CHA2DS2-VA score, which now replaces the CHADS-Vasc score. Patients who require it must receive adequate anticoagulant treatment. New technologies (in particular, smart-watch) have led to advances in the detection and diagnosis of this arrhythmia. Patients suffering from AF may be treated with a heart rate control strategy (to limit tachycardia) or a rhythm control strategy (to maintain sinus rhythm). Catheter ablation is increasingly being offered to patients as an alternative to antiarrhythmic therapy. Controlling risk factors is essential to prevent the onset of AF, and to try to maintain sinus rhythm over the long term.

Cyber-attacks on healthcare entities and leaks of personal identifiable information (PII) are a growing threat. However, it is now possible to learn sensitive characteristics of an individual without PII, by combining advances in artificial intelligence, analytics, and online repositories. We discuss privacy threats and privacy engineering solutions, emphasizing the selection of privacy enhancing technologies for various healthcare cases. Future solutions must consider dynamic flows of data throughout their lifecycle.

Digital technologies are increasingly being implemented in health care to improve the quality and efficiency of care for patients. However, the rapid adoption of health technologies over the last 5 years has failed to adequately consider patient and clinician needs, which results in ineffective implementation. There is also a lack of consideration for the differences between patient and clinician needs, resulting in overgeneralized approaches to the implementation and use of digital health technologies.

This study aimed to explore barriers and facilitators of the implementation of digital technologies in the diagnosis of heart disease for both patients and clinicians, and to provide recommendations to increase the acceptability of novel health technologies.

We recruited 32 participants from across the United Kingdom, including 23 (72%) individuals with lived experience of heart disease and 9 (28%) clinicians involved in diagnosing heart disease. Participants with experience of living with heart disease took part in semistructured focused groups, while clinicians contributed to one-to-one semistructured interviews. Inductive thematic analysis using a phenomenological approach was conducted to analyze the resulting qualitative data and to identify themes. Results were discussed with a cardiovascular patient advisory group to enhance the rigor of our interpretation of the data.

Emerging themes were separated into facilitators and barriers and categorized into resource-, technology-, and user-related themes. Resource-related barriers and facilitators related to concerns around increased clinician workload, the high cost of digital technologies, and systemic limitations within health care systems such as outdated equipment and limited support. Technology-related barriers and facilitators included themes related to reliability, accuracy, safety parameters, data security, ease of use, and personalization, all of which can impact engagement and trust with digital technologies. Finally, the most prominent themes were the user-related barriers and facilitators, which encompassed user attitudes, individual-level variation in preferences and capabilities, and impact on quality of health care experiences. This theme captured a wide variety of perspectives among the sample and revealed how patient and clinician attitudes and personal experiences substantially impact engagement with digital health technologies across the cardiovascular care pathway.

Our findings highlight the importance of considering both patient and clinician needs and preferences when investigating the barriers and facilitators to effective implementation of digital health technologies. Facilitators to technology adoption include the need for cost-effective, accurate, reliable, and easy-to-use systems as well as adequate setup support and personalization to meet individual needs. Positive user attitudes, perceived improvement in care quality, and increased involvement in the care process also enhance engagement. While both clinicians and patients acknowledge the potential benefits of digital technologies, effective implementation hinges on addressing these barriers and leveraging facilitators to ensure that the technologies are perceived as useful, safe, and supportive of health care outcomes.

RR2-10.1136/bmjopen-2023-072952.

Atrial fibrillation (AF) is one of the most common cardiac diseases and a complicating comorbidity for multiple associated diseases. Many clinical decisions regarding AF are currently based on the binary recognition of AF being present or absent with the categorical appraisal of AF as continued or intermittent. Assessment of AF in clinical trials is largely limited to the time to (first) detection of an AF episode. Substantial evidence shows, however, that the quantitative characteristic of intermittent AF has a relevant impact on symptoms, onset, and progression of AF and AF-related outcomes, including mortality. Atrial fibrillation burden is increasingly recognized as a suitable quantitative measure of intermittent AF that provides an estimate of risk attributable to AF, the efficacy of antiarrhythmic treatment, and the need for oral anticoagulation. However, the diversity of assessment methods and the lack of a consistent definition of AF burden prevent a wider clinical applicability and validation of actionable thresholds of AF burden. To facilitate progress in this field, the AF burden Consensus Group, an international and multidisciplinary collaboration, proposes a unified definition of AF burden. Based on current evidence and using a modified Delphi technique, consensus statements were attained on the four main areas describing AF burden: Defining the characteristics of AF burden, the recording principles, the clinical relevance in major clinical conditions, and implementation as an outcome in the clinic and in clinical trials. According to this consensus, AF burden is defined as the proportion of time spent in AF expressed as a percentage of the recording time, undertaken during a specified monitoring duration. A pivotal requirement for validity and comparability of AF burden assessment is a continuous or near-continuous duration of monitoring that needs to be reported together with the AF burden assessment. This proposed unified definition of AF burden applies independent of comorbidities and outcomes. However, the disease-specific actionable thresholds of AF burden need to be defined according to the targeted clinical outcomes in specific populations. The duration of the longest episode of uninterrupted AF expressed as a time duration should also be reported when appropriate. A unified definition of AF burden will allow for comparability of clinical study data to expand evidence and to establish actionable thresholds of AF burden in various clinical conditions. This proposed definition of AF burden will support risk evaluation and clinical treatment decisions in AF-related disease. It will further promote the development of clinical trials studying the clinical relevance of intermittent AF. A unified approach on AF burden will finally inform the technology development of heart rhythm monitoring towards validated technology to meet clinical needs.

Most people do not recognize symptoms of neurological and cardiac emergencies in a timely manner. This leads to delays in hospital arrival and reduced access to therapies that can open arteries. We created a smartphone app to help patients and families evaluate if symptoms may be high risk for stroke or heart attack (myocardial infarction, MI). The ECHAS (Emergency Call for Heart Attack and Stroke) app guides users to assess their risk through evidence-based questions and a test of weakness in one arm by evaluating finger-tapping on the smartphone.

This study is an initial step in the accuracy evaluation of the app focused on sensitivity. We evaluated whether the app provides appropriate triage advice for patients with known stroke or MI symptoms in the Emergency Department. We designed this study to evaluate the sensitivity of the app, since the most dangerous output of the app would be failure to recognize the need for emergency evaluation. Specificity is also important, but the consequences of low specificity are less dangerous than those of low sensitivity.

In this single-center cross-sectional study, we enrolled patients presenting with symptoms of possible stroke or MI. The ECHAS app assessment consisted of a series of evidence-based questions regarding symptoms and a test of finger-tapping speed and accuracy on the phone's screen to detect unilateral arm weakness. The primary outcome was the sensitivity of the ECHAS app in detecting the need for ED evaluation. The secondary outcome was the sensitivity of the ECHAS app in detecting the need for hospital admission. Two independent and blinded board-certified physicians reviewed the medical record and adjudicated the appropriateness of the ED visit based on a 5-point score (ground truth). Finally, we asked patients semistructured questions about the app's ease of use, drawbacks, and benefits.

We enrolled 202 patients (57 with stroke and 145 with MI). The ECHAS score was strongly correlated with the ground truth appropriateness score (Spearman correlation 0.41, P<.001). The ECHAS app had a sensitivity of 0.98 for identifying patients in whom ED evaluation was appropriate. The app had a sensitivity of 1.0 for identifying patients who were admitted to the hospital because of their ED evaluation. Patients completed an app session in an average of 111 (SD 60) seconds for the stroke pathway and 60 (SD 33) seconds for the MI pathway. Patients reported that the app was easy to use and valuable for personal emergency situations at home.

The ECHAS app demonstrated a high sensitivity for the detection of patients who required emergency evaluation for symptoms of stroke or MI. This study supports the need for a study of specificity of the app, and then a prospective trial of the app in patients at increased risk of MI and stroke.

Recent advances have given rise to a spectrum of digital health technologies that have the potential to revolutionize the design and conduct of cardiovascular clinical trials. Advances in domain tasks such as automated diagnosis and classification, synthesis of high-volume data and latent data from adjacent modalities, patient discovery, telemedicine, remote monitoring, augmented reality, and in silico modelling have the potential to enhance the efficiency, accuracy, and cost-effectiveness of cardiovascular clinical trials. However, early experience with these tools has also exposed important issues, including regulatory barriers, clinical validation and acceptance, technological literacy, integration with care models, and health equity concerns. This narrative review summarizes the landscape of digital tools at each stage of clinical trial planning and execution and outlines roadblocks and opportunities for successful implementation of digital tools in cardiovascular clinical trials.

Passive cardiac monitoring has become synonymous with wearable technologies, necessitating patients to incorporate new devices into their daily routines. While this requirement may not be a burden for many, it is a constraint for individuals with chronic diseases who already have their daily routine. In this study, we introduce an innovative technology that harnesses the front-facing camera of smartphones to capture pulsatile signals discreetly when users engage in other activities on their device. We conducted a clinical study to gather real world evidence that passive video-based cardiac monitoring is feasible and it can be used to gather daily information about cardiac status of patients with a history of atrial fibrillation (AF). The study involved 16 patients who used an application called HealthKam AFib (HK) on their Android smartphone for a period of 14 days. They also wore an ECG patch during the first 7 days that was used as a reference device. Subjects were asked to also perform self testing procedures using video selfies twice a day, but measurements were also collected in the background during normal device usage. The 16 subjects had the HK app installed on their device during an average time period of 12.8±2.3 days. On average, the measurement rate was 2.1±1.6 measurements per hour of utilization of the smartphone. Heart rate measurements were found to be highly accurate, with a mean error equal to -0.3 bpm. The study revealed that passive facial video monitoring collected reliable data in real-world conditions.

Atrial fibrillation and heart failure are common cardiovascular conditions that are intricately linked to each other, with a significant impact on morbidity, mortality, and quality of life. These two conditions can create a vicious pathophysiologic milieu associated with neurohormonal changes, elevated cardiac filling pressure, myocardial remodeling, systemic and regional inflammation, fibrosis, and diminished myocardial contractility. It is well known that cardiomyopathy can cause atrial fibrillation and vice-versa, but often it is difficult to sort which came first. Unfortunately, the disease burden will only continue to rise with an aging population, and understanding the epidemiology of the disease and the interplay of these two conditions is vital to improved patient care.

The Apple Watch alerts users to irregular heart rhythms and potential atrial fibrillation (AF), but delays in obtaining electrocardiograms (ECGs) after notifications can impede accurate disease diagnosis. We aimed to predict personalized AF risk using continuous Apple Watch lifelog data to facilitate timely ECG acquisition. We conducted two analyses: Keio and national. In the Keio analysis, AF patients underwent continuous 2-week Holter ECG monitoring, and a machine-learning model combining gradient-boosting decision trees and deep learning was developed. The national analysis recruited Apple Watch users across Japan to assess the model; data and survey responses were collected for seven days via a dedicated iPhone app.

A total of 100 subjects (age: 63.9 ± 12.4 years, AF burden: 37.7 %) participated in the Keio analysis, while 8,935 subjects participated in the national analysis. Significant differences in Apple Watch data, including pulse rate (p < 0.001) and step count (p < 0.001), were observed between days with and without AF onset. Healthcare data measured by the Apple Watch, including sleep patterns, were significantly correlated with subjective survey responses (p < 0.001) and incorporated into the model. The model achieved an F-value of 90.7 % compared to diagnosis based on a 2-week Holter ECG. The model showed an additive benefit to Apple Watch irregular-rhythm notifications for AF detection (irregular-rhythm notification vs. model: 68.8 % vs. 88.2 % for paroxysmal AF and 84.4 % vs. 100.0 % for persistent AF).

Apple Watch-derived lifelogs enabled individualized AF onset risk assessment and the development of a machine-learning model for optimizing ECG timing for early AF detection.

Atrial fibrillation (AF), the most common arrhythmia in the United States, affects 6 million Americans, with numbers projected to increase to 12 million by 2030. A racial paradox difference in the incidence and prevalence of AF exists between Black and White Americans. Black Americans are less prone than White Americans to development of AF, but they display a higher burden of modifiable risk factors for cardiovascular disease and higher rates of ischemic stroke. Data pertaining to the American Heart Association Life's Simple 7 (LS7) health metrics show that Black Americans have suboptimal LS7 scores compared with White Americans on average despite lower genetic predisposition to AF. This trend suggests the impact of cardiovascular health on the development and progression of AF. Social, genetic, and lifestyle risk factors have been shown to play a role in the racial paradox and AF outcomes in Black Americans. This review summarizes factors contributing to the racial paradox and discusses suggestions for improved health outcomes in Black Americans with AF.

Cardiovascular morbidity and mortality rates are higher in hemodialysis (HD) patients, with an increased prevalence of arrhythmias. Atrial fibrillation (AF) is an independent risk factor for mortality and thromboembolic events in dialysis patients. For a better understanding and management of AF in these patients, it is important to know its prevalence. The use of a portable device would be pioneering for this group of patients.

To screen HD patients for AF using a portable gadget and evaluate the device's diagnostic performance.

HD patients at a tertiary hospital underwent AF screening during HD sessions using MyDiagnostick® (Applied Biomedical Systems). Multiple data were collected to evaluate potential associations. Statistical significance was defined as p < 0.05.

388 patients were evaluated (female, 40.7%; mean age of 56.8 years old, SD ± 14.7; and HD time of 27 months, 10-57). Screening was positive in 16 (4.1%) patients. AF was confirmed by electrocardiogram in 7 (1.8%) patients. Male sex (p = 0.019), older age (p = 0.007), altered baseline electrocardiogram (p < 0.001), increased serum potassium (p = 0.021), reduced systolic blood pressure at the beginning of dialysis (p = 0.007), and stable angina (0.011) were associated with positive screening for AF. The device presented a 91.74% specificity (95% CI, 86.65% to 96.91%) and 100% sensitivity (95% CI, 100% to 100%), with a negative predictive value of 100% (95% CI, 100% to 100%) for AF screening.

The use of this device proved to be practical, with high sensitivity and excellent negative predictive value. Subclinical AF has a high prevalence and may be underestimated in this population.