Comparison of Arrhythmia Detection by 24-Hour Holter and 14-Day Continuous Electrocardiography Patch Monitoring

Flexible self-rectifying synapse array for energy-efficient edge multiplication in electrocardiogram diagnosis

Edge computing devices, which generate, collect, process, and analyze data near the source, enhance the data processing efficiency and improve the responsiveness in real-time applications or unstable network environments. To be utilized in wearable and skin-attached electronics, these edge devices must be compact, energy efficient for use in low-power environments, and fabricable on soft substrates. Here, we propose a flexible memristive dot product engine (f-MDPE) designed for edge use and demonstrate its feasibility in a real-time electrocardiogram (ECG) monitoring system. The f-MDPE comprises a 32 × 32 crossbar array embodying a low-temperature processed self-rectifying charge trap memristor on a flexible polyimide substrate and exhibits high uniformity and robust electrical and mechanical stability even under 5-mm bending conditions. Then, we design a neural network training algorithm through hardware-aware approaches and conduct real-time edge ECG diagnosis. This approach achieved an ECG classification accuracy of 93.5%, while consuming only 0.3% of the energy compared to digital approaches, highlighting the strong potential of this approach for emerging edge neuromorphic hardware.

Identifying Demographic Factors Affecting the ECG Duration Collected Using a Single-Lead ECG Patch Device

INTRODUCTION

Atrial fibrillation (AF), affecting 3% of the US adults, is the most common arrhythmia. While ambulatory electrocardiogram (ECG) monitoring is essential for AF detection, conventional technologies have diagnostic limitations due to AF's sporadic nature. ECG patches offer extended monitoring periods, though their effectiveness is primarily limited by deteriorating skin-electrode contact rather than battery or memory constraints.

OBJECTIVES

This analysis reports our experience with the Zio ECG patch (iRhythm, San Francisco, CA) in 256 AF patients.

METHOD

We analyzed human and technical factors and their association with ECG recording duration using previously recorded data which employed the ECG patch as a reference. Descriptive statistics and logistic regression were used to identify associations.

RESULTS

Body mass index (BMI) was found to be an independent predictor of poorer compliance in a dose-dependent manner (B = -0.046, OR = 0.955, 95% CI: 0.916-0.996, p = 0.033). Loss of adhesive was the primary reason for poor compliance (n = 25; 11%). These findings can guide researchers and clinicians in determining the appropriateness of a 14-day ECG patch based on expected wear time and patient compliance.

CONCLUSION

BMI significantly impacts ECG patch compliance, primarily through adhesive failures. These findings indicate the need for improved adhesive technologies for higher BMI patients. Future device development should prioritize maintaining electrode-skin contact across diverse patient populations.

TRIAL REGISTRATION

ClinicalTrials.gov Identifier: NCT04267133.

Usability and acceptability of ambulatory monitoring in undiagnosed syncope: insights from the ASPIRED-Q qualitative study

OBJECTIVES

The aim of this study, which was embedded into the ASPIRED randomised controlled trial (ISRCTN10278811), was to explore patient and healthcare professional usability and acceptability of an enhanced (14-day) ambulatory ECG monitoring patch to manage and facilitate discharge of emergency department patients with unexplained syncope.

DESIGN

A qualitative study using semistructured interviews. Data were analysed using thematic analysis and mapped using the theoretical framework of acceptability.

PARTICIPANTS

A sample of 20 syncope patients recruited to the ASPIRED RCT and 10 healthcare professionals who had a direct care provider and clinical decision role for syncope patients (eg, consultants, junior doctors, advanced nurse practitioners, advanced care practitioners, emergency nurse practitioners and physician associates) were recruited from four hospitals (two in England and two in Scotland) between February 2023 and January 2024.

RESULTS

Three overarching themes developed that mapped to six of the seven constructs within the theoretical framework of acceptability. The themes were: (1) Efficacy: Patients and healthcare professionals felt that the remote intervention would increase patient reassurance. Healthcare professionals perceived the intervention would improve clinical care pathways by overcoming delays for Holter monitors, but that a standard protocol would be required to ensure appropriate intervention use. (2) Burden: Patients considered that the device was non-obstructive and easy to use. However, healthcare professionals noted that although attaching the device was simple, there would be associated time and resource costs (eg, documentation). (3) Communication and education: Comprehensive verbal and written information were considered necessary to ensure that the intervention was usable by, and acceptable to, patients. Healthcare professionals suggested additional training would be required. Additionally, they considered that feedback from patient monitoring would reinforce their decision-making and improve healthcare professionals' self-efficacy to use the device appropriately.

CONCLUSIONS

An immediate, enhanced (14-day) ambulatory ECG monitoring patch was positively received by patients and offered healthcare professionals an acceptable route for monitoring emergency department patients with unexplained syncope. However, future use should be controlled using standardised pathways to prevent inappropriate use.

TRIAL REGISTRATION NUMBER

ISRCTN10278811.

Clinical applications of artificial intelligence and machine learning in neurocardiology: a comprehensive review

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.

Enhancing Comprehensive Assessments in Chronic Heart Failure Caused by Ischemic Heart Disease: The Diagnostic Utility of Holter ECG Parameters

Background and Objectives: Chronic heart failure (CHF) caused by ischemic heart disease (IHD) is the leading cause of death worldwide and presents significant health challenges. Effective management of IHD requires prevention, early detection, and treatment to improve patient outcomes. This study aims to expand the diagnostic utility of various 24 h Holter ECG parameters, such as T-wave alternans (TWA), late ventricular potentials (LVPs), and heart rate variability (HRV) in patients with CHF caused by IHD. Additionally, we seek to explore the association between these parameters and other comorbid conditions affecting the prognosis of CHF patients. Materials and Methods: We conducted a prospective case-control study with 150 patients divided into two subgroups: 100 patients with CHF caused by IHD, and 50 patients in the control group. Data included medical history, physical examination, laboratory tests, echocardiography, and 24 h Holter monitoring. Results: Our comparative analysis demonstrated that both TWA and LVPs were significantly higher in patients with CHF compared to the control group (p < 0.01), indicating increased myocardial electrical vulnerability in CHF patients. Both time and frequency-domain HRV parameters were significantly lower in the CHF group. However, the ratio of NN50 to the total count of NN intervals (PNN50) showed a borderline significance (p = 0.06). While the low-frequency (LF) domain was significantly lower in CHF patients, the high-frequency (HF) domain did not differ significantly between groups. Acceleration and deceleration capacities were also significantly altered in CHF patients. Categorizing CHF patients by left ventricular ejection fraction (LVEF) revealed that the mean of the 5-min normal-to-normal intervals over the complete recording (SDNN Index) was significantly higher in patients with LVEF ≥ 50% compared to those with CHF with reduced EF and CHF with mildly reduced EF (p < 0.001), whereas the other HRV parameters showed no significant differences among the groups. Conclusions: Holter ECG parameters can become a reliable tool in the assessment of patients with CHF. The integration of multiple Holter ECG parameters, such as TWA, LVPs, and HRV, can significantly enhance the diagnostic assessment of CHF caused by IHD. This comprehensive approach allows for a more nuanced understanding of the patient's condition and potential outcomes.

Approaches of wearable and implantable biosensor towards of developing in precision medicine

In the relentless pursuit of precision medicine, the intersection of cutting-edge technology and healthcare has given rise to a transformative era. At the forefront of this revolution stands the burgeoning field of wearable and implantable biosensors, promising a paradigm shift in how we monitor, analyze, and tailor medical interventions. As these miniature marvels seamlessly integrate with the human body, they weave a tapestry of real-time health data, offering unprecedented insights into individual physiological landscapes. This log embarks on a journey into the realm of wearable and implantable biosensors, where the convergence of biology and technology heralds a new dawn in personalized healthcare. Here, we explore the intricate web of innovations, challenges, and the immense potential these bioelectronics sentinels hold in sculpting the future of precision medicine.

A Review on Atrial Fibrillation Detection From Ambulatory ECG

Atrial fibrillation (AF) is a prevalent clinical arrhythmia disease and is an important cause of stroke, heart failure, and sudden death. Due to the insidious onset and no obvious clinical symptoms of AF, the status of AF diagnosis and treatment is not optimal. Early AF screening or detection is essential. Internet of Things (IoT) and artificial intelligence (AI) technologies have driven the development of wearable electrocardiograph (ECG) devices used for health monitoring, which are an effective means of AF detection. The main challenges of AF analysis using ambulatory ECG include ECG signal quality assessment to select available ECG, the robust and accurate detection of QRS complex waves to monitor heart rate, and AF identification under the interference of abnormal ECG rhythm. Through ambulatory ECG measurement and intelligent detection technology, the probability of postoperative recurrence of AF can be reduced, and personalized treatment and management of patients with AF can be realized. This work describes the status of AF monitoring technology in terms of devices, algorithms, clinical applications, and future directions.

Holter ECG for Syncope Evaluation in the Internal Medicine Department-Choosing the Right Patients

Physicians use Holter electrocardiography (ECG) monitoring to evaluate some patients with syncope in the internal medicine department. We questioned whether Holter ECG should be used in the presented setting. Included were all consecutive patients admitted with syncope to one of our nine internal medicine departments who had completed a 24 h Holter ECG between 2018 and 2021. A diagnostic Holter was defined as one which altered the patient’s treatment and met ESC/ACC/AHA diagnostic criteria. A total of 478 Holter tests were performed for syncope evaluation during admission to an internal medicine department in the study period. Of them, 25 patients (5.2%) had a diagnostic Holter finding. Sinus node dysfunction was the most frequent diagnostic recording (13 patients, 52%). In multivariant analysis, predictors for diagnostic Holter were older age (OR 1.35, 95% CI 1.08−1.68), heart failure with preserved ejection fraction (OR 4.1, 95% CI 1.43−11.72), and shorter duration to Holter initiation (OR 0.73, 95% CI 0.56−0.96). There was a positive correlation between time from admission to Holter and hospital stay, r(479) = 0.342, p < 0.001. Our results suggest that completing a 24 h Holter monitoring during admission to the internal medicine department should be restricted to patients with a high pre-test probability to avoid overuse and possible harm.

Continuous 24-h Photoplethysmogram Monitoring Enables Detection of Atrial Fibrillation

Aim: Atrial fibrillation (AF) detection is challenging because it is often asymptomatic and paroxysmal. We evaluated continuous photoplethysmogram (PPG) for signal quality and detection of AF.

Methods: PPGs were recorded using a wrist-band device in 173 patients (76 AF, 97 sinus rhythm, SR) for 24 h. Simultaneously recorded 3-lead ambulatory ECG served as control. The recordings were split into 10-, 20-, 30-, and 60-min time-frames. The sensitivity, specificity, and F1-score of AF detection were evaluated for each time-frame. AF alarms were generated to simulate continuous AF monitoring. Sensitivities, specificities, and positive predictive values (PPVs) of the alarms were evaluated. User experiences of PPG and ECG recordings were assessed. The study was registered in the Clinical Trials database (NCT03507335).

Results: The quality of PPG signal was better during night-time than in daytime (67.3 ± 22.4% vs. 30.5 ± 19.4%, p < 0.001). The 30-min time-frame yielded the highest F1-score (0.9536), identifying AF correctly in 72/76 AF patients (sensitivity 94.7%), only 3/97 SR patients receiving a false AF diagnosis (specificity 96.9%). The sensitivity and PPV of the simulated AF alarms were 78.2 and 97.2% at night, and 49.3 and 97.0% during the daytime. 82% of patients were willing to use the device at home.

Conclusion: PPG wrist-band provided reliable AF identification both during daytime and night-time. The PPG data’s quality was better at night. The positive user experience suggests that wearable PPG devices could be feasible for continuous rhythm monitoring.

Machine Learning for Cardiovascular Outcomes From Wearable Data: Systematic Review From a Technology Readiness Level Point of View

BACKGROUND

Wearable technology has the potential to improve cardiovascular health monitoring by using machine learning. Such technology enables remote health monitoring and allows for the diagnosis and prevention of cardiovascular diseases. In addition to the detection of cardiovascular disease, it can exclude this diagnosis in symptomatic patients, thereby preventing unnecessary hospital visits. In addition, early warning systems can aid cardiologists in timely treatment and prevention.

OBJECTIVE

This study aims to systematically assess the literature on detecting and predicting outcomes of patients with cardiovascular diseases by using machine learning with data obtained from wearables to gain insights into the current state, challenges, and limitations of this technology.

METHODS

We searched PubMed, Scopus, and IEEE Xplore on September 26, 2020, with no restrictions on the publication date and by using keywords such as "wearables," "machine learning," and "cardiovascular disease." Methodologies were categorized and analyzed according to machine learning-based technology readiness levels (TRLs), which score studies on their potential to be deployed in an operational setting from 1 to 9 (most ready).

RESULTS

After the removal of duplicates, application of exclusion criteria, and full-text screening, 55 eligible studies were included in the analysis, covering a variety of cardiovascular diseases. We assessed the quality of the included studies and found that none of the studies were integrated into a health care system (TRL<6), prospective phase 2 and phase 3 trials were absent (TRL<7 and 8), and group cross-validation was rarely used. These issues limited these studies' ability to demonstrate the effectiveness of their methodologies. Furthermore, there seemed to be no agreement on the sample size needed to train these studies' models, the size of the observation window used to make predictions, how long participants should be observed, and the type of machine learning model that is suitable for predicting cardiovascular outcomes.

CONCLUSIONS

Although current studies show the potential of wearables to monitor cardiovascular events, their deployment as a diagnostic or prognostic cardiovascular clinical tool is hampered by the lack of a realistic data set and proper systematic and prospective evaluation.

Arrhythmia Detection is Improved by 14-Day Continuous Electrocardiography Patch Monitoring and CHA2DS2-VASc Score

BACKGROUND

Arrhythmias are not always easy to capture because they are often paroxysmal or asymptomatic.

METHODS

Using the CHA2DS2-VASc score for arrhythmia risk assessment, a 14-day electrocardiography monitor patch was used to evaluate patients with no documented history of arrhythmia.

RESULTS

Ninety-three patients (mean age 59.8 ± 12.0 years, 46.2% female) received 14-day electrocardiography telemonitoring, and 14 patients (15%) were diagnosed with arrhythmias during a follow-up of 1004.4 person-days (mean recorded days 10.8 ± 4.1). The patients who were detected to have arrhythmias were older and had a higher prevalence of heart failure and chronic kidney disease. The result showed that arrhythmias were more likely to develop during a 14-day monitoring period in the patients with a CHA2DS2-VASc score of ≥ 3 or ≥ 4. Atrioventricular block was more likely to be detected in the patients with a CHA2DS2-VASc score of ≥ 3 or ≥ 4 during 7-day or 14-day monitoring periods. Ventricular tachycardia was also more likely to be detected in the patients with a CHA2DS2-VASc score of ≥ 4 or ≥ 5 during a 14-day monitoring period. When evaluating the risk of arrhythmia, a CHA2DS2-VASc score of ≥ 3 or ≥ 4 was associated with a higher risk of any arrhythmias during a 14-day monitoring period, while a CHA2DS2-VASc score of ≥ 4 was associated with a higher risk of any arrhythmias during a 7-day monitoring period.

CONCLUSIONS

The results may suggest that a 14-day monitoring period is more favorable to detect arrhythmias. Atrioventricular block and ventricular tachycardia were more likely to develop in the patients with a higher CHA2DS2-VASc score.