Arrhythmia Detection Research Articles

ECG diagnosis for arrhythmia detection with a cloud-based service and a wearable sensor network in a smart city environment

Irregular heartbeats are a primary indicator of Cardiovascular Disease (CVD), which is the leading cause of death in a developing smart city environment. Wearable devices can reliably monitor cardiac beats by producing Electrocardiogram (ECG) readings. The considerable value gained from a wireless wearable system allows for remote ECG assessment with continuous real-time functionality. The data collected from the wearable sensor network in the smart city platform gives timely alarms and treatment that could save lives. Cloud-based ECG methods can be accurate to a certain extent, as latency is still an existing problem. Cloud-based portals linked immediately to wearable devices can provide numerous advantages, such as reduced latency and a good level of service. Therefore, a novel cloud-based arrhythmia detection using the Recurrent Neural Network (RNN) (NC-RNN) method has been proposed for the ECG diagnosis with a wearable sensor in the smart city environment. The ECG signal collected from the wearable sensor involves three phase diagnosis stage. R-peak detection techniques are used for preliminary diagnostics in edge devices. The ECG signals are then classified using RNN at the edge device, with the severity of irregular beat detected in the ECG signal. Finally, a cloud platform classification method can evaluate the obtained ECG signals. While the proposed method's training session is runnable on the technically rich Cloud data centers, the interpretation unit is deployed over the cloud infrastructure for evaluating the ECG signals and setting off the emergency remedies with minimum latency. The simulation results of the suggested framework can accomplish effective ECG detection via wearable devices with high accuracy and less latency.

Accuracy of Heart Rate Measurement with Wrist-Worn Wearable Devices in Various Skin Tones: a Systematic Review.

Wearable consumer technology allows for the collection of a growing amount of personal health data. Through the analysis of reflected LED light on the skin, heart rate measurement and arrhythmia detection can be performed. Given that melanin alters skin light absorption, this study seeks to summarize the accuracy of cardiac data from wrist-worn wearable devices for participants of varying skin tones. We conducted a systematic review, searching Embase, MEDLINE, CINAHL, and Cochrane for original studies that stratified heart rate and rhythm data for consumer wearable technology according to participant race and/or skin tone. A total of 10 studies involving 469 participants met inclusion criteria. The frequency-weighted Fitzpatrick score for skin tone was reported in six studies (n = 293), with a mean participant score of 3.5 (range 1-6). Overall, four of the ten studies reported a significant reduction in accuracy of heart rate measurement with wearable devices in darker-skinned individuals, compared to participants with lighter skin tones. Four studies noted no effect of user skin tone on accuracy. The remaining two studies showed mixed results. Preliminary evidence is inconclusive, but some studies suggest that wearable devices may be less accurate for detecting heart rate in participants with darker skin tones. Higher quality evidence is necessary, with larger sample sizes and more objective stratification of participants by skin tone, in order to characterize potential racial bias in consumer devices.

A novel deep neural network heartbeats classifier for heart health monitoring

The electrocardiogram (ECG) is a very useful diagnostic tool to examine the functioning of the heart and to detect myocardial infarction (MI) and arrhythmias. It contains the records of the electrical signal of the heart and it is an investigation tool to check the heart's rhythm and thereby analyze heartbeats. Automatic detection of arrhythmia is possible by analyzing a patient's abnormal heartbeats and has become a major research area in recent years, as the manual examination of heart activity is time-consuming and prone to errors. Nowadays, the deployment of artificial intelligence (AI) - based algorithms to predict abnormal heartbeats categorized into five classes namely, non-ectopic (N), supra ventricular ectopic (S), ventricular ectopic (V), fusion (F) and unknown beats (Q) has drawn more attention in detecting arrhythmias. The use of intuitive hand-crafted features with shallow feature learning architectures is one of the key drawbacks of machine learning (ML) techniques. So, we present a novel deep neural network heartbeat classifier to extract and classify the heartbeat signals. The novel one-dimensional convolution neural network (1D CNN) model is developed by modifying the LENET architecture for the classification of heat beats (MIT-BIH Arrhythmia Database) and has attained an accuracy of 97.37%. This model's performance is also enhanced by the implementation of smote oversampling technique and gained an accuracy of 98.41%. Finally, the proposed model's performance is compared with other pre-existing models and various oversampling methods are deployed for analysis.

An end-to-end model for ECG signals classification based on residual attention network

Arrhythmia is the most threatening disease among cardiovascular diseases, and in the last few years, the automatic detection of arrhythmia using neural networks have been intensely focused by physicians. In our work, we propose an effective method to automatically classify electrocardiogram (ECG) signals utilizing residual attention network (RA-NET). RA-NET combines the residual structure and attention mechanism, which can not only generate the attention weight of atrial fibrillation (AF) category to enhance the effective information, but also avoid the network degradation problem in the deep network. Besides, a novel filling algorithm for filling sample values of other recordings with the same category is presented, which is combined with RA-NET to validate model on the PhysioNet Challenge 2017 dataset. According to the comparison with other relevant classification models and filling methods, the experimental results demonstrate that the model we proposed achieves an excellent classification performance, the average of F1-score and sensitivity reach 0.8289 and 0.8955, respectively. For AF category, the precision, F1-score and specificity achieve 0.8763, 0.8835 and 0.9858, separately. With its preeminent performance, the proposed model is capable to play an important auxiliary role in single-lead AF detection.

An explainable attention-based TCN heartbeats classification model for arrhythmia detection

Background and Objective:Electrocardiogram (ECG) is a non-invasive tool to measure the heart’s electrical activity. ECG signal based automatic heartbeat classification is a critical task for arrhythmia detection and continues to be challenging. While diverse automated classification methods have been developed, they still cannot provide acceptable performance in classifying different heartbeats because of their poor ability to extract abstract patterns comprehensively. Besides, the performance of previous work drops sharply when dealing with imbalanced datasets and lacks interpretability. Methods:This paper proposes a novel, explainable attention-based temporal convolutional network(TCN) heartbeat classification method. The first contribution of our approach is that we fuse the TCN architecture and self-attention mechanism to encode the ECG heartbeat sequences. Specifically, TCN and the self-attention block are designed to capture global variation tends and local features, respectively, to best serve the classification. Meanwhile, multi-class focal loss helps model training overcome the class imbalance problem. In the end, the dynamic perturbation based high-fidelity explanation module was introduced to understand the AI-based model and enhance the model’s transparency to clinicians. Conclusions:Experiments on the MIT-BIH-AD dataset demonstrate that our model with a simpler architecture can achieve 99.84% accuracy, 99.90% specificity and 99.60% precision for the intra-patient scheme and 87.81% accuracy, 91.85% sensitivity and 89.81% precision for the inter-patient scheme, which outperforms most of the state-of-the-art(SOTA) works, especially for minority classes.

Cardiac arrhythmias associated with immune checkpoint inhibitors: A comprehensive disproportionality analysis of the FDA adverse event reporting system.

Introduction: With the widespread application of Immune checkpoint inhibitors (ICIs), it is important to explore the association between ICIs and cardiac arrhythmias and to characterize the clinical features of ICI-associated cardiac arrhythmias in real-world studies. Objective: The purpose of this study was to characterize the main features of ICI-related cardiac arrhythmias. Methods: From January 2017 to June 2021, data in the Food and Drug Administration Adverse Event Reporting System (FAERS) database were retrieved to conduct the disproportionality analysis. For the ICI-related cardiac arrhythmia detection, signals were detected by reporting odds ratio (ROR) and information component (IC), calculated using two-by-two contingency tables The clinical characteristics of patients reported with ICI-related cardiac arrhythmias were compared between fatal and non-fatal groups, and the time to onset (TTO) following different ICI regimens was further investigated. Multivariate logistic regression was used to evaluate the association between concurrent cardiotoxicities and ICI-associated arrhythmias. Results: We identified a total of 1957 ICI-associated cardiac arrhythmias reports which appeared to influence more men (64.44%) than women (30.76%), with a median age of 68 [interquartile range (IQR) 60-75] years. Cardiac arrhythmias were reported most often in patients with lung, pleura, thymus and heart cancers (38.02% of 1957 patients). Compared with the full database, ICIs were detected with pharmacovigilance of cardiac arrhythmias (ROR025 = 1.16, IC025 = 0.19). Anti-PD-1 and anti-PD-L1 monotherapies were found to be related to higher reporting of arrhythmias, corresponding to ROR025 = 1.03, IC025 = 0.06 and ROR025 = 1.27, IC025 = 0.29, respectively, with the exception of anti-CTLA-4 monotherapies (ROR025 = 0.57, IC025 = -1.21). The spectrum of arrhythmias induced by ICIs differed among therapeutic regimens. There was no significant difference in the onset time between monotherapy and combination regimen. Moreover, reports of ICI-associated arrhythmias were associated with other concurrent cardiotoxicity, including cardiac failure [ROR 2.61 (2.20-3.09)], coronary artery disorders [ROR 2.28 (1.83-2.85)], myocardial disorders [ROR 5.25 (4.44-6.22)], pericardial disorders [ROR 2.76 (2.09-3.64)] and cardiac valve disorders [ROR 3.21 (1.34-7.68)]. Conclusion: ICI monotherapy and combination therapy can lead to cardiac arrhythmias that can result in serious outcomes and tend to occur early. Our findings underscore the importance of early recognition and management of ICI-related cardiac arrhythmias.

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

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. 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)]. 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).

Deep learning-based system to predict cardiac arrhythmia using hybrid features of transform techniques

• Decomposed of ECG signals with discrete wavelet transform (DWT), empirical mode decomposition (EMD) and variational mode decomposition (VMD) methods. • Extraction of informative time-frequency based multi-domain features. • Ranking of features based on weightage in Chi-squared test and PSO search methods. • Classification of ECG beats using deep neural network. • Comparison of results with deep learning and discussion with published works. An early and accurate detection of arrhythmias is essential reduce the mortality rate due to cardiac diseases. Manual screening of the electrocardiogram (ECG) signals are time consuming, strenuous, and liable to human errors. This article proposes a deep learning approach for automated detection of cardiac arrhythmia using RCG signals fro MIT-BIH database. Various decomposition techniques namely: discrete wavelet transform (DWT), empirical mode decomposition (EMD) and variational mode decomposition (VMD) are used to de-noise the ECG signal. The time-frequency based multi-domain features are extracted from the various coefficients of the sub-bands from de-noised signals. These obtained features are ranked based on Chi-squared test and particle swarm optimization (PSO) based methods to select the best informative features for better classification accuracy. The hybrid features was classified with deep neural network (DNN) with ten-fold cross validation strategy in classifying five types of ECG beats. The best results was obtained with an accuracy of 99.75% with less computational complexity of 0.14 s using Chi squared selection approach. Thus the proposed model can be used in the hospitals set-up to automatically screen the abnormal ECG beats.

The Role of Contemporary Wearable and Handheld Devices in the Diagnosis and Management of Cardiac Arrhythmias.

Cardiac arrhythmias are associated with significant morbidity, mortality and economic burden on the health care system. Detection and surveillance of cardiac arrhythmias using medical grade non-invasive methods (electrocardiogram, Holter monitoring) is the accepted standard of care. Whilst their accuracy is excellent, significant limitations remain in terms of accessibility, ease of use, cost, and a suboptimal diagnostic yield (up to ∼50%) which is critically dependent on the duration of monitoring. Contemporary wearable and handheld devices that utilise photoplethysmography and the electrocardiogram present a novel opportunity for remote screening and diagnosis of arrhythmias. They have significant advantages in terms of accessibility and availability with the potential of enhancing the diagnostic yield of episodic arrhythmias. However, there is limited data on the accuracy and diagnostic utility of these devices and their role in therapeutic decision making in clinical practice remains unclear. Evidence is mounting that they may be useful in screening for atrial fibrillation, and anecdotally, for the diagnosis of other brady and tachyarrhythmias. Recently, there has been an explosion of patient uptake of such devices for self-monitoring of arrhythmias. Frequently, the clinician is presented such information for review and comment, which may influence clinical decisions about treatment. Further studies are needed before incorporation of such technologies in routine clinical practice, given the lack of systematic data on their accuracy and utility. Moreover, challenges with regulation of quality standards and privacy remain. This state-of-the-art review summarises the role of novel ambulatory, commercially available, heart rhythm monitors in the diagnosis and management of cardiac arrhythmias and their expanding role in the diagnostic and therapeutic paradigm in cardiology.

Detection of arrhythmia in 12-lead varied-length ECG using multi-branch signal fusion network

Objective. Automatic detection of arrhythmia based on electrocardiogram (ECG) plays a critical role in early prevention and diagnosis of cardiovascular diseases. With the increase in widely available digital ECG data and the development of deep learning, multi-class arrhythmia classification based on automatic feature extraction of ECG has become increasingly attractive. However, the majority of studies cannot accept varied-length ECG signals and have limited performance in detecting multi-class arrhythmias. Approach. In this study, we propose a multi-branch signal fusion network (MBSF-Net) for multi-label classification of arrhythmia in 12-lead varied-length ECG. Our model utilizes the complementary power between different structures, which include Inception with depthwise separable convolution (DWS-Inception), spatial pyramid pooling (SPP) Layer, and multi-scale fusion Resnet (MSF-Resnet). The proposed method can extract features from each lead of 12-lead ECG recordings separately and then effectively fuse the features of each lead by integrating multiple convolution kernels with different receptive fields, which can achieve the information of complementation between different angles of the ECG signal. In particular, our model can accept 12-lead ECG signals of arbitrary length. Main results. The experimental results show that our model achieved an overall classification F1 score of 83.8% in the 12-lead ECG data of CPSC-2018. In addition, the F1 score of the MBSF-Net performed best among the MBF-Nets which are removed the SPP layer from MBSF-Net. In comparison with the latest ECG classification algorithms, the proposed model can be applied in varied-length signals and has an excellent performance, which not only can fully retain the integrity of the original signals, but also eliminates the cropping/padding signal beforehand when dealing with varied-length signal database. Significance. MBSF-Net provides an end-to-end multi-label classification model with outperfom performance, which allows detection of disease in varied-length signals without any additional cropping/padding. Moreover, our research is beneficial to the development of computer-aided diagnosis.

A novel multi-scale 2D CNN with weighted focal loss for arrhythmias detection on varying-dimensional ECGs

Objective. The ECG is a standard diagnostic tool for identifying many arrhythmias. Accurate diagnosis and early intervention for arrhythmias are of great significance to the prevention and treatment of cardiovascular disease. Our objective is to develop an algorithm that can automatically identify 30 arrhythmias by using varying-dimensional ECG signals. Approach. In this paper, we firstly proposed a novel multi-scale 2D CNN that can effectively capture pathological information from small-scale to large-scale from ECG signals to identify 30 arrhythmias from 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead ECGs. Secondly, we explored the effects of varying convolution kernels sizes and branch subnetworks on the model’s performance for each arrhythmia. Thirdly, we introduced the weighted focal loss to alleviate the positive-negative class imbalance problem in the multi-label arrhythmias classification. Fourthly, we explored the utility of reduced-lead ECGs in detecting arrhythmias by comparing the performances of models on varying-dimensional ECGs. Main results. As a follow-up entry after the PhysioNet/Computing in Cardiology Challenge (2021), our proposed approach achieved the official test scores of 0.52, 0.47, 0.53, 0.51, and 0.50 for the 12-lead, 6-lead, 4-lead, 3-lead, and 2-lead ECGs on the hidden test set (comparable to that of 6th, 11th, 4th, 5th, and 7th out of 39 teams in the Challenge). Significance. A multi-scale framework capable of detecting 30 arrhythmias from varying-dimensional ECGs was proposed in our work. We preliminarily verified that the multi-scale perception fields may be necessary to capture more comprehensive pathological information for arrhythmias detection. Besides, we also verified that the weighted focal loss may alleviate the positive–negative class imbalance and improve the model’s generalization performance on the cross-dataset. In addition, we observed that some reduced-lead models, such as the 4-lead and 3-lead models, can even achieve performance that is almost comparable to that of the 12-lead model. The excellent performance of our proposed framework demonstrates its great potential in detecting a wide range of arrhythmias.

Arrhythmia Detection Based on WGAN-GP and SE-ResNet1D

A WGAN-GP-based ECG signal expansion and an SE-ResNet1D-based ECG classification method are proposed to address the problem of poor modeling results due to the imbalanced sample distribution of ECG data sets. The network architectures of WGAN-GP and SE-ResNet1D are designed according to the characteristics of ECG signals so that they can be better applied to the generation and classification of ECG signals. First, ECG data were generated using WGAN-GP on the MIT-BIH arrhythmia database to balance the dataset. Then, the experiments were performed using the AAMI category and inter-patient data partitioning principles, and classification experiments were performed using SE-ResNet1D on the imbalanced and balanced datasets, respectively, and compared with three networks, VGGNet, DenseNet and CNN+Bi-LSTM. The experimental results show that using WGAN-GP to balance the dataset can improve the accuracy and robustness of the model classification, and the proposed SE-ResNet1D outperforms the comparison model, with a precision of 95.80%, recall of 96.75% and an F1 measure of 96.27% on the balanced dataset. Our methods have the potential to be a useful diagnostic tool to assist cardiologists in the diagnosis of arrhythmias.

Analysis of Early Warning Diagnostic Indexes and Influencing Factors of Anxiety and Depression in Patients with Arrhythmia.

Objective Arrhythmia patients complicated with psychological problems are very common in clinics. The imbalance of autonomic nervous regulation of the heart caused by anxiety and depression will further promote the occurrence and development of arrhythmia. For nonorganic heart disease, β receptor blockers combined with antianxiety drugs have a good effect. Therefore, it is necessary to analyze the influencing factors of anxiety and depression in patients with arrhythmias. Methods We included 150 patients with arrhythmia and divided them into observation groups (80 patients with anxiety and depression) and control groups (70 patients without anxiety and depression). All patients were monitored by Holter, and the detection of arrhythmia was compared between the two groups. We took the general situation and quality of life of the investigated patients as independent variables and the anxiety and depression status of the patients as dependent variables. Results The detection rates of atrioventricular premature beats, ventricular premature beats, atrial fibrillation, short bursts of atrial tachycardia, and atrioventricular block in the observation group were all higher than those in the control group by dynamic electrocardiogram. Multivariate logistic stepwise regression analysis showed that age, years of education, obsessive-compulsive score, somatization score and alcohol consumption were the main influencing factors for anxiety and depression. Conclusions The detection rate of arrhythmia in patients with anxiety/depression status was higher than in those without abnormal psychophylaxis. We should need to pay close attention to the risk factors of age, education years, obsessive-compulsive score, somatization score, and alcohol consumption, so as to prevent and timely detect anxiety and depression symptoms in patients with arrhythmias.

A life-threatening arrhythmia detection method based on pulse rate variability analysis and decision tree.

Extreme bradycardia (EB), extreme tachycardia (ET), ventricular tachycardia (VT), and ventricular flutter (VF) are the four types of life-threatening arrhythmias, which are symptoms of cardiovascular diseases. Therefore, in this study, a method of life-threatening arrhythmia recognition is proposed based on pulse rate variability (PRV). First, noise and interference are wiped out from the arterial blood pressure (ABP), and the PRV signal is extracted. Then, 19 features are extracted from the PRV signal, and 15 features with highly important and significant variation were selected by random forest (RF). Finally, the back-propagation neural network (BPNN), extreme learning machine (ELM), and decision tree (DT) are used to build, train, and test classifiers to detect life-threatening arrhythmias. The experimental data are obtained from the MIMIC/Fantasia and the 2015 Physiology Net/CinC Challenge databases. The experimental results show that the DT classifier has the best average performance with accuracy and kappa coefficient (kappa) of 98.76 ± 0.08% and 97.59 ± 0.15%, which are higher than those of the BPNN (accuracy = 94.85 ± 1.33% and kappa = 89.95 ± 2.62%) and ELM (accuracy = 95.05 ± 0.14% and kappa = 90.28 ± 0.28%) classifiers. The proposed method shows better performance in identifying four life-threatening arrhythmias compared to existing methods and has potential to be used for home monitoring of patients with life-threatening arrhythmias.

Arrhythmia detection using insertable cardiac monitors after a negative electrophysiology study in Brugada syndrome: observations from a multicenter Spanish registry

Abstract Background/Introduction Risk stratification in Brugada syndrome (BrS) remains controversial. In this respect, the role of electrophysiology study (EPS) has been subject of debate. It is common practice in some centers to implant an insertable cardiac monitor (ICM) after a negative EPS, especially in the presence of unexplained symptoms. However, the diagnostic value of this approach has never been specifically addressed. Purpose We aimed to describe the baseline characteristics and the main findings of a diagnostic work-up strategy using an insertable cardiac monitor (ICM) after a negative EPS in patients with BrS. Methods We retrospectively evaluated data from a multicenter registry including 56 BrS patients from 7 referral hospitals who received an ICM to help risk stratification. Only patients with a negative EPS (ie, non-inducible VT/VF) prior to ICM implantation were considered for this analysis. EPS protocols differed across hospitals (see Figure 1) Results A total of 26 patients from 5 different hospitals were studied. Mean age was 33.0±12.8 and 77% were male. Spontaneous type 1 pattern was present in 12 patients (46%). Positive genotype was found in 10 (38%) and family history of sudden cardiac death was present in 11 (42%). Previous symptoms were syncope/presyncope in 15 patients (58%) and palpitations in 3 patients (12%). The rest of the patients (30%) were asymptomatic. After a median follow-up of 33.4 months (IQR 16.5 and 43.1 months), none of the patients presented ventricular arrhythmias. ICM allowed the detection of other arrhythmias in 5 patients (19%), which led to specific therapeutic actions in all but 2 of them (see Table 1). ICM-detected arrhythmias correlated with previously reported symptoms only in one of the patients. Conclusion The results of this exploratory analysis support the notion that EPS in BrS has a high negative predictive value for risk stratification. ICM implantation after a negative EPS may allow the detection of incidental arrhythmias during follow-up. Despite the apparent low correlation of these findings with previously reported symptoms, this strategy may lead to important treatment decisions in a significant proportion of patients. Funding Acknowledgement Type of funding sources: None.

Various arrhythmia types and their day-by-day occurrence rates over a 14-day period using a P-wave sensitive ambulatory ECG monitored population

Abstract Background Many studies on ECG monitoring and arrhythmia detection use the term “diagnostic yield”, a vague term and one without the type of diagnostic precision that cardiologists value. Moreover, diagnostic yield of specific arrhythmias is not well understood on a day-by-day basis. Purpose We used a continuous 14-day ECG monitor to record the incremental occurrence of a broad variety of specific arrhythmias each day from a general outpatient population suspected of having an arrhythmia. Methods A total of 546 patients were monitored for 14±1 day in the absence of artifact that would otherwise obscure the rhythm. Without such stipulations, arrhythmias could not be truly categorized as a function of time. Patients were randomly selected who satisfied the aforementioned criteria. The studies were prescribed by the patient's managing physician for standard clinical indications, and they spanned across 237 distinct institutions. The recordings were interpreted by 3 serial readers clinically knowledgeable on electrophysiological principles of arrhythmia diagnostics. All reports were then confirmed in their entirety by a cardiac electrophysiologist. The daily diagnostic rate for specific arrhythmia occurrence was then tabulated. Of note, algorithmic and AI diagnostic approaches were not relied upon for arrhythmia diagnoses. Results Select arrhythmia/conduction abnormalities are shown in the attached Figure, demonstrating different arrhythmias manifesting at different rates. In 61% of pts, at least one rhythm disorder was found that could affect patient management over 14 days. In 28% of pts, two disorders were found while 12% had three or more disorders. P-wave specificity on the ECG aided in identifying 67.9% of those unique arrhythmias. When more than one arrhythmia type was identified, they typically occurred on different days. In contrast, the standard 1-day report, if implemented, would have diagnosed only 20% of patients and rarely would have found multiple rhythm abnormalities Conclusion Different arrhythmia categories manifest at different rates on a 14-day continuous ECG. Clinical abnormalities in rhythm and/or conduction occur in 61% of patients randomly selected from a broad array of institutions. Moreover, 28% had 2 disorders and 12% had >3 disorders, usually occurring on different days. Lastly, 67.9% of rhythms were identified due to a high fidelity P-wave ECG signal. These findings suggest that a 14-day P-wave sensitive ECG recording has substantive diagnostic value even if a suspected arrhythmia were to occur on day 1. Further, ECG recordings of 1 day (i.e., standard Holter monitor duration) severely diminish diagnostic value and should be avoided. Funding Acknowledgement Type of funding sources: None.

Detection of arrhythmias in patients with cardiac amyloidosis using implantable ECG recorders

Abstract Introduction Cardiac Amyloidosis frequently results in congestive cardiac failure and arrhythmias, from a disruption in cardiac substrate with subsequent electro-mechanical remodeling. Arrhythmias are vary based on the amyloidosis type. Conduction defects and atrial arrhythmias are more prevalent in transthyretin amyloidosis compared with light chain amyloidosis, and this difference might be a reflection of the longer survival time in the former. Methods 112 transthyretin amyloidosis (TTR) patients with completed underlying diagnosis including 99mTc-DPD scan, genetic testing and endomyocardioal biopsy (27%) without documented arrhythmias were randomized to standard clinical follow-up including arrhythmias or implantation of an ECG loop recorder (ILR). The classic FU took place in a heart failure clinic, and the group of patients with ILR was monitored by remote control with automatic daily report of the occurrence of arrhythmias by an independent organization. If an arrhythmia was detected, the patient was contacted immediately. The mean follow-up time for both groups was 17±7 months. Results The results are summarized in Table 1. Conclusions Currently, there is no consensus on the absolute benefit that ICDs in patients with cardiac amyloidosis. When non-sustained VT and syncope are captured and documented, ICD implantation for prevention of SCD in CA is most likely a reasonable approach. However, intensive monitoring of arrhythmias in patients with CA using ILR can lead to accurate and early detection of ventricular arrhythmias in particular and early initiation of ICD treatment as a prevention of SCD. Documentation of ventricular arrhythmias in CA patients was significantly higher by ILR (p<0.005) and was a clear predictor of patient survival (HR 2.51). Funding Acknowledgement Type of funding sources: None.

A service evaluation of patch technology compared with traditional holter monitoring in a stroke pathway

Abstract Background Atrial fibrillation (AF) is a known risk factor for embolic stroke. Establishing a diagnosis of AF will guide clinical decision making and help with downstream secondary stroke prevention. Patch technology is increasingly used for long-term cardiac monitoring for arrhythmia detection, as healthcare organisations look for new innovative ways to streamline service delivery. We were selected as a host site to evaluate the service and patient benefits of Zio XT in AF detection for cryptogenic stroke, as part a Artificial Intelligence Award. Purpose To evaluate the service and patient benefits of patch technology versus traditional Holter in a Stroke / TIA pathway. Methods The Zio XT data were collected between March and December 2021. A total of 778 patients were included. We only selected patients who were referred for a long-term ambulatory monitoring following a recent diagnosis of stroke or transient ischaemic attack (TIA) of an unknown cause (cryptogenic). The stroke pathway operates across three sites and all were included. We undertook a retrospective analysis of our previous pathway using Holter monitoring and sampled 100 stroke / TIA patients who underwent 24–72 hours of monitoring between January to June 2019. In order to obtain the requisite data a variety of sources were scrutinised: referral letters, test reports, patient medical records, internal clinical systems and third-provider platforms. Results The comparison of the ECG technologies showed the Zio XT used less staff time. We found a 50% reduction in-clinic monitor fitting when compared with Holter. Zio XT were all analysed by the provider staff resulting in significant savings in service resource time for analysis. The Zio XT had a faster test turnaround time (referral to report available), 19 days (inclusive of 14 days wear time) for Zio compared with 60 days for Holters. The rapid Zio turnaround led to a 27.5% reduction in repeat clinic appointments, due to results being unavailable for the consultation (table 1). Zio XT also had fewer repeat testing due to inconclusive results, 1% for Zio versus 16% for Holter. AF yield did not vary significantly between technologies, 3% yield for both Holter and Zio, which could be due to the young mean age of the stroke/ TIA the patient cohort: 63.8 years for Holter versus 62.9 years for Zio XT. Conclusion Introducing new ECG technologies such as Zio XT could increase outpatient and diagnostic capacity due to patches being more readily available than Holters, reduced reliance on clinical staff for fitting and analysis as well as fewer repeat clinic appointments. Overall, access to rapid long term cardiac monitoring has benefits over traditional Holter monitoring for TIA/stroke patients and service delivery. Funding Acknowledgement Type of funding sources: Public Institution(s). Main funding source(s): AI award from the Accelerated Access Collaborative (ACC) in partnership with NHSX and National Institute for Health Research

A service evaluation of Zio XT: the Liverpool experience

Abstract Introduction The Zio XT is an adhesive, ambulatory heart rhythm monitoring device that can be worn for up to 14 days. It can be fitted by patients and utilises an Artificial Intelligence-based algorithm for rhythm analysis, offering potential convenience, accuracy and efficiency compared to Holter monitors. However, there is a lack of data regarding its efficacy and long-term impact. Thus, until further evidence ensues, NICE guidelines recommend Zio XT as a potential option for those requiring prolonged rhythm monitoring. Purpose We evaluated the efficacy of Zio XT for heart rhythm monitoring compared to Holter monitors. Methods 200 sequential patients that had Holter monitors and 204 that had Zio XT were included. Zio cases were randomly selected over 6 months to avoid the learning curve effect. Primary outcomes included time to results and the arrhythmia detection rate. Secondary outcomes included the proportion of patients that had heart rhythm monitoring in the 12 months preceding their investigation, those who required further tests as well as rates of outpatient appointments (OPAs) for device fitting and follow-up, and procedures such as device implantation and ablations. Results Data from 22 (10.8%) Zio patches was unavailable due to these being lost/not returned/unwearable, thus post-investigation outcomes were analysed for 182 Zio and 200 Holter cases. Zio XT was associated with a significantly shorter time to results compared to Holter monitors (median time: 21 days (interquartile range (IQR) 18–25) vs. 46 days (IQR 37.3–87.8), p<0.001), and a higher significant arrhythmia detection rate (55.4% vs. 17.5%, p<0.001). 26.5% of Zio patients had heart-rhythm monitoring in the preceding 12 months, compared to the 14.5% in the Holter group, p=0.003, with 55.8% having Holters and 28.8% having Zios previously, in the Zio group. A higher proportion of Zio recipients also required repeat tests (19.4 vs. 8.5%, p=0.002). Reasons for this included post-intervention monitoring (44.1%), lack of results due to devices being lost/faulty/not returned (41.2%) and a lack of diagnosis (14.7%). Zio monitoring was associated with a significant reduction in the need for OPAs for fitting (0.5% vs. 96%, p<0.001) and follow-up (70.1% vs. 87.0, p<0.001), and resulted in a significant increase in ablations (5.9% vs. 1.0%, p=0.005) but not device implantations (5.9% vs. 3.9, p=0.209). Conclusion Our findings indicate that Zio XT is associated with a statistically significant reduction in time to results, higher arrhythmia detection rate and a reduced need for OPAs. We demonstrated a higher rate of both Holter and Zio testing before and Zio testing after these investigations. We postulate that this has partly been due to a learning curve effect with the introduction of a new technology compared to the Holter which has been in use for many decades. Further large-scale evaluation is recommended to yield vital information on management pathways and cost efficacy. Funding Acknowledgement Type of funding sources: None.

Assessment of palpitation complaints in patients with benign paroxysmal positional vertigo.

The detection of cardiac arrhythmias during vertigo attacks along with the resolution of vertigo by treating the arrhythmias is defined as cardiac vertigo. The cause of palpitations that develop following attacks of non-cardiac vertigo is unknown. We aimed to investigate the effect of benign paroxysmal positional vertigo (BPPV) on the cardiac conduction system and evaluate patients' palpitation complaints using 24-hour ambulatory ECG (Holter) monitoring. Sixty-five patients with BPPV and forty-eight healthy controls were included in the study. ECG was performed on all participants, and ECG parameters were measured. Holter monitoring was performed, and the recordings were analyzed. Evaluation of the time-domain heart rate variability (HRV) results was done. The average age of the vertigo group was 49.1 ± 7.8 years. In terms of demographic or laboratory data, there was no statistically significant difference between the groups (p>0.05). The study group's ECG parameters, including Pd, TpTe, and TpTec, were longer, and the TpTe/QT and TpTe/QTc ratios were higher (p<0.05). Holter monitoring detected abnormal rhythms in 41 (63%) of the study group patients and three (6.2%) of the control group patients. The SDNN, LF, and LF/HF values, which are known as HRV markers, were significantly different in the vertigo group compared to the control group (p<0.001). This study revealed that the risk of arrhythmias increased following attacks of BPPV in patients without a known history of cardiac vertigo.