Detection Of Atrial Arrhythmias Research Articles

Patient Driven EKG Device Performance in Adults with Fontan Palliation.

The aim of this study was to evaluate the accuracy of the KardiaMobile (KM) device in adults with a Fontan palliation, and to assess the KM function as a screening tool for atrial arrhythmias. While patient driven electrocardiogram (EKG) devices are becoming a validated way to evaluate cardiac arrhythmias, their role for patients with congenital heart disease is less clear. Patients with single ventricle Fontan palliation have a high prevalence of atrial arrhythmias and represent a unique cohort that could benefit from early detection of atrial arrhythmias. This single center prospective study enrolled adult patients with Fontan palliation to use the KM heart rhythm monitoring device for both symptomatic episodes and asymptomatic weekly screening over a 1-year period. Accuracy was assessed by comparing the automatic KM interpretation (KM-auto) to an electrophysiologist overread (KM-EP) and traditional EKG. Fifty patients were enrolled and 510 follow-up transmissions were received. The sensitivity and specificity of enrollment KM-auto compared to EKG was 65% and 100%, respectively. The sensitivity and specificity of enrollment KM-auto compared to the KM-EP was 75% and 96%, respectively. In the adult Fontan palliation, the accuracy of the KM device to detect a normal rhythm was reliable and best with a physician overread. Abnormal or uninterpretable KM-auto device interpretations, symptomatic transmissions, and any transmissions with a high heart rate compared to a patient's normal baseline should warrant further review.

Association of Atrial Fibrillation Burden and Mortality Among Patients With Cardiac Implantable Electronic Devices.

Current estimates of atrial fibrillation (AF)-associated mortality rely on claims- or clinical-derived diagnoses of AF, limit AF to a binary entity, or are confounded by comorbidities. The objective of the present study is to assess the association between device-recognized AF and mortality among patients with cardiac implantable electronic devices capable of sensitive and continuous atrial arrhythmia detection. Secondary outcomes include relative mortality among cohorts with no AF, paroxysmal AF, persistent AF, and permanent AF. Using the deidentified Optum Clinformatics US claims database (2015 to 2020) linked to the Medtronic CareLink database, we identified individuals with a cardiac implantable electronic device who transmitted data ≥6 months after implantation. AF burden was assessed during the first 6 months after implantation (baseline period). Subsequent mortality, assessed from claims data, was compared between patients with and without AF, with adjustment for age, geographic region, insurance type, Charlson Comorbidity Index, and implantation year. Of 21 391 patients (age, 72.9±10.9 years; 56.3% male) analyzed, 7798 (36.5%) had device-recognized AF. During a mean of 22.4±12.9 months (median, 20.1 [12.8-29.7] months) of follow-up, the overall incidence of mortality was 13.5%. Patients with AF had higher adjusted all-cause mortality than patients without AF (hazard ratio, 1.29 [95% CI, 1.20-1.39]; P<0.001). Among those with AF, patients with nonparoxysmal AF had the greatest risk of mortality (persistent AF versus paroxysmal AF: hazard ratio, 1.36 [95% CI, 1.18-1.58]; P<.001; permanent AF versus paroxysmal AF: hazard ratio, 1.23 [95% CI, 1.14-1.34]; P<.001). After adjustment for potential confounding factors, the presence of AF was associated with higher mortality in our cohort of patients with cardiac implantable electronic devices. Among those with AF, nonparoxysmal AF was associated with the greatest risk of mortality.

Artificial intelligence–based electrocardiogram analysis improves atrial arrhythmia detection from a smartwatch electrocardiogram

Abstract Aims Smartwatch electrocardiograms (SW ECGs) have been identified as a non-invasive solution to assess abnormal heart rhythm, especially atrial arrhythmias (AAs) that are related to stroke risk. However, the performance of these tools is limited and could be improved with the use of deep neural network (DNN) algorithms, particularly for specific populations encountered in clinical cardiology practice. Methods and results A total of 400 patients from the electrophysiology department of one tertiary care hospital were included in two similar clinical trials (respectively, 200 patients per study). Simultaneous ECGs were recorded with the watch and a 12-lead recording system during consultation or before and after an electrophysiology procedure if any. The SW ECGs were processed by using the DNN and with the Apple watch ECG software (Apple app). Corresponding 12-lead ECGs (12L ECGs) were adjudicated by an expert electrophysiologist. The performance of the DNN was assessed vs. the expert interpretation of the 12L ECG, and inconclusive rates were reported. Overall, the DNN and the Apple app presented, respectively, a sensitivity of 91% [95% confidence interval (CI) 85–95%] and 61% (95% CI 44–75%) with a specificity of 95% (95% CI 91–97%) and 97% (95% CI 93–99%) when compared with the physician 12L ECG interpretation. The DNN was able to provide a diagnosis on 99% of ECGs, while the Apple app was able to classify only 78% of strips (22% of inconclusive diagnosis). Conclusion In this study, by including patients from a cardiology department, a DNN-based algorithm applied to an SW ECG provided an accurate diagnosis for AA detection on virtually all tracings, outperforming the SW algorithm.

Effectiveness of photoplethysmography-based rhythm monitoring after atrial fibrillation ablation using a smartphone application

Abstract Introduction Recurrence of atrial fibrillation (AF) after AF ablation is frequent. Monitoring recurrence is essential for attributing patient symptoms and for assessing both AF burden and treatment effectiveness. The conventional approach relies on periodic (long-term) electrocardiograms (ECG) and is constrained by limited monitoring time, measurement dispersion, and cost. Furthermore, patients are unable to prioritize measurements based on symptoms. Photoplethysmography (PPG) emerges as a technology that could potentially transform any smartphone into a rhythm monitoring device, thereby mitigating the limitations associated with current practices. Selected applications leveraging this technology have demonstrated excellent usability and accuracy for the detection of AF. However, the effectiveness of PPG-based follow-up remains uncertain. Purpose To compare the effectiveness of digital follow-up utilizing a PPG-based smartphone application with conventional ECG-based follow-up for the detection of atrial arrhythmia recurrence after ablation. Methods Patients undergoing AF ablation were consecutively enrolled and monitored using a 24h-ECG at 3-6-12 months on top of ECGs conducted for clinical indications (conventional follow-up). Additionally, patients were instructed to perform PPG measurements twice daily or whenever symptoms were perceived, over the course of one year (digital follow-up). The primary outcome was recurrence of atrial arrhythmia. Results In total, 96 patients (69% male, mean age 64 [58 – 68] years) performed 39,895 PPG measurements. The compliance rate (n performed/prescribed) was 92.6% for ECG and 78.2% for PPG recordings. After one year follow-up, atrial arrhythmia recurrence was detected by conventional follow-up in 17.9% and in 38.5% of patients by digital follow-up (odds ratio, 3.4; 95% CI: 1.7-7.1). The confidence interval lower limit exceeded the predefined non-inferiority margin (p for non-inferiority &amp;gt; 0.001). Hence, superiority was tested (p for superiority = 0.001). The negative predictive value of digital follow-up for atrial arrhythmia detected with conventional follow-up was 98.3% (95% CI: 90.1-99.9%). Symptoms were reported in 81.1% of PPG-detected atrial arrhythmias and episodes sustained for 3.9 [1.1 – 22.7] hours. Conclusions Among patients with AF ablation, digital PPG-based rhythm monitoring with a smartphone, was non-inferior in the detection of atrial arrhythmia recurrence after ablation. Moreover, the detection of atrial arrhythmia was significantly increased compared to conventional ECG-based monitoring.

On-chip, non-invasive detection of all atrial arrhythmias for immediate and accurate characterization in adult rats

Abstract Background To monitor and record the occurrence and duration of cardiac arrhythmias in freely moving animals, ECG telemetry devices are often used. However, traditional telemetry devices require complex equipment unsuitable for on-site application in most animal housing facilities. Additionally, current atrial arrhythmias detection algorithms are mainly based on ECG R-R interval variability for atrial fibrillation (AF) detection. Such algorithms do not allow the detection of stable R-R interval atrial arrhythmias such as flutter. Thus there is currently a lack of non-invasive methods allowing automated detection of all atrial arrhythmias subtypes, thereby precluding in-depth research into general and subtype-specific mechanisms and treatment. Purpose Here we aim to create a non-invasive system allowing fast and accurate on-site detection and characterization of all atrial arrhythmias in rats. Methods Our atrial arrhythmia detector system was made of an on-skin ECG sensor, a low-power microprocessor unit, a large data storage unit and a battery. All components were assembled within a lightweight rat jacket. The filtered ECG signal was sent to the microprocessor allowing algorithm-based, real-time detection of atrial arrhythmias. The device allowed storage of ECG traces as well as arrhythmia characteristics (including type of arrhythmia and its duration). Atrial arrhythmias were induced by transesophageal atrial burst pacing in Wistar rats. These arrhythmia recordings were used to develop an AI detection method. Next, real-time detection algorithms based on R-R variability and AI were both integrated on-chip and compared using the same ECG data. Results ECG traces measured with our new system were similar to classical ECG measurements. Stored ECG traces provided the raw data for the development of an AI-based detection algorithm. The AI training was done using ECG data recorded from five different rats and reached 99.5% self-testing accuracy to detect all sub-types of atrial arrhythmias based on pre-categorized data. Using uncategorized data (n=25 from 5 rats) different from the training dataset, the AI algorithm could detect &amp;gt;80% of all types of atrial arrhythmias within 3s after initiation, while the rest could be detected within 10s. Though R-R interval based algorithm showed a high detection rate of 88% of AF within 10s, this method did not allow the detection of flutter or AF presenting regular R-R intervals within 1 minute after initiation. Conclusion Our atrial arrhythmia detection and analysis system provides a novel method for non-invasive investigation into atrial arrhythmias in rats and could easily be scaled for other species. It allows on-site fast and accurate detection and characterization of atrial arrhythmia subtypes without external equipment, thereby opening new possibilities for mechanistic studies and therapeutic testing, including closed-loop applications aiming for arrhythmia termination.

Long-term stability of atrial sensing in implantable cardioverter-defibrillators with floating atrial dipole leads

Abstract Introduction To maintain the advantages of having atrial sensing without the need to implant an additional lead, a single-lead ICD system with a floating atrial dipole (VDD DX ICD, Biotronik) with active fixation to the right ventricle has been developed. In this generation of ICDs, specially filtered atrial signs may be high enough to allow early detection of atrial arrhythmias and improve discrimination between atrial and ventricular tachycardias. However, maintaining reliable and stable atrial sensing via the floating dipole could be a concern regarding this technology. We aimed to determine the long-term stability of atrial sensing in patients (P) with this type of device. Methods All P implanted with ICDs with an active fixation DX lead at our centre between 2013 and 2021 were included. Atrial sensing and ventricular or supraventricular arrhythmic events were recorded during follow-up. We retrospectively analysed the atrial sensing evolution and compared it with a control group that had been implanted with a VDD pacemaker (PM). Results Seventy DX ICD P (82.9% males, age 69±14 years [between 19 and 86], 81.4% implanted as primary prevention) with &amp;gt; 1-year follow-up were included. The control group included 52P (age 82±6.3 years) who underwent PM implantation due to an advanced atrioventricular block. The mean P-wave amplitude at implantation was 4.85±2.44 mV in the DX ICD group and 1.54±0.89 mV in the VDD PM group. At one year after implantation, P-wave amplitude was 4.26±2.68 mV in the DX ICD group and 1.20±1.16 mV in the control group. From the control group, 7P (15,6%) lost atrial sensing after one year of follow-up, having their PM programmed as VVI after that. None of the P in the ICD group had lost atrial sensing in the same time period. After one year of follow-up, the P-wave amplitude had a mean reduction of 41.3% in the DX ICD group and of 65% in the control group (P=0.05). Conclusions Atrial signals can be reliably sensed by the floating dipole rings of a DX ICD in a long-term follow-up. This technology resulted in a higher stability of atrial sensing when compared with that obtained in P with a VDD PM. Additionally, a noteworthy number of P with a VDD PM lost atrial sensing, which did not happen in the group with the DX ICD.Results

Electromechanical Cycle Length Mapping for atrial arrhythmia detection and cardioversion success assessment

Background:Direct current cardioversion (DCCV) is an established treatment to acutely convert atrial fibrillation (AF) to normal sinus rhythm. Yet, more than 70% of patients revert to AF shortly thereafter. Electromechanical Cycle Length Mapping (ECLM) is a high framerate, spectral analysis technique shown to non-invasively characterize electromechanical activation in paced canines and re-entrant flutter patients. This study assesses ECLM feasibility to map and quantify atrial arrhythmic electromechanical activation rates and inform on 1-day and 1-month DCCV response. Methods:Forty-five subjects (30 AF; 15 healthy sinus rhythm (SR) controls) underwent transthoracic ECLM in four standard apical 2D echocardiographic views. AF patients were imaged within 1 h pre- and post-DCCV. 3D-rendered atrial ECLM cycle length (CL) maps and spatial CL histograms were generated. CL dispersion and percentage of arrhythmic CLs≤333ms across the entire atrial myocardium were computed transmurally. ECLM results were subsequently used as indicators of DCCV success. Results:ECLM successfully confirmed the electrical atrial activation rates in 100% of healthy subjects (R2=0.96). In AF, ECLM maps localized the irregular activation rates pre-DCCV and confirmed successful post-DCCV with immediate reduction or elimination. ECLM metrics successfully distinguished DCCV 1-day and 1-month responders from non-responders, while pre-DCCV ECLM values independently predicted AF recurrence within 1-month post-DCCV. Conclusions:ECLM can characterize electromechanical activation rates in AF, quantify their extent, and identify and predict short- and long-term AF recurrence. ELCM constitutes thus a noninvasive arrhythmia imaging modality that can aid clinicians in simultaneous AF severity quantification, prediction of AF DCCV response, and personalized treatment planning.

Association between atrial fibrillation and healthcare costs among patients with cardiac implantable electronic devices

Abstract Funding Acknowledgements Type of funding sources: None. Background Previous research on atrial fibrillation (AF)-related healthcare cost is limited by claims-derived categorization of AF diagnosis and does not assess for incremental differences in cost based on degree of AF burden. Objective To directly assess the incremental cost of device detected AF (ddAF), and compare relative costs among cohorts with no AF, paroxysmal AF (pAF), persistent AF (PeAF), and permanent AF (PermAF) in patients with cardiac implantable electronic devices (CIED) capable of sensitive and continuous atrial arrhythmia detection. Methods Using the de-identified Optum® Clinformatics® U.S. claims database (2015 to 2020) linked with the Medtronic CareLink® database, we identified CIED patients that transmitted data ≥6 months post-implant (baseline period). Annualized per-patient costs in follow up were analyzed from insurance claims and adjusted to 2020 US Dollars. Total costs were compared between patients with no AF and those with device detected pAF, PeAF and PermAF. Analyses were adjusted for geographical region, insurance type, CHA2DS2-VASc Score, and implant year. Results Of the 21,391 patients (72.9±10.9 yrs; 56.3% male) analyzed, 7,798 (36.5%) had ddAF. Among these, 5,966 (76.5%) were pAF (avg burden 2.9±8.6%), 1,145 (14.7%) were PeAF (avg burden 47.2±29.9%), and 687 (8.8%) were PermAF (avg burden 99.3±0.7%). Patients with ddAF had higher overall annualized total healthcare costs than those without ddAF (fig). The incremental annualized increased cost in those with ddAF was $12,789 ± $161,749 per patient. Patients with pAF, PeAF and PermAF all had higher adjusted healthcare costs than those without AF (p for all &amp;lt;0.001). Patients with PeAF and PermAF both had higher total adjusted costs than patients with pAF. In addition, patients with PeAF had higher healthcare costs than those with PermAF (fig). Conclusions In the present analysis of CIED patients, ddAF was associated with increased healthcare costs after adjustment for clinical and demographic covariates. Among those with ddAF, patients with PeAF had the highest healthcare costs. Preventing development of AF, and progression to PeAF, may reduce healthcare costs.

Influence of monitoring and atrial arrhythmia burden on quality of life and health care utilization in patients undergoing pulsed field ablation: A secondary analysis of the PULSED AF trial

Freedom from atrial arrhythmia (AA) recurrence ≥30 seconds after pulsed field ablation (PFA) in patients with atrial fibrillation (AF) was reported in PULSED AF (Pulsed Field Ablation to Irreversibly Electroporate Tissue and Treat AF; ClinialTrials.gov Identifier: NCT04198701). AA burden may be a more clinically meaningful endpoint. The purpose of this study was to determine the influence of monitoring strategies on AA detection and AA burden association with quality of life (QoL) and health care utilization (HCU) after PFA. Patients underwent 24-hour Holter monitoring at 6 and 12 months and weekly, and symptomatic transtelephonic monitoring (TTM). AA burden post-blanking was calculated as the greater of (1) percentage of AA on total Holter time; or (2) percentage of weeks with ≥1 TTM with AA out of all weeks with ≥1 TTM. Freedom from all AAs varied by >20% when differing monitoring strategies were used. PFA resulted in zero burden in 69.4% of paroxysmal atrial fibrillation (PAF) and 62.2% of persistent atrial fibrillation (PsAF) patients. Median burden was low (<9%). Most PAF and PsAF patients had ≤1 week of AA detection on TTM (82.6% and 75.4%) and <30 minutes of AA per day of Holter monitoring (96.5% and 89.6%), respectively. Only PAF patients with <10% AA burden averaged a clinically meaningful (>19 point) QoL improvement. PsAF patients experienced clinically meaningful QoL improvements irrespective of burden. Repeat ablations and cardioversions significantly increased with higher AA burden (P <.01). The ≥30-second AA endpoint is dependent on the monitoring protocol used. PFA resulted in low AA burden for most patients, which was associated with clinically relevant improvement in QoL and reduced AA-related HCU.

High diagnostic accuracy of the detection of atrial arrhythmias from smartwatch electrocardiograms using a deep neural network

High diagnostic accuracy of the detection of atrial arrhythmias from smartwatch electrocardiograms using a deep neural network

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).

The influence of atrial flutter in automated detection of atrial arrhythmias - are we ready to go into clinical practice?”

ObjectiveTo investigate the impact of atrial flutter (Afl) in the atrial arrhythmias classification task. We additionally advocate the use of a subject-based split for future studies in the field in order to avoid within-subject correlation which may lead to over-optimistic inferences. Finally, we demonstrate the effectiveness of the classifiers outside of the initially studied circumstances, by performing an inter-dataset model evaluation of the classifiers in data from different sources. MethodsECG signals of two private and three public (two MIT-BIH and Chapman ecgdb) databases were preprocessed and divided into 10s segments which were then subject to feature extraction. The created datasets were divided into a training and test set in two ways, based on a random split and a patient split. Classification was performed using the XGBoost classifier, as well as two benchmark classification models using both data splits. The trained models were then used to make predictions on the test data of the remaining datasets. ResultsThe XGBoost model yielded the best performance across all datasets compared to the remaining benchmark models, however variability in model performance was seen across datasets, with accuracy ranging from 70.6% to 89.4%, sensitivity ranging from 61.4% to 76.8%, and specificity ranging from 87.3% to 95.5%. When comparing the results between the patient and the random split, no significant difference was seen in the two private datasets and the Chapman dataset, where the number of samples per patient is low. Nonetheless, in the MIT-BIH dataset, where the average number of samples per patient is approximately 1300, a noticeable disparity was identified. The accuracy, sensitivity, and specificity of the random split in this dataset of 93.6%, 86.4%, and 95.9% respectively, were decreased to 88%, 61.4%, and 89.8% in the patient split, with the largest drop being in Afl sensitivity, from 71% to 5.4%. The inter-dataset scores were also significantly lower than their intra-dataset counterparts across all datasets. ConclusionsCAD systems have great potential in the assistance of physicians in reliable, precise and efficient detection of arrhythmias. However, although compelling research has been done in the field, yielding models with excellent performances on their datasets, we show that these results may be over-optimistic. In our study, we give insight into the difficulty of detection of Afl on several datasets and show the need for a higher representation of Afl in public datasets. Furthermore, we show the necessity of a more structured evaluation of model performance through the use of a patient-based split and inter-dataset testing scheme to avoid the problem of within-subject correlation which may lead to misleadingly high scores. Finally, we stress the need for the creation and use of datasets with a higher number of patients and a more balanced representation of classes if we are to progress in this mission.

Smartwatch-based detection of atrial arrhythmia using a deep neural network in a tertiary care hospital

Abstract Funding Acknowledgements Type of funding sources: None. Background/Introduction Smartwatch electrocardiograms (SW ECG) have been identified as a promising noninvasive solution to assess heart rhythm abnormalities, especially atrial arrhythmias (AA) which includes atrial fibrillation, atrial flutter and supraventricular tachycardia. This study evaluates the performance of the detection of AA with a smartwatch and compares the accuracy of two algorithms, the latest version of the original companion application (Apple ECG 2.0 App) and a novel deep neural network (DNN), in a population typical of an electrophysiology department. Purpose Determine if a novel DNN can improve the detection of AA on SW ECG in a tertiary care hospital. Methods 101 patients from the electrophysiology department of one tertiary center were included in this ongoing study. Three simultaneous ECGs were collected for each patient: one 12-lead ECG (Mindray BeneHeart R12) and two SW ECGs (Apple Watch) taken from the left wrist (SWw ECG) and the lower left abdomen (SWa ECG). 12-lead ECGs were adjudicated by a blinded expert electrophysiologist as 52 AA and 49 not AA and considered as gold standard. The SW ECGs were processed by the ECG 2.0 App and the DNN in parallel. The proportions of inconclusive diagnoses returned and the performances were assessed and compared. Results Overall, the ECG 2.0 App yielded inconclusive diagnoses for 19% (19/101) of all SWw ECGs while the DNN reduced that number to 0% (0/101). A similar result holds for SWa ECGs (Figure 1). Regarding the detection of AA from SWw ECGs, the ECG 2.0 App had a sensitivity of 81% (95% CI, 67%-90%), a specificity of 97% (95% CI, 87%-100%) and an accuracy of 89% (95% CI, 80%-94%) while the DNN had a sensitivity of 92% (95% CI, 82%-97%), a specificity of 90% (95% CI, 78%-96%) and an accuracy of 91% (95% CI, 84%-95%). For SWa ECGs (Figure 2), the sensitivity of the DNN was found significantly higher compared to the ECG 2.0 App: 96% (95% CI, 89%-98%) vs 76% (95% CI, 61%-87%). Conclusion(s): A novel DNN algorithm decreased the number of inconclusive diagnostics in the detection of AA from SW ECG from around 20% to 0%, which could help limit the overreading time spent by the physicians. Excluding inconclusive diagnostics, we observed no significant difference in performance between the two algorithms except for the sensitivity for SW ECG taken from the abdomen where the DNN outperforms the ECG 2.0 App. Routine application of this SW ECG analysis in tertiary care hospitals offers significant promise in arrhythmia diagnosis.

Abstract 10175: An Artificial Intelligence-Based Smartwatch Ecg Analysis Improves the Detection of Atrial Arrhythmia

Introduction: Smartwatch ECGs (SW-ECG) have been identified as a noninvasive solution to assess abnormal heart rhythms, especially atrial arrhythmias (AA) which are related to stroke risk. This study assesses the detection of AA with the Apple Watch and compares the accuracy of two algorithms, the original companion application (ECG 1.0 App) and a novel deep neural network (DNN), in a population typical of an electrophysiology department. Hypothesis/Objective: To determine if a novel DNN can improve the detection of AA on SW-ECGs. Methods: 146 simultaneous pairs of 12-lead ECGs (GE Mac 2000 or Mindray BeneHeart R12) and SW-ECGs have been collected on 144 patients from the electrophysiology department of one tertiary center. 12-lead ECGs were adjudicated by an expert electrophysiologist as 40 AA and 106 not AA and considered as ground truth. The SW-ECGs were processed by the ECG 1.0 App and the DNN in parallel. The proportions of inconclusive diagnoses returned and the performances were assessed and compared. Results: Overall, the ECG 1.0 App yielded inconclusive diagnoses for 25% (37/146) of all SW-ECGs while the DNN reduced that number to 1% (2/146). After excluding SW-ECGs with an inconclusive diagnosis (37/146), the ECG 1.0 App and the DNN had a sensitivity of 62% (95% CI, 55%-70%) and 96% (95% CI, 93%-99%) respectively, and both had a specificity of 95% (95% CI, 92%-99%). Conclusions: A novel DNN improved the performance for the detection of AA. It reduced the burden of inconclusive diagnostics by 24% and improved the sensitivity by 34% with no change in specificity. Routine application of this SW-ECG analysis offers significant promise in arrhythmia diagnosis. Further investigations are needed to assess the classification of atrial arrhythmias more precisely.

Role of Remote Monitoring in Detection of Atrial Arrhythmia, Stroke Reduction, and Use of Anticoagulation Therapy - A Systematic Review and Meta-Analysis.

The effect of remote monitoring (RM) in atrial arrhythmia detection, stroke reduction, and anticoagulation therapy remains unknown, particularly for patients with implantable or wearable cardiac devices. We performed a systematic review and meta-analysis to evaluate the role of RM in atrial arrhythmia detection, stroke reduction and anticoagulation therapeutic intervention. Online databases were queried to include randomized controlled trials comparing detection of atrial arrhythmia and stroke risk between patients undergoing RM and those receiving in-office (IO) follow-up. Outcomes and complications of RM-guided anticoagulation therapy and conventional therapy in patients with atrial fibrillation were also reviewed. A total of 16 studies were included. Compared with patients receiving IO follow-up, patients undergoing RM had a significantly higher detection rate of atrial arrhythmia (risk ratio [RR], 1.363; 95% confidence interval [CI], 1.147-1.619), and a lower risk of stroke (RR, 0.539; 95% CI, 0.301-0.936). The higher rate of atrial arrhythmia was only noted in patients with wearable devices (RR, 4.070; 95% CI, 2.408-6.877), and the lower risk of stroke was only noted in patients with cardiovascular implantable electronic devices (CIED) (RR, 0.513; 95% CI, 0.265-0.996). RM is effective for atrial arrhythmia detection in patients using wearable devices and for reducing the risk of stroke in patients with CIED.

Modeling Framework for the Generation of Synthetic RR Series during Atrial Arrhythmias.

We introduced a modeling framework for the generation of realistic ventricular interval (RR) series to be used in the validation of atrial arrhythmia detection algorithms. The framework included three previously proposed models, which reproduced the specific variability properties of RR series in normal sinus rhythm, atrial flutter (AFL) and atrial fibrillation (AF). Transitions between the three rhythms were governed by a three-state continuous-time Markov chain model, which could be tuned to obtain arrhythmic episodes of the requested length. As a representative application, the modeling framework was used to generate a database of RR series for the validation of a previously proposed AF detection algorithm, which was based on RR pattern similarity. The validation showed the deterioration of detector performance in presence of simulated AFL episodes. Thanks to the detailed reproduction of the specific features of the two most common atrial arrhythmias, our modeling framework may constitute a novel tool for the assessment and comparison of detection algorithm performance.

Prevalence and predictors of atrial arrhythmias in patients with sinus node dysfunction and atrial pacing.

This study aimed to determine the incidence, prevalence, and predictors of atrial arrhythmias (AAs) in patients with symptomatic sinus node dysfunction (SND) who required permanent pacemaker implantation. Also, we evaluated the impact of atrial pacing (AP) on AAs. All consecutive patients who underwent pacemaker implantation from 2005 to 2011 were included. Atrial fibrillation (AF), atrial flutter (AFL), atrial tachycardia (AT), and AV nodal reentrant tachycardia (AVNRT) were detected via pacemaker interrogation and clinical documentation. The study group included 322 patients (44% male) with mean age 68.8 ± 15years and followed for an average of 5.6 ± 2.2years (median 5.7years). Overall, 61.8% were found to have any AA at follow-up. Individual prevalence of AAs was high as follows: AF 43.5%, AFL 6.5%, AT 25%, and AVNRT 6.8%. AF was documented in 23% of patients (n = 74) prior to pacemaker; among those, 15% (n = 11) had no recurrence of AF with average AP of 74%. The incidence of new-onset AF after pacemaker was 15.8%. In subgroup analysis, prevalence of AF was increased by 16% with high rate of AP (81-100%) and 17% with lower rate of AP (0-20%). Incidence of new-onset AF was not affected by AP. Diabetes, hypertension, and left atrial enlargement were predictors of AAs. White men and women had higher prevalence of AF. AAs are highly prevalent in SND, particularly in white patients. Paroxysmal AF is suppressed with AP in minority, but there is no impact of AP on new-onset AF. Patients with diabetes, hypertension, and dilated atria must be monitored closely for early detection of AAs.

A Diagnostic System for Detection of Atrial and Ventricular Arrhythmia Episodes from Electrocardiogram

Cardiac arrhythmias, with each passing day, are becoming highly prevalent in modern society. The ever increasing number of patients added to the sheer amount of data that is recorded from a patient during monitoring limits the ability of a medical practitioner to diagnose these problems quickly. Therefore, an intelligent system is required which can produce a reliable diagnosis in a short period of time. In this paper, a new intelligent diagnostic system for detection of atrial arrhythmia (atrial flutter and atrial fibrillation) and ventricular arrhythmia (premature ventricular contractions, ventricular bigeminy, ventricular escape rhythm, ventricular tachycardia and ventricular fibrillation) episodes from Electrocardiogram (ECG) is proposed. This system is based on the non-linear analysis of the variational modes of ECG. Variational mode decomposition is used for decomposition of ECG signal into several modes. Then, the non-linear features namely, the distribution entropy and the sample entropy are evaluated from the modes of ECG. The performance of variational mode distribution entropy (VMDE) and variational mode sample entropy (VMSE) features is assessed using support vector machine (SVM) and adaptive neuro-fuzzy inference system classifiers. Experimental results reveal that, the combination of VMDE and VMSE features, and the radial basis function kernel based multi-class SVM classifier are suitable for detection of arrhythmia episodes from ECG with an average accuracy value of 95.60%.

Home monitoring report from a single lead Lumax DX implantable cardioverter defibrillator: New observations in a new system

A 56-year-old man underwent a single lead Lumax 640 DX implantable cardioverter defibrillator implantation for primary prevention of sudden cardiac death. A DX system consists of a single lead, which provides atrial as well as ventricular electrograms, and enhances atrial arrhythmia detection. Three months after the implantation, high-frequency episodes were detected on the far field and the atrial channels, but not on the bipolar right ventricular channel; these were classified as atrial tachycardia. In the present report, we discussed the unusual pattern of the artifacts that was related to an electromagnetic interference detected by the novel DX system.

Early detection and treatment of atrial arrhythmias with home monitoring may decrease atrial fibrillation burden in pacemaker recipients: The randomized, multicenter SETAM trial

Background Home monitoring (HM) technology in pacemakers provides relevant daily notifications on atrial high-rate for detection of atrial arrhythmias. The SETAM trial has already shown as a main endpoint that HM reduced the time to manage atrial arrhythmias as compared to conventional follow-ups in pacemaker recipients. Purpose As secondary objective, the SETAM trial examined the impact of HM on atrial fibrillation burden per day (percentage of time at a high-defined atrial rate) and clinical events. Methods Recipients of dual chamber pacemaker were eligible for enrolment if they were in sinus rhythm, untreated with antiarrhythmics and antithrombotics and if they had a ≥ 2 CHA2DS2-VASc score for thromboembolic risk. The patients were randomly assigned to an active group followed by HM (HM-ON), or a control group without home monitoring surveillance (HM-OFF). The proportion of patients who experienced at least one serious adverse event (SAE) and the mean atrial fibrillation burden (percentage of time per 24 h spent at an atrial rate > 200 bpm) were compared between the groups. Results A total of 595 patients (mean age = 79 ± 8 y.o, 63% male, mean CHA2DS2-VASc score = 3.7 ± 1.2) were followed during 12.8 ± 3.3 months. The most prevalent concomitant disorders were hypertension (81% patients), diabetes (29%) and vascular disease (24%). Atrial arrhythmias were detected in 83 of 291 patients (28%) in the HM-ON group versus 66 of 304 patients (22%) in the HM-OFF group (P = ns). A treatment was prescribed to 49 of the 83 patients (59%) in the HM-ON group vs 43 of the 66 patients (65%) in the HM-OFF group (P = ns). Anticoagulation was introduced in 80% of patients and antiarrhythmic drugs in 55% of patients with similar rates in both study groups. Among the 92 treated patients, the 12-month atrial fibrillation burden was ≤ 10%/24 h in 33 patients (89%) in the HM-ON group, vs 21 patients (68%) in the HM-OFF group (P = 0.03). This significant difference was observed over time: the mean atrial fibrillation burden was reduced by 4 hours per day (18% of 24 h) over the last 4 months of follow-up in the HM-ON group (6 ± 19% per day versus 24 ± 41% per day in the HM-OFF, P = 0.04). No significant difference was observed between the groups in terms of SAE. Conclusion The SETAM study provided evidence that early detection and treatment of atrial arrhythmias with home monitoring reduced atrial fibrillation burden in pacemaker recipients.