Detection Of Paroxysmal Atrial Fibrillation Research Articles

An explainable AI for trustworthy detection of atrial fibrillation on reduced lead ECGs in mobile applications

Abstract Introduction Artificial intelligence (AI), particularly deep learning (DL), has demonstrated high performance in various diagnostic problems, including the detection of paroxysmal atrial fibrillation (AF) from electrocardiograms (ECGs). In mobile applications, these approaches can help to detect AF at an early stage and thus prevent possible secondary diseases. However, due to their black-box nature, DL approaches lack explainability and interpretability. Furthermore, 12-lead ECGs are the clinical standard, but mobile devices usually only provide 1–3 leads, which are similar but not identical to Einthoven leads and differ in morphology. Purpose We apply a recently introduced explainable ECG analysis architecture (xECGArch) to single-lead ECGs to verify its performance in mobile applications. xECGArch can learn rhythmic and morphological characteristics using two parallel convolutional neural networks of different dimensions (Fig. 1). When combined with methods from explainable AI, the classification can be traced back to rhythmic and morphological characteristics. Methods We used a subset of 9 854 ECGs (n(AF) = n(non-AF) = 4 927) from 4 public databases (Chapman-Shaoxing, CPSC2018, Georgia, and PTB-XL). Noise was removed using a cascade of high-pass filtering at 0.3 Hz and discrete wavelet transform. For each lead, we trained xECGArch on single-lead ECGs of 10 s length to classify AF vs. non-AF using 90% of the ECGs with 5-fold cross-validation and tested it on the remaining randomly selected ECGs (n(AF) = 507, n(non-AF) = 479). Consistent data splitting was ensured for all leads. Model explanations were generated using deep Taylor decomposition. Results Both models achieved minimum 91.1% accuracy for each ECG lead (Fig. 1). On lead I, the morphology model outperformed the rhythm model with 92.8% vs. 91.5% accuracy, while the rhythm model slightly outperformed the morphology model on leads II and III with 94.2%–95.0% accuracy vs. 91.1%–94.0%. Both models achieved maximum accuracy of 95.0% (rhythm) and 94.0% (morphology) on lead II. By combining both models, xECGArch reached 93.7%–95.1% accuracy. The model explanations confirm that the rhythm model primarily considers QRS complexes as relevant, while the morphology model focuses on fibrillatory waves (Fig. 1). Conclusions Both rhythm and morphology models achieved reliable results across all leads, competing with the state-of-the-art for automatic AF detection from single-lead ECGs. The combination of both models in xECGArch further increased the accuracy. xECGArch is based on the medical reading of ECGs by considering rhythm and morphology characteristics and is therefore interpretable by design. The model explanations are consistent with the diagnostic criteria for AF (Fibrillatory waves and absolute arrhythmia) across leads. With high accuracy on different single-lead ECGs and improved interpretability, xECGArch provides a trustworthy method for ECG analysis in mobile applications.

Screening Tool for Paroxysmal Atrial Fibrillation Based on a Deep-Learning Algorithm Using Printed 12-Lead Electrocardiographic Records during Sinus Rhythm.

Recent advancements in artificial intelligence (AI) have significantly improved atrial fibrillation (AF) detection using electrocardiography (ECG) data obtained during sinus rhythm (SR). However, the utility of printed ECG (pECG) records for AF detection, particularly in developing countries, remains unexplored. This study aims to assess the efficacy of an AI-based screening tool for paroxysmal AF (PAF) using pECGs during SR. We analyzed 5688 printed 12-lead SR-ECG records from 2192 patients admitted to Beijing Chaoyang Hospital between May 2011 to August 2022. All patients underwent catheter ablation for PAF (AF group) or other electrophysiological procedures (non-AF group). We developed a deep learning model to detect PAF from these printed SR-ECGs. The 2192 patients were randomly assigned to training (1972, 57.3% with PAF), validation (108, 57.4% with PAF), and test datasets (112, 57.1% with PAF). We developed an applet to digitize the printed ECG data and display the results within a few seconds. Our evaluation focused on sensitivity, specificity, accuracy, F1 score, the area under the receiver-operating characteristic curve (AUROC), and precision-recall curves (PRAUC). The PAF detection algorithm demonstrated strong performance: sensitivity 87.5%, specificity 66.7%, accuracy 78.6%, F1 score 0.824, AUROC 0.871 and PRAUC 0.914. A gradient-weighted class activation map (Grad-CAM) revealed the model's tailored focus on different ECG areas for personalized PAF detection. The deep-learning analysis of printed SR-ECG records shows high accuracy in PAF detection, suggesting its potential as a reliable screening tool in real-world clinical practice.

Abstract NS8: Interventional Nurse Practitioner-Led Loop Recorder Implantation Program: Impact on Quality of Etiopathogenic Diagnosis of Ischemic Stroke

Background: Extended cardiac rhythm monitoring increases the odds of detecting paroxysmal atrial fibrillation (PAF), an important finding in the etiopathogenic evaluation of patients with ischemic stroke. The development of a systematic approach to extended cardiac monitoring in this population is bound to positively influence the quality of diagnostic evaluation and, by extension, the application of tailored protocols for secondary stroke prevention. Methods: We retrospectively analyzed our experience with a cardiac loop recorder implantation program specifically designed for ischemic stroke patients suspected of having cardiogenic embolism, led and implemented by an interventional nurse practitioner in our team. We specifically queried its diagnostic yield as it relates to the quality of etiopathogenic diagnosis of this population. Results: The program has been currently in operation for 21 months, during which, 103 patients have undergone successful implantation of a cardiac loop recorder. The cohort includes 54 women and 49 men, their ages ranging 39-89 years (Mean = 67), 90 (87.38%) of whom had suffered an ischemic stroke, while the remainder had transient ischemic attacks. A total of 12 (11.65%) patients had newly detected PAF during the monitoring period, which varied 12-612 days (Mean = 316). The interval from implantation to PAF detection varied 3-202 days (mean = 90). Only one (0.97%) procedural complication (i.e., site infection) occurred, requiring device explantation without any long-term effects. All instances (100%) of PAF detection resulted in a change in from antiplatelet to anticoagulant agents for secondary stroke prevention. Conclusions: Programmatic implantation of cardiac loop recorders can successfully be carried out by interventional nurse practitioners, and it effectively enhances the etiopathogenic evaluation of ischemic stroke patients. Moreover, its yield for detection of PAF is considerable, and it translates in measurable changes in preventive antithrombotic regimens.

A Program to Optimize the Detection of Paroxysmal Atrial Fibrillation: The RITMO Study.

Atrial fibrillation (AF) is the most common sustained arrythmia, but still underdiagnosed especially among asymptomatic patients. To evaluate a simple strategy to optimize the identification of AF. Asymptomatic patients aged 65 years or older, with hypertension or heart failure (HF), were included. Data were inserted into the REDCap software platform. Patients were assessed for the risk for AF using the Stroke Risk Analysis (SRA) mathematical algorithm, which was applied on a one-hour electrocardiogram (ECG). All patients at high risk for AF were instructed to follow a home ECG protocol for seven days using a portable Kardia 6 (OMRON, AliveCor®). The Kolmogorov-test was used to test the normality of quantitative variables; those with normal distribution were expressed as mean and standard deviation. A p<0.05 was set as statistically significant. A total of 423 patients were assessed; 15 were excluded due to absence of SRA, yielding a sample of 408 patients. In 13 (3.2%), AF was identified, 120 (29.4%) were considered at high risk and 275 (67.4%) without increased risk for AF. Of the 120 high-risk patients, 111 successfully completed the seven-day protocol with Kardia; at least one episode of AF was identified in 43 patients. The strategy adopted in the RITMO study was shown to be effective in identifying AF in asymptomatic elderly patients with hypertension or HF, with an incidence of 13.7% (56/408).

Short-term paroxysmal atrial fibrillation detection with intra- and inter-patient paradigm based on R-R intervals

Paroxysmal Atrial Fibrillation (PAF) may lead to the decline of atrial mechanism and hemodynamic disturbance, which is the major risk factor for stroke, myocardial infarction, heart failure and other diseases. Although a number of methods have been developed to detect PAF, they rely on long ECG signals. Furthermore, most studies are only for the intra-patient test, ignoring individual specificity. Therefore, this paper proposes an automatic detection algorithm based on the combination of RR interval time-domain and nonlinear features to detect short-term PAF. The proposed features reflect the underlying physiological phenomenon of highly irregular ventricular activity caused by atrial unstable conduction. These include changes in morphological features and intrinsic changes in the cardiac dynamic system, which can capture subtle changes in early short-term PAF episodes and attenuate specificity between individuals. Finally, the random forest algorithm was used to detect the MIT-BIH Atrial Fibrillation Database and MIT-BIH Arrhythmia Database with intra-patient and inter-patient paradigm. The results show that the two databases’ algorithm accuracy in different paradigms of intra-patient and inter-patient have achieved more than 99.50% and 95.50%, respectively. Therefore, the proposed algorithm has a potential application for clinical monitoring.

The exploratory clinical trial of AI-enabled Holter electrocardiogram for diagnosis of paroxysmal atrial fibrillation from sinus rhythm waveforms

Abstract Backgrounds Machine learning (ML) models using convolutional neural networks (CNNs) have been successfully applied to arrhythmia detection and prediction. The current study aimed to develop a CNN-based AI algorithm for the prediction of paroxysmal atrial fibrillation (PAF) patients during sinus rhythm waveforms from Holter electrocardiograms. Methods A ML model was developed by using 2-leads from Holter ECG waveforms divided into slots of 30 seconds each. As training data, we prepared &amp;gt; 300000 slots with sinus rhythm and they were subsequently converted to image data for application to the CNN-based AF detection algorithm. The performance metrics obtained for the ML model for PAF detection were as follows: sensitivity, 85.2 %; specificity, 64.0 % and AUC for PAF prediction was 0.84. To validate the performance of the ML model, multicenter clinical trial was conducted. The clinical trial was conducted at three independent centers and included 24 patients with PAF and 20 patients in true sinus rhythm. Five factors were matched between the PAF and sinus groups: age, gender, hypertension under treatment, diabetes under treatment, and smoking. Waveform data from validation datasets to Grad-CAM were applied to obtain explainable AI (XAI) images, which allowed for a heat map over the waveform to be produced. Results For the primary endpoint, the estimated sensitivity and specificity [95% CI] were 91.7% [73.0-99.0%] and 65.0% [40.8-84.6%], respectively (Table 1). The sensitivity and specificity of the secondary endpoints using 10 time-independent slots were the same as for the primary endpoint. Regarding safety endpoints, no adverse events attributable to the test device itself were observed. Based on the regions of interest highlighted via Grad-CAM, the most contributing featured regions to predict PAF were indicated by areas on P waves and QT area (Figure 1). Featured regions to rule out the existence of PAF indicated areas just on QRS waves were also present. It was therefore determined that the proposed CNN-based ML model focuses on the P-wave area and atrial repolarization area in the case of PAF. Conclusion The study suggested that 2-lead Holter ECG with 30 second slot could detect PAF patients from their sinus rhythm waveforms and the performance was more effectively than using 12-lead ECGs. The results of this clinical trial are expected to contribute to the screening of patients with PAF that could not be detected by a single time Holter ECG.Table 1Figure 1

Accurate detection of paroxysmal atrial fibrillation with certified-GAN and neural architecture search

This paper presents a novel machine learning framework for detecting PxAF, a pathological characteristic of electrocardiogram (ECG) that can lead to fatal conditions such as heart attack. To enhance the learning process, the framework involves a generative adversarial network (GAN) along with a neural architecture search (NAS) in the data preparation and classifier optimization phases. The GAN is innovatively invoked to overcome the class imbalance of the training data by producing the synthetic ECG for PxAF class in a certified manner. The effect of the certified GAN is statistically validated. Instead of using a general-purpose classifier, the NAS automatically designs a highly accurate convolutional neural network architecture customized for the PxAF classification task. Experimental results show that the accuracy of the proposed framework exhibits a high value of 99.0% which not only enhances state-of-the-art by up to 5.1%, but also improves the classification performance of the two widely-accepted baseline methods, ResNet-18, and Auto-Sklearn, by 2.2% and 6.1%.

Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model.

Atrial fibrillation (AF) is one of the most common arrhythmias clinically. Aging tends to increase the risk of AF, which also increases the burden of other comorbidities, including coronary artery disease (CAD), and even heart failure (HF). The precise detection of AF is a challenge due to its intermittence and unpredictability. A method for the accurate detection of AF is still needed. A deep learning model was used to detect atrial fibrillation. Here, a distinction was not made between AF and atrial flutter (AFL), both of which manifest as a similar pattern on an electrocardiogram (ECG). This method not only discriminated AF from normal rhythm of the heart, but also detected its onset and offset. The proposed model involved residual blocks and a Transformer encoder. The data used for training were obtained from the CPSC2021 Challenge, and were collected using dynamic ECG devices. Tests on four public datasets validated the availability of the proposed method. The best performance for AF rhythm testing attained an accuracy of 98.67%, a sensitivity of 87.69%, and a specificity of 98.56%. In onset and offset detection, it obtained a sensitivity of 95.90% and 87.70%, respectively. The algorithm with a low FPR of 0.46% was able to reduce troubling false alarms. The model had a great capability to discriminate AF from normal rhythm and to detect its onset and offset. Noise stress tests were conducted after mixing three types of noise. We visualized the model's features using a heatmap and illustrated its interpretability. The model focused directly on the crucial ECG waveform where showed obvious characteristics of AF.

Detection of atrial fibrillation and sinus pause in embolic stroke of undetermined sources by chest strap‐style 7‐day Holter monitoring

AbstractBackgroundLong‐time monitoring of electrocardiogram with an implantable loop recorder is useful for detection of paroxysmal atrial fibrillation (PAF) in ESUS patients. However, usefulness of noninvasive 7‐day Holter monitoring has not been established. Furthermore, the incidence of other arrhythmias such as sinus pause (SP) remains unknown.Aim(1) The aim of this study was to examine the usefulness of 7‐day Holter monitoring to detect PAF in both acute and chronic periods since index stroke and (2) to clarify the incidence of SP in ESUS patients.MethodsProspectively, a total of 738 patients including 241 consecutive ESUS patients were enrolled, from April 2016 to March 2021. One hundred forty patients among 241 consecutive ESUS patients underwent chest strap‐style 7‐day Holter monitor. We examined PAF and SP (≧3 s).ResultsThe 7‐day Holter monitoring started since index stroke at a median of 17 days. Among 80 patients within 1 month since index stroke, PAF was detected in three patients (3.8%) and SP was in two patients (2.5%). By contrast, among 52 patients over 1 month since index stroke, PAF was found in only one patients (1.9%).ConclusionAlthough the incidence of PAF detected with this monitoring was low (3.8%) in ESUS patients, SP was also found in 2.5% within 1 month since index stroke. Within 1 month since stroke onset in ESUS patients, 7‐day Holter monitoring would be useful for detection of PAF and SP that would be potentially a cardiac source of embolism and might require urgent intervention.

Removal of Insertable Cardiac Monitor for Cryptogenic Stroke: A Technical Note.

Insertable cardiac monitors (ICM) allow continuous long-term electrocardiogram monitoring and the detection of paroxysmal atrial fibrillation (PAF) in patients with cryptogenic stroke (CS). Several years have passed since ICM was indicated for CS, and many stroke neurologists will experience cases in which ICM removal is required. As a standard protocol, reincision of the wound at the time of implantation has been proposed by ICM brands. However, it may be difficult due to adhesions of subcutaneous tissue, migration of the device from its original position, and the capsule formed around the device. Our objective is to describe simple alternative techniques for successful ICM removal. From December 2016 to September 2021, 37 patients with CS underwent ICM removal at our institution. The device was removed through an incision directly above the proximal end of the device, perpendicular to the wound at the time of ICM implantation. The subcutaneous tissue was removed bluntly using forceps along the edges of the proximal end of the device. When a capsule was attached to the device, we cut the capsule with the blade to release the device. Once the device was visible, the proximal end of the device was grasped with forceps, and the device was pulled from the pocket with gentle traction. All patients undergoing ICM removal received a systematic check for wound dehiscence, wound infection, bleeding, and tissue ischemia at an outpatient examination of 1 week. The 37 patients who underwent removal of ICM were retrospectively reviewed in the medical record and analyzed for procedural success, intraoperative complications, and wound course at one week. All patients achieved procedural success. There were no intraoperative complications, wound dehiscence, bleeding, or skin ischemia at one week postoperatively. The reasons for removal were battery depletion in 65%, early removal before battery life after PAF detection in 32%, and exposure to the body surface in 3%. The devices removed were 62% Reveal LINQ (Medtronic, Minneapolis), 30% Confirm Rx (Abbott, Illinois), and 8% BioMonitor 2 (BIOTRONIK, Berlin), indicating that our method is effective regardless of model. We describe a simple technique for ICM removal for CS that is safe, reliable, and potentially effective in wound healing.

Useful Test for Classification of Cerebral Infarction at Hospital Specializing in Neurosurgery.

Background and Purpose: There are many cases of cerebral infarction of unknown etiology in which the embolic sources cannot be identified including atrial fibrillation despite achievement of complete revascularization after thrombectomy. Method: An analysis was conducted for 556 consecutive cases of patients who were hospitalized for cerebral infarction to determine the significance of accurate classification of disease type and investigation into causes of cerebral infarction of unknown cause. Result: According to the Trials of Org 10172 in Acute Stroke Treatment (TOAST) classification, cerebral infarction of other/unknown etiology was observed in 94 cases, of which 22 cases were found to have causes by additional workup. Implantable cardiac monitors were inserted in 15 of 76 cases of cryptogenic cerebral infarction, of which 4 cases (26%) showed detection of paroxysmal atrial fibrillation (PAF) during observation period (223-384 days). Conclusion: Brain natriuretic peptide (BNP) measurement, abdomen-pelvic computed tomography (CT), cardiac monitoring for 1 week, and implantable cardiac monitors (ICM) were useful for the classification of disease type and detection of cryptogenic atrial fibrillation. (This is secondary publication from J Jpn Coll Angiol 2021; 61: 49-55.).

A comparative study on neural networks for paroxysmal atrial fibrillation events detection from electrocardiography

ObjectiveThis work conducts a comparative study on the effect of neural networks of different architectures on the detection of paroxysmal atrial fibrillation (PAF) events from dynamic electrocardiography (ECG) recordings, a problem raised in the 4th China Physiological Signal Challenge 2021 (CPSC2021). ApproachWe proposed 3 neural network models and an auxiliary one for QRS detection to tackle the problem. A convolutional recurrent neural network (CRNN) model and a U-Net model that accepts ECG waveform input make sample-wise predictions. This regards the PAF events detection as a segmentation task. A stacked bidirectional long short-term memory (LSTM) model takes the sequence of RR intervals, which is derived from the output of the QRS detection model and makes beat-wise predictions. The QRS detection model also has a CRNN architecture, which is slightly different from the model for the AF segmentation task. Final predictions are merged by outputs from models making sample-wise predictions and making beat-wise predictions. Finally, the locations of QRS complexes are used to filter out segments (both normal and AF) shorter than 5 beats.In order to make the neural network models more sensitive to the critical sample points (onsets and offsets) of the AF events, we proposed a novel masked binary cross-entropy (MaskedBCE) loss function for training the models. This loss function is the conventional BCE loss multiplied by a mask, whose values in a neighbourhood of critical sample points are significantly larger than elsewhere. Main resultsOur method received a score of 1.9972 on the first part of the hidden test set of CPSC2021 and a score of 3.0907 on the second part. The average score was 2.5440, ranked 5th out of 17 teams with successful official entries. SignificanceThis work proposed an effective solution to the problem of the detection of PAF events from dynamic ECGs and validated the efficacy of several neural network architectures on this problem.

Predicting Paroxysmal Atrial Fibrillation in Patients with Embolic Stroke of Undetermined Source (Esus) In the Real-World Practice: Comparison Between Brown-Af, As5f And Cha2ds2-Vasc Scores

Introduction: Searching paroxysmal atrial fibrillation (PAF) is fundamental and strongly recommended in patients suffering from cryptogenic stroke or embolic stroke of undetermined source (ESUS). In the latest years some prediction scores for detecting post-stroke PAF have been proposed, such as Brown-AF and AS5F. However, external validations lack. The aim of the present study was to analyze the predictive power of AS5F and Brown-AF scores and compare them with the CHA2DS2-VASc score. Materials and Methods We analyzed demographic, clinical, trans-thoracic echocardiography and brain computer tomography characteristics of patients with ESUS undergone to two weeks external ECG monitoring after hospital discharge. PAF was considered detected when any evidence of AF and/or atrial flutter occurred at monitoring. For each patient we calculated the Brown-AF, AS5F and CHA2DS2-VASc scores and we analyzed and compared their predictive power by using area under the Receiver Operating Curve (AUROC). Results: Eighty-two consecutive ESUS patients with mean age ± SD 72 ± 10 years were the study population. Overall, PAF was detected in 43.9% of patients. PAF detection increased from 18.75% of patients with Brown ESUS-AF score 0 to 54.3% of patients with Brown ESUS-AF score ≥ 2. PAF was detected in 37.2% of patients with AS5F &lt; 67.5 and 51.2% of patients with AS5F score ≥ 67.5. AUROC of Brown ESUS-AF score in predicting AF detection was 0.642 (95% CI: 0.528-0.745), while AUROC of AS5F was 0.618 (95% CI: 0.504-0.723)(p=0.6872). No difference between predictive power of Brown ESUS-AF and AS5F scores with CHA2DS2-VASc (AUROC 0.671, 95% CI: 0.559-0.771) was found. Conclusion: Both Brown ESUS-AF and AS5F scores could be used as a screening tool for selecting ESUS patients requiring prolonged ECG monitoring aimed to detect PAF. However, in our study their predictive power was quite low and not superior to that of CHA2DS2-VASc score.

Diagnosis of Atrial Fibrillation Using Machine Learning With Wearable Devices After Cardiac Surgery: Algorithm Development Study.

BackgroundSome attempts have been made to detect atrial fibrillation (AF) with a wearable device equipped with photoelectric volumetric pulse wave technology, and it is expected to be applied under real clinical conditions.ObjectiveThis study is the second part of a 2-phase study aimed at developing a method for immediate detection of paroxysmal AF, using a wearable device with built-in photoplethysmography (PPG). The objective of this study is to develop an algorithm to immediately diagnose AF by an Apple Watch equipped with a PPG sensor that is worn by patients undergoing cardiac surgery and to use machine learning on the pulse data output from the device.MethodsA total of 80 patients who underwent cardiac surgery at a single institution between June 2020 and March 2021 were monitored for postoperative AF, using a telemetry-monitored electrocardiogram (ECG) and an Apple Watch. AF was diagnosed by qualified physicians from telemetry-monitored ECGs and 12-lead ECGs; a diagnostic algorithm was developed using machine learning on the pulse rate data output from the Apple Watch.ResultsOne of the 80 patients was excluded from the analysis due to redness caused by wearing the Apple Watch. Of 79 patients, 27 (34.2%) developed AF, and 199 events of AF including brief AF were observed. Of them, 18 events of AF lasting longer than 1 hour were observed, and cross-correlation analysis showed that pulse rate measured by Apple Watch was strongly correlated (cross-correlation functions [CCF]: 0.6-0.8) with 8 events and very strongly correlated (CCF>0.8) with 3 events. The diagnostic accuracy by machine learning was 0.9416 (sensitivity 0.909 and specificity 0.838 at the point closest to the top left) for the area under the receiver operating characteristic curve.ConclusionsWe were able to safely monitor pulse rate in patients who wore an Apple Watch after cardiac surgery. Although the pulse rate measured by the PPG sensor does not follow the heart rate recorded by telemetry-monitored ECGs in some parts, which may reduce the accuracy of AF diagnosis by machine learning, we have shown the possibility of clinical application of using only the pulse rate collected by the PPG sensor for the early detection of AF.

Sinus rhythm restoration and improved outcomes in patients with acute ischemic stroke and in-hospital paroxysmal atrial fibrillation.

It is unclear whether early cardiac rhythm control is beneficial in patients with acute ischemic stroke and paroxysmal atrial fibrillation (PAF). We sought to investigate whether PAF self-termination and in-hospital sinus rhythm (SR) restoration is associated with improved outcome in ischemic stroke patients with PAF, compared to those with sustained atrial fibrillation (AF). Consecutive patients with first-ever acute stroke and confirmed PAF during hospitalization were followed for up to 10 years after the index stroke or until death. We investigated the association of in-hospital self-terminated PAF and PAF conversion to SR compared to sustained AF with 10-year all-cause mortality, stroke recurrence, and major adverse cardiovascular events (MACE). Cox regression analysis was performed to identify independent predictors of each outcome. Among 297 ischemic stroke patients with in-hospital PAF detection, PAF was self-terminated in 87 (29.3%) patients, while 143 (48.1%) patients received antiarrhythmic medication in order to achieve PAF conversion to SR. During a median (Interquartile range, IQR) period of 28 (4-68) months, among patients with self-terminated PAF there were 13.5 deaths, 3.6 stroke recurrences, and 5.3 MACE per 100 patient-year while in patients who underwent medical PAF conversion there were 11.7 deaths, 4.6 stroke recurrences, and 5.8 MACE per 100 patient-year. Patients with sustained AF experienced 23.8 deaths, 8.7 stroke recurrences, and 13.9 MACE per 100 patient-years. In multivariable analysis, compared to patients with sustained AF, PAF self-termination was associated with significantly lower 10 years-risk of death (adjusted hazards ratio (adjHR): HR: 0.63, 95% Confidence interval: 0.40-0.96), stroke recurrence (adjHR: HR: 0.41, 95% CI: 0.19-0.91), and MACE (adjHR: 0.43, 95% CI: 0.23-0.81), while PAF medical conversion to SR was associated with lower 10 years-risk of death (adjHR: 0.65, 95% CI: 0.44-0.97) and MACE (adjHR: 0.56, 95% CI: 0.33-0.95). This study showed that in-hospital PAF self-termination was associated with lower risk of 10-year mortality, stroke recurrence, and MACE, potentially attributed to the lower burden of AF, whereas in-hospital PAF conversion to SR was associated with lower risk of 10-year mortality and MACE. Early restoration of sinus rhythm is associated with improved survival and MACE in patients with acute ischemic stroke and PAF.

Predictive Power of Brown Esus-Af Score for Detection of Post Stroke Atrial Fibrillation: A Brief Report from Real World

Introduction: Searching paroxysmal atrial fibrillation (PAF) is the cornerstone in post embolic stroke of undetermined source (ESUS) patients. The Brown ESUS-AF score was proposed as a simple and good prognosticator of poststroke PAF detection. Age (≥ 75 years 2 points, 65-74 years 1 point) and moderate-severe left atrial enlargement (LAE, 2 points) are the variables enclosed in the score. External validation of Brown ESUS-AF score was the aim of the present study. Materials and Methods: We analyzed demographic, clinical, trans-thoracic echocardiography and brain computer tomography characteristics of patients with ESUS undergone to two weeks external ECG monitoring after hospital discharge. PAF was considered detected when any evidence of AF and/or atrial flutter occurred at monitoring. Results: Eighty-two consecutive ESUS patients with mean age ± SD 72 ± 10 years were the study population. PAF detection increased from 18.75% of patients with Brown ESUS-AF score 0 to 54.3% of patients with Brown ESUS-AF score ≥ 2. AUC of Brown ESUS-AF score in predicting AF detection was 0.642 (95% CI: 0.528-0.745). No difference between predictive power of Brown ESUS-AF score and CHA2DS2-VASc score was found. Conclusion: Brown ESUS-AF score could be used as a screening tool for selecting ESUS patients requiring prolonged ECG monitoring aimed to detect PAF. However, in our study the predictive power of Brown ESUS-AF score was not superior to that of CHA2DS2-VASc score.

Detection of paroxysmal atrial fibrillation in 994 patients with a cerebrovascular event by intermittent 21-day ECG-monitoring and 7-day continuous Holter-recording

BackgroundThe detection of paroxysmal atrial fibrillation (AF) is of importance in stroke care. The method used is continuous electrocardiogram (ECG)-monitoring or multiple short ECG-recordings during an extended period. Their relative efficiency is a matter of discussion. In a retrospective cohort study on 994 patients with an ischemic stroke or transient ischemic attack (TIA), we have compared continuous 7-day monitoring to intermittent recording 60 sec three times daily with a handheld device during 3 weeks. We related the result to subsequent occurrence of AF as detected in 12-lead ECG recordings.MethodsThe patients were identified in the local database of cardiovascular investigations. Their clinical profile and vital status during the follow-up were obtained from the Swedish Stroke Register and the Swedish general population registry. For comparison, we used an age- and sex-matched population with no known cerebrovascular event and a population with a cerebrovascular event that was not screened.ResultsAF was detected in 7.1% by continuous screening and in 5.1% by intermittent screening (P = 0.3). During follow-up of 32 months, AF in 12-lead ECG was found in 7.0%. In the subgroup with positive screening, 46.3% had AF compared with 6.7% in the subgroup with negative screening (P < 0.0001).ConclusionsThe two screening approaches had a similar yield of arrhythmia, in spite of the group with intermittent monitoring having a more favorable clinical profile. A positive screening was highly predictive of AF in ECG during the follow-up.

Premature Beats Rejection Strategy on Paroxysmal Atrial Fibrillation Detection.

Paroxysmal atrial fibrillation (PAF) may related to the risk of thromboembolism and is the most common cardiac risk factor of cryptogenic stroke (CS). Due to its paroxysmal characteristics, it is usually diagnosed by continuous long-term ECG. Patients with paroxysmal atrial fibrillation usually have premature beats at the same time which is easy to be confused with the rhythm of atrial fibrillation. Therefore, in this article, we designed a screening algorithm for single premature beat, multi premature beats, bigeminy and trigeminy premature beats, according to their rhythm characteristics to reduce false detection caused by premature beats during the PAF detection process. The proposed elimination method was verified on ECG segments with different types of premature beats, and tested on long-term ECG data of PAF patients. ECG segments of different kinds of premature beats were selected from MIT Atrial Fibrillation database (MIT-AFDB), MIT-BIH Arrhythmia database (MIT-AR) and wearable ECG data from the China Physiological Signal Challenge 2021 (CPSC 2021). The proposed method can effectively eliminate single premature beat segments with 99.5% accuracy, and it also can eliminate more than 95% of ECG segments with other types of premature beats. We designed PAF-score as a new index to evaluate the accuracy of detection, and we also calculate the misjudged and missed segments to comprehensively evaluate the PAF detection algorithm. The proposed method get a PAF-score of 0.912 on MIT-AFDB. The proposed method also has the potential to implant low computing power wearable devices for real-time analysis.

Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model

Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model

Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model

Detection of Paroxysmal Atrial Fibrillation from Dynamic ECG Recordings Based on a Deep Learning Model