Real-time Atrial Fibrillation Research Articles

Efficacy of wearable cardiac monitoring devices versus traditional methods in detecting atrial fibrillation: a systematic review and meta-analysis

Introduction: Atrial fibrillation (AF) is a prevalent arrhythmia with significant health and economic impacts. Traditional detection methods like 12-lead ECGs and Holter monitors are effective but limited by cost and patient compliance. Wearable devices, such as smartwatches and patches, offer a promising alternative for real-time AF detection.Objective: This systematic review aims to evaluate the efficacy of wearable cardiac monitoring devices compared to traditional methods in detecting AF.Methods: A comprehensive literature search identified studies comparing wearable devices to traditional methods for AF detection. Data on sensitivity, specificity, and usability were extracted and analyzed. A pooled analysis using both fixed-effect and random-effects models assessed overall sensitivity and specificity.Results: This systematic review analyzed data from 15 studies comparing wearable devices to traditional methods for AF detection. Wearable devices, including smartwatches, patch-type ECGs, and PPG-based technologies, showed high sensitivity and specificity, with the fixed-effect model estimating overall sensitivity at 91.59% and specificity at 92.13%. The random-effects model provided slightly higher sensitivity (94.03%) and specificity (95.96%). Smartwatches like the Apple Watch with KardiaBand demonstrated up to 97.5% sensitivity, comparable to insertable cardiac monitors (ICMs). Patch-type ECGs, such as MobiCARE-MC100 and Zio XT, matched Holter monitors in accuracy, with extended monitoring enhancing AF detection. PPG-based technologies, exemplified by the WATCH AF trial, showed 93.7% sensitivity and 98.2% specificity. Despite high accuracy, significant heterogeneity among studies highlighted the need for standardized protocols.Conclusion: Wearable devices show high sensitivity and specificity for AF detection, comparable to traditional methods. However, substantial heterogeneity indicates the need for standardized protocols and further research to optimize these technologies for clinical use.

Edge AI Model Deployed for Real-Time Detection of Atrial Fibrillation Risk during Sinus Rhythm.

Objectives: The study aimed to develop a deep learning-based edge AI model deployed on electrocardiograph (ECG) devices for the real-time detection of atrial fibrillation (AF) risk during sinus rhythm (SR) using standard 10 s, 12-lead electrocardiograms (ECGs). Methods: A novel approach was used to convert standard 12-lead ECGs into binary images for model input, and a lightweight convolutional neural network (CNN)-based model was trained using data collected by the Japan Agency for Medical and Research Development (AMED) between 2019 and 2022. Patients over 40 years old with digital, SR ECGs were retrospectively enrolled and divided into AF and non-AF groups. The data labeling was supervised by cardiologists. The dataset was randomly allocated into training, validation, and internal testing datasets. External testing was conducted on data collected from other hospitals. Results: The best-trained model achieved an AUC of 0.82 and 0.80, sensitivity of 79.5% and 72.3%, specificity of 77.8% and 77.7%, precision of 78.2% and 76.4%, and overall accuracy of 78.6% and 75.0% in the internal and external testing datasets, respectively. The deployed model and app package utilized 2.5 MB and 40 MB of the available ROM and RAM capacity on the edge ECG device, correspondingly. The processing time for AF risk detection was approximately 2 s. Conclusions: The model maintains comparable performance and improves its suitability for deployment on resource-constrained ECG devices, thereby expanding its potential impact to a wide range of healthcare settings. Its successful deployment enables real-time AF risk detection during SR, allowing for timely intervention to prevent AF-related serious consequences like stroke and premature death.

Optimization of Using Multiple Machine Learning Approaches in Atrial Fibrillation Detection Based on a Large-Scale Data Set of 12-Lead Electrocardiograms: Cross-Sectional Study.

Atrial fibrillation (AF) represents a hazardous cardiac arrhythmia that significantly elevates the risk of stroke and heart failure. Despite its severity, its diagnosis largely relies on the proficiency of health care professionals. At present, the real-time identification of paroxysmal AF is hindered by the lack of automated techniques. Consequently, a highly effective machine learning algorithm specifically designed for AF detection could offer substantial clinical benefits. We hypothesized that machine learning algorithms have the potential to identify and extract features of AF with a high degree of accuracy, given the intricate and distinctive patterns present in electrocardiogram (ECG) recordings of AF. This study aims to develop a clinically valuable machine learning algorithm that can accurately detect AF and compare different leads' performances of AF detection. We used 12-lead ECG recordings sourced from the 2020 PhysioNet Challenge data sets. The Welch method was used to extract power spectral features of the 12-lead ECGs within a frequency range of 0.083 to 24.92 Hz. Subsequently, various machine learning techniques were evaluated and optimized to classify sinus rhythm (SR) and AF based on these power spectral features. Furthermore, we compared the effects of different frequency subbands and different lead selections on machine learning performances. The light gradient boosting machine (LightGBM) was found to be the most effective in classifying AF and SR, achieving an average F1-score of 0.988 across all ECG leads. Among the frequency subbands, the 0.083 to 4.92 Hz range yielded the highest F1-score of 0.985. In interlead comparisons, aVR had the highest performance (F1=0.993), with minimal differences observed between leads. In conclusion, this study successfully used machine learning methodologies, particularly the LightGBM model, to differentiate SR and AF based on power spectral features derived from 12-lead ECGs. The performance marked by an average F1-score of 0.988 and minimal interlead variation underscores the potential of machine learning algorithms to bolster real-time AF detection. This advancement could significantly improve patient care in intensive care units as well as facilitate remote monitoring through wearable devices, ultimately enhancing clinical outcomes.

A Data Quality Measurement Framework Using Distribution-Based Modeling and Simulation in Real-Time Telemedicine Systems

In modern telemedicine systems, the data path can be exceedingly complex, with data passing through a number of phases and processes before reaching its ultimate state. It is extremely difficult to predict the effects of lacking data or improperly processed data on the final outcome. In real-time systems, and particularly in the field of telemedicine, it is crucial to rapidly identify and rectify issues in order to prevent the loss of large amounts of data and the degradation of data quality. A basic simulation is insufficient for a comprehensive examination of the system; instead, modeling approaches are required. However, a minor system’s state space can be immense. We present a methodology and a hybrid framework that incorporate simulation, emulation, and modeling in order to evaluate the state space and potential consequences of a sufficiently large system in a more targeted and condensed manner. In this paper, we demonstrate the structure and operation of our framework using an actively researched telemedicine use case, as well as how data quality can fluctuate and new anomalies can emerge if data is corrupted during an intermediate phase. According to our real-time Atrial Fibrillation (AF) and classification use case, data loss can be as high as 15%.

Generalizable calibrated machine learning models for real-time atrial fibrillation risk prediction in ICU patients

BackgroundAtrial Fibrillation (AF) is the most common arrhythmia in the intensive care unit (ICU) and is associated with increased morbidity and mortality. Identification of patients at risk for AF is not routinely performed as AF prediction models are almost solely developed for the general population or for particular ICU populations. However, early AF risk identification could help to take targeted preemptive actions and possibly reduce morbidity and mortality. Predictive models need to be validated across hospitals with different standards of care and convey their predictions in a clinically useful manner. Therefore, we designed AF risk models for ICU patients using uncertainty quantification to provide a risk score and evaluated them on multiple ICU datasets. MethodsThree CatBoost models, utilizing feature windows comprising data 1.5-13.5, 6-18, or 12-24 hours before AF occurrence, were built using 2-repeat-10-fold cross-validation on AmsterdamUMCdb, the first freely available European ICU database. Furthermore, AF Patients were matched with no-AF patients for training. Transferability was validated using a direct and a recalibration evaluation on two independent external datasets, MIMIC-IV and GUH. The calibration of the predicted probability, used as an AF risk score, was measured using the Expected Calibration Error (ECE) and the presented Expected Signed Calibration Error (ESCE). Additionally, all models were evaluated across time during the ICU stay. ResultsThe model performance reached Areas Under the Curve (AUCs) of 0.81 at internal validation. Direct external validation showed partial generalizability with AUCs reaching 0.77. However, recalibration resulted in performances matching or exceeding that of the internal validation. All models furthermore showed calibration capabilities demonstrating adequate risk prediction competence. ConclusionUltimately, recalibrating models reduces the challenge of generalization to unseen datasets. Moreover, utilizing the patient-matching methodology together with the assessment of uncertainty calibration can serve as a step toward the development of clinical AF prediction models.

Detecting Atrial Fibrillation in Real Time Based on PPG via Two CNNs for Quality Assessment and Detection

Real-time detection of atrial fibrillation (AFib) is made possible by the quality assessment via a 1-D convolutional neural network (1D-CNN) in a processor of a photoplethysmography (PPG) sensor patch and a 2-D convolutional neural network (2D-CNN) for AFib detection in cloud. The 1D-CNN is able to filter out the unqualified PPG that is contaminated by motion artifacts and/or ambient light interference. The remaining qualified PPG is then inputted to another built 2D-CNN for detecting AFib. This 1D-CNN consists of four layers of convolutions and max pooling, one long short-term memory (LSTM), and an output dense layer. The 2D-CNN is pretrained based on the electrocardiography (ECG) data from multiparameter intelligent monitoring in intensive care (MIMIC) III database, for which the RR-intervals (RRIs) of ECG data are first extracted in Poincaré images and then regarded as input features to the model for training. This 2D-CNN has also four layers of convolutions and max pooling and four output dense layers. The pretrained model is next fine-tuned based on peak-to-peak intervals (PPIs) of PPG measured from wearable devices as input features for detecting AFib effectively. The quality-assessment 1D-CNN model is implemented in the wearable device to transmit only qualified data to the 2D-CNN model in cloud for AFib detection, achieving power efficiency. Both models are trained by the Adam optimizer. To validate the models, the PPIs of PPG were collected to evaluate the performance of the established models in real time. Experimental results show that the fine-tuned 2D-CNN for AFib detection achieves the accuracy, sensitivity, and specificity were 98.08%, 96.82%, and 98.86%, respectively, the most favorable as opposed to other reported works based on PPG. The models are able to not only assist clinicians in AFib detection but also provide a mechanism to detect AFib via wearable devices in real time.

An investigation of the contextual distribution of false positives in a deep learning-based atrial fibrillation detection algorithm

Goal:To investigate the contextual and temporal distribution of false positives (FPs) in a state-of-the-art deep learning (DL)-based atrial fibrillation (AF) detection algorithm when applied to an electrocardiogram (ECG) dataset collected under free-living ambulatory conditions. We hypothesize that under such conditions, the FPs detected by a DL model might have some correlations with the patient’s ambulatory contexts. Method:First, a DL model is trained and evaluated on three public arrhythmia datasets from PhysioNet. It is ensured that the model has state-of-the-art performance on these public datasets. Thereafter, the same model is applied to a 215-days long contextualized single-channel ECG dataset collected under free-living ambulatory conditions. Through a manual examination of the model’s output, ground truth is obtained and the correlations between the patient’s ambulatory contexts and the true/false positive rate are analyzed. Results:Nearly 62% of the segments marked as AF by the model were ≤50 seconds in length, and 99.9% of them were FPs. Among these non-trivial short segments of FPs, almost 78% were mainly associated with three specific contextual events; change in activity, change in body position (especially during the night), and sudden movement acceleration. Moreover, the number of FPs detected by the DL model are higher in female than in male participants. Finally, true positive (TP) AF segments are found more in the morning and late evening. Significance:These findings may have significant implications for the current use and future design of DL models for AF detection, and help understand the role of context information in reducing the FP rate in real-time AF detection under free-living conditions.

Abstract 15553: The Long-term Outcome Beyond Pulmonary Vein Isolation of Ablation Guided by the Online and Real-time Atrial Fibrillation Imaging System: Extra Mapping Project

Introduction: Although modulation of atrial fibrillation (AF) drivers and/or substrates has been proposed as one of the effective ablation strategies for non-paroxysmal AF (Non-PAF), previous meta-analyses showed that ablation, targeting complex fractionated atrial electrogram (CFAE) indirectly-reflecting Non-PAF drivers, had no additional benefit for post-pulmonary vein isolation (PVI) Non-PAF. As an alternative ablation strategy for Non-PAF, rotor ablation has been proposed as one of the potentiated ablation strategies for Non-PAF. However, the optimal ablation strategy is still unclear because reliable method detecting AF drivers remain unsettled in clinical practice. Hypothesis: Because rotors are known as key mechanisms for Non-PAF, we might open the possibility of Non-PAF control by the real-time visualization of wave dynamics during AF ablation. Methods: Consecutive 140 Non-PAF patients were enrolled in this study. The clinically-available online and real-time AF imaging system with high-spatiotemporal density (ExTRa Mapping TM ) developed by our group was applied in case Non-PAF was remained after PVI. Then, we detected and ablated non-passively-activated areas where rotational activations in the form of meandering rotors and/or multiple wavelets assumed to contain Non-PAF drivers were frequently observed (figure, top). The recurrence rate of Non-PAF or atrial tachycardia (AT) after the ablation was compared to that in patients underwent PVI-alone at our hospital. Results: The propensity scores selected each 34 people from ExTRa-strategy group and PVI-alone group (figure, middle). The 24-month freedom ratio from Non-PAF/AT in the matched-ExTRa-strategy group was higher than the matched-PVI-alone group, which was close to significance (p = 0.056) (figure, bottom). Conclusion: The ExTRa Mapping-guided ablation for PVI-refractory Non-PAF might be superior to PVI-alone.

A Review of Atrial Fibrillation Detection Methods as a Service.

Atrial Fibrillation (AF) is a common heart arrhythmia that often goes undetected, and even if it is detected, managing the condition may be challenging. In this paper, we review how the RR interval and Electrocardiogram (ECG) signals, incorporated into a monitoring system, can be useful to track AF events. Were such an automated system to be implemented, it could be used to help manage AF and thereby reduce patient morbidity and mortality. The main impetus behind the idea of developing a service is that a greater data volume analyzed can lead to better patient outcomes. Based on the literature review, which we present herein, we introduce the methods that can be used to detect AF efficiently and automatically via the RR interval and ECG signals. A cardiovascular disease monitoring service that incorporates one or multiple of these detection methods could extend event observation to all times, and could therefore become useful to establish any AF occurrence. The development of an automated and efficient method that monitors AF in real time would likely become a key component for meeting public health goals regarding the reduction of fatalities caused by the disease. Yet, at present, significant technological and regulatory obstacles remain, which prevent the development of any proposed system. Establishment of the scientific foundation for monitoring is important to provide effective service to patients and healthcare professionals.

Implementation and validation of real-time algorithms for atrial fibrillation detection on a wearable ECG device

BackgroundDue to the growing epidemic of atrial fibrillation (AF), new strategies for AF screening, diagnosis, and monitoring are required. Wearable devices with on-board AF detection algorithms may improve early diagnosis and therapy outcomes. In this work, we implemented optimized algorithms for AF detection on a wearable ECG monitoring device and assessed their performance. MethodsThe signal processing framework was composed of two main modules: 1) a QRS detector based on a finite state machine, and 2) an AF detector based on the Shannon entropy of the symbolic word series obtained from the instantaneous heart rate. The AF detector was optimized off-line by tuning its parameters to reduce the computational burden while preserving detection accuracy. On-board performance was assessed in terms of detection accuracy, memory usage, and computation time. ResultsThe on-board implementation of the QRS detector produced an overall accuracy of 99% on the MIT-BIH Arrhythmia Database, with memory usage = 672 bytes, and computation time ≤90 μs. The on-board implementation of the optimized AF algorithm gave an overall accuracy of 98.1% (versus 98.3% of the original version) on the MIT-BIH AF Database, with increased sensitivity (99.2% versus 98.5%) and decreased specificity (97.3% versus 98.2%), memory usage = 4648 bytes, and computation time ≤ 75 μs (consistent with real-time detection). ConclusionsThis study demonstrated the feasibility of real-time AF detection on a wearable ECG device. It constitutes a promising step towards the development of novel ECG monitoring systems to tackle the growing AF epidemic.

Real-time Atrial Fibrillation Detection Using Artificial Neural Network on a Wearable Electrocardiogram

Providing equal healthcare quality on heart diseases are an issue in developing countries, especially in Indonesia, due to is wide-spread areas. It is founded that the heart diseases occur not only in big cities but also in rural areas, that is caused by unhealthy lifestyle and foods. Heart disease itself is a disease with gradually symptoms changes that can be seen based on the hearts' electrical activity or electrocardiogram signals. Now, wearable medical devices are capable to be worn daily, so that, it can monitor our heart condition and alert if there is an abnormality. An embedded device worn on the chest can be used to perform a real-time data acquisition and processing of the electrocardiogram, that consists of a 1-lead ECG, an ARM processor, a Bluetooth module, an SD card, and rechargeable batteries. Also, by performing a digital filter and Tompkins algorithm, we obtain the P-wave presences and the heart rate variability values (heartbeat, average heartbeat, standard deviation, and root mean square) then by using an artificial neural network with 4 input, 6 hidden, and 1 output layers that has multi-layer perceptrons and backpropagation. We are able to perform a pre-diagnosis of atrial fibrillation, that is one of the common arrhythmias, from 41 recorded training samples (Physionet MIT/BIH AFDB and NSRDB) and 6 healthy subjects as test samples. The neural network has 0.1% error rate and needed 31548 epochs to train itself for classification the heart disease. Based on the results, this prototype can be used as a medical-grade wearable device thatcan help cardiologist in giving an early warning on the user's heart condition, so that it can prevent sudden death due to heart diseases in rural areas.

Screening for atrial fibrillation during influenza vaccinations by primary care nurses using a smartphone electrocardiograph (iECG): A feasibility study.

People with unknown atrial fibrillation (AF), who are often asymptomatic, have a substantially increased risk of stroke. Although recommended in European guidelines, AF screening is not routinely performed. Screening at the time of influenza vaccination presents an ideal opportunity to detect AF in large numbers in a primary care medical setting, with an existing annual recall system for patients aged ≥65 years. Cross-sectional pilot study of handheld smartphone electrocardiogram (iECG) screening to identify unknown AF. General practices in Sydney, Australia, were recruited during the influenza-vaccination period of April-June 2015. Practice nurses screened patients aged ≥65 years with a 30-second iECG, which has a validated algorithm for detecting AF in real time. In order to confirm the accuracy of the algorithm, two research cardiologists reviewed de-identified iECGs. In order to explore barriers and enablers, semi-structured interviews were conducted with selected nurses, practice managers and general practitioners. Five general practices were recruited, and 973/2476 (39%) patients attending influenza vaccination were screened. Screening took an average of 5 minutes (range 1.5-10 minutes); however, abnormal iECGs required additional time. Newly identified AF was found in 8/973 patients (0.8%). The sensitivity of the iECG automated algorithm was 95% (95% confidence interval: 83-99%) and the specificity was 99% (95% confidence interval: 98-100%). Screening by practice nurses was well accepted by practice staff. Key enablers were the confidence and competence of nurses and a 'designated champion' to lead screening at the practice. Barriers were practice specific, and mainly related to staff time and funding. Screening with iECG during influenza vaccination by primary care nurses is feasible and well accepted by practice staff. Addressing barriers is likely to increase uptake.

136-22: Fast and Regular Activities outside the Pulmonary Veins following Circumferential Pulmonary Vein Ablation in AF Patients

Introduction: Atrial Fibrillation (AF) might be sustained by fast and regular activities, while fragmented electrograms might be unrelated to the driving mechanism of AF. This study aimed to analyze the prevalence of these organized activities in patients remaining in AF after circumferential pulmonary vein ablation (CPVA). Methods: In 21 patients with paroxysmal and persistent AF who underwent an ablation procedure and remained in AF after CPVA, a novel 3D mapping software (EnSite™ Velocity™ Research Version, St Jude Medical Inc.) was used retrospectively to analyze AF maps collected before and after CPVA. Conclusions: Although CPVA eliminated organized drivers in the PVs and modified AF substrates elsewhere, the existing and emergent drivers at non-PV area might continue to maintain AF after CPVA in some patients. Real-time AF substrate mapping might be a valuable tool to establish a mechanism-targeted ablation strategy.

A Real-Time Atrial Fibrillation Detection Algorithm Based on the Instantaneous State of Heart Rate.

Atrial fibrillation (AF), the most frequent cause of cardioembolic stroke, is increasing in prevalence as the population ages, and presents with a broad spectrum of symptoms and severity. The early identification of AF is an essential part for preventing the possibility of blood clotting and stroke. In this work, a real-time algorithm is proposed for accurately screening AF episodes in electrocardiograms. This method adopts heart rate sequence, and it involves the application of symbolic dynamics and Shannon entropy. Using novel recursive algorithms, a low-computational complexity can be obtained. Four publicly-accessible sets of clinical data (Long-Term AF, MIT-BIH AF, MIT-BIH Arrhythmia, and MIT-BIH Normal Sinus Rhythm Databases) were used for assessment. The first database was selected as a training set; the receiver operating characteristic (ROC) curve was performed, and the best performance was achieved at the threshold of 0.639: the sensitivity (Se), specificity (Sp), positive predictive value (PPV) and overall accuracy (ACC) were 96.14%, 95.73%, 97.03% and 95.97%, respectively. The other three databases were used for independent testing. Using the obtained decision-making threshold (i.e., 0.639), for the second set, the obtained parameters were 97.37%, 98.44%, 97.89% and 97.99%, respectively; for the third database, these parameters were 97.83%, 87.41%, 47.67% and 88.51%, respectively; the Sp was 99.68% for the fourth set. The latest methods were also employed for comparison. Collectively, results presented in this study indicate that the combination of symbolic dynamics and Shannon entropy yields a potent AF detector, and suggest this method could be of practical use in both clinical and out-of-clinical settings.

선형분석 기반의 심방세동 분류를 위한 불규칙 RR 간격의 최적값 검출

Several algorithms have been developed to detect AFIB(Atrial Fibrillation) which either rely on the linear and frequency analysis. But they are more complex than time time domain algorithm and difficult to get the consistent rule of irregular RR interval rhythm. In this study, we propose algorithm for optimal value detection of irregular RR interval for AFIB classification based on linear analysis. For this purpose, we detected R wave, RR interval, from noise-free ECG signal through the preprocessing process and subtractive operation method. Also, we set scope for segment length and detected optimal value and then classified AFIB in realtime through liniar analysis such as absolute deviation and absolute difference. The performance of proposed algorithm for AFIB classification is evaluated by using MIT-BIH arrhythmia and AFIB database. The optimal value indicate   in AFIB classification.

A Novel Method for Real‐Time Atrial Fibrillation Detection in Electrocardiograms Using Multiple Parameters

Automatic detection of atrial fibrillation (AF) in electrocardiograms (ECGs) is beneficial for AF diagnosis, therapy, and management. In this article, a novel method of AF detection is introduced. Most current methods only utilize the RR interval as a critical parameter to detect AF; thus, these methods commonly confuse AF with other arrhythmias. We used the average number of f waves in a TQ interval as a characteristic parameter in our robust, real-time AF detection method. Three types of clinical ECG data, including ECGs from normal, AF, and non-AF arrhythmia subjects, were downloaded from multiple open access databases to validate the proposed method. The experimental results suggested that the method could distinguish between AF and normal ECGs with accuracy, sensitivity, and positive predictive values (PPVs) of 93.67%, 94.13%, and 98.69%, respectively. These values are comparable to those of related methods. The method was also able to distinguish between AF and non-AF arrhythmias and had performance indexes (accuracy 94.62%, sensitivity 94.13%, and PPVs 97.67%) that were considerably better than those of other methods. Our proposed method has prospects as a practical tool enabling clinical diagnosis, treatment, and monitoring of AF.

Improvements in atrial fibrillation detection for real-time monitoring

Electrocardiographic (ECG) monitoring plays an important role in the management of patients with atrial fibrillation (AF). Automated real-time AF detection algorithm is an integral part of ECG monitoring during AF therapy. Before and after antiarrhythmic drug therapy and surgical procedures require ECG monitoring to ensure the success of AF therapy. This article reports our experience in developing a real-time AF monitoring algorithm and techniques to eliminate false-positive AF alarms. We start by designing an algorithm based on R-R intervals. This algorithm uses a Markov modeling approach to calculate an R-R Markov score. This score reflects the relative likelihood of observing a sequence of R-R intervals in AF episodes versus making the same observation outside AF episodes. Enhancement of the AF algorithm is achieved by adding atrial activity analysis. P-R interval variability and a P wave morphology similarity measure are used in addition to R-R Markov score in classification. A hysteresis counter is applied to eliminate short AF segments to reduce false AF alarms for better suitability in a monitoring environment. A large ambulatory Holter database (n = 633) was used for algorithm development and the publicly available MIT-BIH AF database (n = 23) was used for algorithm validation. This validation database allowed us to compare our algorithm performance with previously published algorithms. Although R-R irregularity is the main characteristic and strongest discriminator of AF rhythm, by adding atrial activity analysis and techniques to eliminate very short AF episodes, we have achieved 92% sensitivity and 97% positive predictive value in detecting AF episodes, and 93% sensitivity and 98% positive predictive value in quantifying AF segment duration.