RawECGNet: Deep Learning Generalization for Atrial Fibrillation Detection From the Raw ECG.

INTRODUCTION: Deep learning models for detecting episodes of atrial fibrillation (AF) using rhythm information in long-term ambulatory ECG recordings have shown high performance. However, the rhythm-based approach does not take advantage of the morphological information conveyed by the different ECG waveforms, particularly the f-waves. As a result, the performance of such models may be inherently limited. METHODS: To address this limitation, we have developed a deep learning model, named RawECGNet, to detect episodes of AF and atrial flutter (AFl) using the raw, single-lead ECG. We compare the generalization performance of RawECGNet on two external data sets that account for distribution shifts in geography, ethnicity, and lead position. RawECGNet is further benchmarked against a state-of-the-art deep learning model, named ArNet2, which utilizes rhythm information as input. RESULTS: Using RawECGNet, the results for the different leads in the external test sets in terms of the F1 score were 0.91-0.94 in RBDB and 0.93 in SHDB, compared to 0.89-0.91 in RBDB and 0.91 in SHDB for ArNet2. The results highlight RawECGNet as a high-performance, generalizable algorithm for detection of AF and AFl episodes, exploiting information on both rhythm and morphology.

A Review on Atrial Fibrillation Detection From Ambulatory ECG.

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

Generalizable and robust deep learning algorithm for atrial fibrillation diagnosis across geography, ages and sexes.

To drive health innovation that meets the needs of all and democratize healthcare, there is a need to assess the generalization performance of deep learning (DL) algorithms across various distribution shifts to ensure that these algorithms are robust. This retrospective study is, to the best of our knowledge, an original attempt to develop and assess the generalization performance of a DL model for AF events detection from long term beat-to-beat intervals across geography, ages and sexes. The new recurrent DL model, denoted ArNet2, is developed on a large retrospective dataset of 2,147 patients totaling 51,386 h obtained from continuous electrocardiogram (ECG). The model's generalization is evaluated on manually annotated test sets from four centers (USA, Israel, Japan and China) totaling 402 patients. The model is further validated on a retrospective dataset of 1,825 consecutives Holter recordings from Israel. The model outperforms benchmark state-of-the-art models and generalized well across geography, ages and sexes. For the task of event detection ArNet2 performance was higher for female than male, higher for young adults (less than 61 years old) than other age groups and across geography. Finally, ArNet2 shows better performance for the test sets from the USA and China. The main finding explaining these variations is an impairment in performance in groups with a higher prevalence of atrial flutter (AFL). Our findings on the relative performance of ArNet2 across groups may have clinical implications on the choice of the preferred AF examination method to use relative to the group of interest.

Effect of temporal resolution on the detection of cardiac arrhythmias using HRV features and machine learning.

Objective.Arrhythmia is an abnormal cardiac rhythm that affects the pattern and rate of the heartbeat. Wearable devices with the functionality to measure and store heart rate (HR) data are growing in popularity and enable diagnosing and monitoring arrhythmia on a large scale. The typical sampling resolution of HR data available from non-medical grade wearable devices varies from seconds to several minutes depending on the device and its settings. However, the impact of sampling resolution on the performance and quality of arrhythmia detection has not yet been quantified.Approach.In this study, we investigated the detection and classification of three arrhythmias, namely atrial fibrillation, bradycardia, tachycardia, from down-sampled HR data with various temporal resolution (5-, 15-, 30- and 60 s averages) in 1 h segments extracted from an annotated Holter ECG database acquired at the University of Virginia Heart Station. For the classification task, a total of 15 common heart rate variability (HRV) features were engineered based on the HR time series of each patient. Three different types of machine learning classifiers were evaluated, namely logistic regression, support vector machine and random forest.Main results.A decrease in temporal resolution drastically impacted the detection of atrial fibrillation but did not substantially affect the detection of bradycardia and tachycardia. A HR resolution up to 15 s average demonstrated reasonable performance with a sensitivity of 0.92 and a specificity of 0.86 for a multiclass random forest classifier.Significance.HRV features extracted from low resolution long HR recordings have the potential to increase the early detection of arrhythmias in undiagnosed individuals.

Atrial fibrillation risk prediction from the 12-lead electrocardiogram using digital biomarkers and deep representation learning.

Aims: This study aims to assess whether information derived from the raw 12-lead electrocardiogram (ECG) combined with clinical information is predictive of atrial fibrillation (AF) development. Methods and results: We use a subset of the Telehealth Network of Minas Gerais (TNMG) database consisting of patients that had repeated 12-lead ECG measurements between 2010 and 2017 that is 1 130 404 recordings from 415 389 unique patients. Median and interquartile of age for the recordings were 58 (46-69) and 38% of the patients were males. Recordings were assigned to train-validation and test sets in an 80:20% split which was stratified by class, age and gender. A random forest classifier was trained to predict, for a given recording, the risk of AF development within 5 years. We use features obtained from different modalities, namely demographics, clinical information, engineered features, and features from deep representation learning. The best model performance on the test set was obtained for the model combining features from all modalities with an area under the receiver operating characteristic curve (AUROC) = 0.909 against the best single modality model which had an AUROC = 0.839. Conclusion: Our study has important clinical implications for AF management. It is the first study integrating feature engineering, deep learning, and Electronic medical record system (EMR) metadata to create a risk prediction tool for the management of patients at risk of AF. The best model that includes features from all modalities demonstrates that human knowledge in electrophysiology combined with deep learning outperforms any single modality approach. The high performance obtained suggest that structural changes in the 12-lead ECG are associated with existing or impending AF.

Remote Atrial Fibrillation Burden Estimation Using Deep Recurrent Neural Network.

OBJECTIVE: The atrial fibrillation burden (AFB) is defined as the percentage of time spent in atrial fibrillation (AF) over a long enough monitoring period. Recent research has suggested the added prognostic value of using the AFB compared to a binary diagnosis. We evaluate, for the first time, the ability to estimate the AFB over long-term continuous recordings, using a deep recurrent neutral network (DRNN) approach. METHODS: The models were developed and evaluated on a large database of p = 2,891 patients, totaling t = 68,800 hours of continuous electrocardiography (ECG) recordings from the University of Virginia. Specifically, 24h beat-to-beat time series were obtained from a single portable ECG channel. The network, denoted ArNet, was benchmarked against a gradient boosting (XGB) model, trained on 21 features including the coefficient of sample entropy (CosEn) and AFEvidence that is derived from the number of irregular points revealed by the Lorenz plot. The generalizations of ArNet and XGB were also evaluated on the independent PhysioNet LTAF test database. RESULTS: the absolute AF burden estimation error [Formula: see text], median and interquartile, on the test set, was 1.2 (0.1-6.7) for ArNet and 2.8 (0.9-11.7) for XGB for AF individuals. Generalization results on LTAF were consistent with [Formula: see text] of 2.7 (1.1-14.7) for ArNet and 3.6 (1.0-16.7) for XGB. CONCLUSION: This research demonstrates the feasibility of AFB estimation from 24h beat-to-beat interval time series utilizing DRNNs. SIGNIFICANCE: The novel data-driven approach enables robust remote diagnosis and phenotyping of AF.