A new deep learning algorithm of 12-lead electrocardiogram for identifying atrial fibrillation during sinus rhythm.
Ontology highlight
ABSTRACT:
SUBMITTER: Baek YS
PROVIDER: S-EPMC8211689 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:BackgroundRecent 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.MethodsWe 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).ResultsThe 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.ConclusionsThe 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.
| S-EPMC11317324 | biostudies-literature
Project description:AimsThis 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 resultsWe 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.ConclusionOur 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.
| S-EPMC9707938 | biostudies-literature
Project description:BackgroundThis study aimed to increase the knowledge on how to enhance the performance of artificial intelligence (AI)-enabled electrocardiography (ECG) to detect atrial fibrillation (AF) on sinus rhythm ECG (SR-ECG).MethodsIt is a retrospective analysis of a single-center, prospective cohort study (Shinken Database). We developed AI-enabled ECG using SR-ECG to predict AF with a convolutional neural network (CNN). Among new patients in our hospital (n = 19,170), 276 AF label (having ECG on AF [AF-ECG] in the ECG database) and 1896 SR label with following three conditions were identified in the derivation dataset: (1) without structural heart disease, (2) in AF label, SR-ECG was taken within 31 days from AF-ECG, and (3) in SR label, follow-up ≥ 1,095 days. Three patterns of AF label were analyzed by timing of SR-ECG to AF-ECG (before/after/before-or-after, CNN algorithm 1 to 3). The outcome measurement was area under the curve (AUC), sensitivity, specificity, accuracy, and F1 score. As an extra-testing dataset, the performance of AI-enabled ECG was tested in patients with structural heart disease.ResultsThe AUC of AI-enabled ECG with CNN algorithm 1, 2, and 3 in the derivation dataset was 0.83, 0.88, and 0.86, respectively; when tested in patients with structural heart disease, 0.75, 0.81, and 0.78, respectively.ConclusionWe confirmed high performance of AI-enabled ECG to detect AF on SR-ECG in patients without structural heart disease. The performance enhanced especially when SR-ECG after index AF-ECG was included in the algorithm, which was consistent in patients with structural heart disease.
| S-EPMC8760502 | biostudies-literature
Project description:BackgroundArtificial intelligence (AI) models applied to 12-lead ECG waveforms can predict atrial fibrillation (AF), a heritable and morbid arrhythmia. However, the factors forming the basis of risk predictions from AI models are usually not well understood. We hypothesized that there might be a genetic basis for an AI algorithm for predicting the 5-year risk of new-onset AF using 12-lead ECGs (ECG-AI)-based risk estimates.MethodsWe applied a validated ECG-AI model for predicting incident AF to ECGs from 39 986 UK Biobank participants without AF. We then performed a genome-wide association study (GWAS) of the predicted AF risk and compared it with an AF GWAS and a GWAS of risk estimates from a clinical variable model.ResultsIn the ECG-AI GWAS, we identified 3 signals (P<5×10-8) at established AF susceptibility loci marked by the sarcomeric gene TTN and sodium channel genes SCN5A and SCN10A. We also identified 2 novel loci near the genes VGLL2 and EXT1. In contrast, the clinical variable model prediction GWAS indicated a different genetic profile. In genetic correlation analysis, the prediction from the ECG-AI model was estimated to have a higher correlation with AF than that from the clinical variable model.ConclusionsPredicted AF risk from an ECG-AI model is influenced by genetic variation implicating sarcomeric, ion channel and body height pathways. ECG-AI models may identify individuals at risk for disease via specific biological pathways.
| S-EPMC10524395 | biostudies-literature
Project description:This SuperSeries is composed of the SubSeries listed below.
2023-04-30 | GSE226284 | GEO
Project description:GSE2240 contains two different experimental subsets: 1) Comparison of atrial and ventricular gene expression (atrial tissue of patients with sinus rhythm vs. human left ventricular non-failing myocardium) The purpose of our investigation was to identify the transcriptional basis for ultrastructural and functional specialization of human atria and ventricles. Using exploratory microarray analysis (Affymetrix U133A+B), we detected 11,740 transcripts expressed in human heart, representing the most comprehensive report of the human myocardial transcriptome to date. Variation in gene expression between atria and ventricles accounted for the largest differences in this data set, as 3.300 and 2.974 transcripts showed higher expression in atria and ventricles, respectively. Functional classification based on Gene Ontology identified chamber-specific patterns of gene expression and provided molecular insights into the regional specialization of cardiomyocytes, correlating important functional pathways to transcriptional activity: Ventricular myocytes preferentially express genes satisfying contractile and energetic requirements, while atrial myocytes exhibit specific transcriptional activities related to neurohumoral function. In addition, several pro-fibrotic and apoptotic pathways were concentrated in atrial myocardium, substantiating the higher susceptibility of atria to programmed cell death and extracellular matrix remodelling observed in human and experimental animal models of heart failure. Differences in transcriptional profiles of atrial and ventricular myocardium thus provide molecular insights into myocardial cell diversity and distinct region-specific adaptations to physiological and pathophysiological conditions (Barth AS et al., Eur J Physiol, 2005). 2) Comparison of atrial gene expression in patients with permanent atrial fibrillation and sinus rhythm. Atrial fibrillation is associated with increased expression of ventricular myosin isoforms in atrial myocardium, regarded as part of a dedifferentiation process. Whether re-expression of ventricular isoforms in atrial fibrillation is restricted to transcripts encoding for contractile proteins is unknown. Therefore, this study compares atrial mRNA expression in patients with permanent atrial fibrillation to atrial mRNA expression of patients with sinus rhythm as well as to ventricular gene expression using Affymetrix U133 arrays. In atrial myocardium, we identified 1.434 genes deregulated in atrial fibrillation, the majority of which, including key elements of calcium-dependent signaling pathways, displayed down-regulation. Functional classification based on Gene Ontology provided the specific gene sets of the interdependent processes of structural, contractile and electrophysiological remodeling. In addition, we demonstrate for the first time a prominent up-regulation of transcripts involved in metabolic activities, suggesting an adaptive response to an increased metabolic demand in fibrillating atrial myocardium. Ventricular-predominant genes were five times more likely to be up-regulated in atrial fibrillation (174 genes up-regulated, 35 genes down-regulated), while atrial-specific transcripts were predominantly down-regulated (56 genes up-regulated, 564 genes down-regulated). Overall, in atrial myocardium, functional classes of genes characteristic of ventricular myocardium were found to be up-regulated (e.g. metabolic processes) while functional classes predominantly expressed in atrial myocardium were down-regulated in atrial fibrillation (e.g. signal transduction and cell communication). Therefore, dedifferentiation with adoption of a ventricular-like signature is a general feature of the fibrillating atrium, uncovering the transcriptional response pattern in pmAF (Barth AS et al., Circ Res, 2005). Keywords = human myocardium Keywords = atrial fibrillation Keywords = sinus rhythm Keywords = left ventricular gene expression Keywords: other
2005-05-13 | GSE2240 | GEO
Project description:Understanding atrial fibrillation (AF) requires integrated understanding of ionic currents and Ca2+ transport in remodeled human atrium, but appropriate models are limited.To study AF, we developed a new human atrial action potential (AP) model, derived from atrial experimental results and our human ventricular myocyte model.Atria versus ventricles have lower I(K1), resulting in more depolarized resting membrane potential (?7 mV). We used higher I(to,fast) density in atrium, removed I(to,slow), and included an atrial-specific I(Kur). I(NCX) and I(NaK) densities were reduced in atrial versus ventricular myocytes according to experimental results. SERCA function was altered to reproduce human atrial myocyte Ca2+ transients. To simulate chronic AF, we reduced I(CaL), I(to), I(Kur) and SERCA, and increased I(K1),I(Ks) and I(NCX). We also investigated the link between Kv1.5 channelopathy, [Ca2+]i, and AF. The sinus rhythm model showed a typical human atrial AP morphology. Consistent with experiments, the model showed shorter APs and reduced AP duration shortening at increasing pacing frequencies in AF or when I(CaL) was partially blocked, suggesting a crucial role of Ca2+ and Na+ in this effect. This also explained blunted Ca2+ transient and rate-adaptation of [Ca2+]i and [Na+]i in chronic AF. Moreover, increasing [Na+]i and altered I(NaK) and I(NCX) causes rate-dependent atrial AP shortening. Blocking I(Kur) to mimic Kv1.5 loss-of-function increased [Ca2+]i and caused early afterdepolarizations under adrenergic stress, as observed experimentally.Our study provides a novel tool and insights into ionic bases of atrioventricular AP differences, and shows how Na+ and Ca2+ homeostases critically mediate abnormal repolarization in AF.
| S-EPMC3208665 | biostudies-literature
Project description:BackgroundDespite benefits of oral anticoagulation (OAC), many individuals with diagnosed atrial fibrillation (AF) do not receive OAC.ObjectiveThe purpose of this study was to assess whether cardiac rhythm assessment for AF impacted use of OAC in patients with previously diagnosed AF.MethodsVITAL-AF was a cluster randomized controlled trial conducted in 16 primary care practices assessing the efficacy of AF rhythm assessment with single-lead electrocardiogram in routine care. Patients 65 years and older were offered rhythm assessment at visits. In this secondary analysis, we evaluated rhythm assessment uptake and compared initiation and discontinuation of OAC in patients with previously diagnosed AF from intervention and control arms over 1 year.ResultsThe study included 4593 patients with previously diagnosed AF (2250 intervention; 2343 control). In the intervention arm, 2022 (89.9%) completed rhythm assessment (median 2 visits with rhythm assessment) and 40.1% had ≥1 "Possible AF" result. Initiation of OAC was similar in the intervention (17.7%) and control (19.1%) arms but was influenced by the rhythm assessment result: higher with a "Possible AF" (26.1%; adjusted odds ratio [aOR] 1.62; 95% confidence interval [CI] 1.04-2.51), and lower with a "Normal" result (9.9%; aOR 0.45; 95% CI 0.29-0.71) compared to control. OAC discontinuation was similar in the intervention (6.3%) and control (7.2%) arms, with lower discontinuation with a "Possible AF" result (3.8%; aOR 0.51; 95% CI 0.32-0.81).ConclusionsIncluding patients with previously diagnosed AF in a point-of-care rhythm assessment strategy did not increase overall OAC use compared to the control arm. However, the rhythm assessment result influenced both initiation and discontinuation of OAC.
| S-EPMC10461197 | biostudies-literature
Project description:Classification of atrial fibrillation (AF) is currently based on clinical characteristics. However, classifying AF using an objective electrophysiological parameter would be more desirable. The aim of this study was to quantify parameters of atrial conduction during sinus rhythm (SR) using an intra-operative high-resolution epicardial mapping approach and to relate these parameters to clinical classifications of AF. Patients were divided according to the standard clinical classification and spontaneous termination of AF episodes. The HATCH score, a score predictive of AF progression, was calculated, and surface ECGs were evaluated for signs of interatrial block. Conduction disorders mainly differed at Bachmann's bundle (BB). Activation time (AT) at BB was longer in persistent AF patients (AT-BB: 75 (53-92) ms vs. 55 (40-76) ms, p = 0.017), patients without spontaneous termination of AF episodes (AT-BB: 53.5 (39.6-75.8) ms vs. 72.0 (49.6-80.8) ms, p = 0.009) and in patients with a P-wave duration ≥ 120 ms (64.3 (52.3-93.0) ms vs. 50.5 (39.6-56.6) ms, p = 0.014). HATCH scores also correlated positively to AT-BB (rho 0.326, p = 0.029). However, discriminatory values of electrophysiological parameters, as calculated using ROC-curves, were limited. These results may reflect shortcomings of clinical classifications and further research is needed to establish an objective substrate-based classification of AF.
| S-EPMC8269325 | biostudies-literature
Project description:Electrocardiogram (ECG) is a widely used reliable, non-invasive approach for cardiovascular disease diagnosis. With the rapid growth of ECG examinations and the insufficiency of cardiologists, accurate and automatic diagnosis of ECG signals has become a hot research topic. In this paper, we developed a deep neural network for automatic classification of cardiac arrhythmias from 12-lead ECG recordings. Experiments on a public 12-lead ECG dataset showed the effectiveness of our method. The proposed model achieved an average F1 score of 0.813. The deep model showed superior performance than 4 machine learning methods learned from extracted expert features. Besides, the deep models trained on single-lead ECGs produce lower performance than using all 12 leads simultaneously. The best-performing leads are lead I, aVR, and V5 among 12 leads. Finally, we employed the SHapley Additive exPlanations method to interpret the model's behavior at both the patient level and population level.
| S-EPMC8082080 | biostudies-literature