Dataset Information

Identifying patients with atrial fibrillation during sinus rhythm on ECG: Significance of the labeling in the artificial intelligence algorithm.

ABSTRACT:

Background

This 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).

Methods

It 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.

Results

The 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.

Conclusion

We 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.

SUBMITTER: Suzuki S

PROVIDER: S-EPMC8760502 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

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

Project description:Slowly inactivating Na+ channels conducting "late" Na+ current (INa,late) contribute to ventricular arrhythmogenesis under pathological conditions. INa,late was also reported to play a role in chronic atrial fibrillation (AF). The objective of this study was to investigate INa,late in human right atrial cardiomyocytes as a putative drug target for treatment of AF. To activate Na+ channels, cardiomyocytes from transgenic mice which exhibit INa,late (?KPQ), and right atrial cardiomyocytes from patients in sinus rhythm (SR) and AF were voltage clamped at room temperature by 250-ms long test pulses to -30 mV from a holding potential of -80 mV with a 100-ms pre-pulse to -110 mV (protocol I). INa,late at -30 mV was not discernible as deviation from the extrapolated straight line IV-curve between -110 mV and -80 mV in human atrial cells. Therefore, tetrodotoxin (TTX, 10 ?M) was used to define persistent inward current after 250 ms at -30 mV as INa,late. TTX-sensitive current was 0.27±0.06 pA/pF in ventricular cardiomyocytes from ?KPQ mice, and amounted to 0.04±0.01 pA/pF and 0.09±0.02 pA/pF in SR and AF human atrial cardiomyocytes, respectively. With protocol II (holding potential -120 mV, pre-pulse to -80 mV) TTX-sensitive INa,late was always larger than with protocol I. Ranolazine (30 ?M) reduced INa,late by 0.02±0.02 pA/pF in SR and 0.09±0.02 pA/pF in AF cells. At physiological temperature (37°C), however, INa,late became insignificant. Plateau phase and upstroke velocity of action potentials (APs) recorded with sharp microelectrodes in intact human trabeculae were more sensitive to ranolazine in AF than in SR preparations. Sodium channel subunits expression measured with qPCR was high for SCN5A with no difference between SR and AF. Expression of SCN8A and SCN10A was low in general, and lower in AF than in SR. In conclusion, We confirm for the first time a TTX-sensitive current (INa,late) in right atrial cardiomyocytes from SR and AF patients at room temperature, but not at physiological temperature. While our study provides evidence for the presence of INa,late in human atria, the potential of such current as a target for the treatment of AF remains to be demonstrated.

Project description:AimsHuman atrial electrophysiology exhibits high inter-subject variability in both sinus rhythm (SR) and chronic atrial fibrillation (cAF) patients. Variability is however rarely investigated in experimental and theoretical electrophysiological studies, thus hampering the understanding of its underlying causes but also its implications in explaining differences in the response to disease and treatment. In our study, we aim at investigating the ability of populations of human atrial cell models to capture the inter-subject variability in action potential (AP) recorded in 363 patients both under SR and cAF conditions.Methods and resultsHuman AP recordings in atrial trabeculae (n = 469) from SR and cAF patients were used to calibrate populations of computational SR and cAF atrial AP models. Three populations of over 2000 sampled models were generated, based on three different human atrial AP models. Experimental calibration selected populations of AP models yielding AP with morphology and duration in range with experimental recordings. Populations using the three original models can mimic variability in experimental AP in both SR and cAF, with median conductance values in SR for most ionic currents deviating less than 30% from their original peak values. All cAF populations show similar variations in G(K1), G(Kur) and G(to), consistent with AF-related remodeling as reported in experiments. In all SR and cAF model populations, inter-subject variability in I(K1) and I(NaK) underlies variability in APD90, variability in I(Kur), I(CaL) and I(NaK) modulates variability in APD50 and combined variability in Ito and I(Kur) determines variability in APD20. The large variability in human atrial AP triangulation is mostly determined by I(K1) and either I(NaK) or I(NaCa) depending on the model.ConclusionExperimentally-calibrated human atrial AP models populations mimic AP variability in SR and cAF patient recordings, and identify potential ionic determinants of inter-subject variability in human atrial AP duration and morphology in SR versus cAF.