Development and Validation of a Machine Learning-Based Radiomics Model on Cardiac Computed Tomography of Epicardial Adipose Tissue in Predicting Characteristics and Recurrence of Atrial Fibrillation

Abstract

PurposeThis study aimed to evaluate the feasibility of differentiating the atrial fibrillation (AF) subtype and preliminary explore the prognostic value of AF recurrence after ablation using radiomics models based on epicardial adipose tissue around the left atrium (LA-EAT) of cardiac CT images.MethodThe cardiac CT images of 314 patients were collected wherein 251 and 63 cases were randomly enrolled in the training and validation cohorts, respectively. Mutual information and the random forest algorithm were used to screen for the radiomic features and construct the radiomics signature. Radiomics models reflecting the features of LA-EAT were built to differentiate the AF subtype, and the multivariable logistic regression model was adopted to integrate the radiomics signature and volume information. The same methodology and algorithm were applied to the radiomic features to explore the ability for predicting AF recurrence.ResultsThe predictive model constructed by integrating the radiomic features and volume information using a radiomics nomogram showed the best ability in differentiating AF subtype in the training [AUC, 0.915; 95% confidence interval (CI), 0.880–0.951] and validation (AUC, 0.853; 95% CI, 0.755–0.951) cohorts. The radiomic features have shown convincible predictive ability of AF recurrence in both training (AUC, 0.808; 95% CI, 0.750–0.866) and validation (AUC, 0.793; 95% CI, 0.654–0.931) cohorts.ConclusionsThe LA-EAT radiomic signatures are a promising tool in the differentiation of AF subtype and prediction of AF recurrence, which may have clinical implications in the early diagnosis of AF subtype and disease management.

Radiomics signature of epicardial adipose tissue for predicting postoperative atrial fibrillation after pulmonary endarterectomy

“…Epicardial adipose tissue is a special visceral adipose tissue located between the myocardium and the visceral pericardium ( 14 ). This privileged location positions EAT to exert important paracrine and vasocrine effects on neighboring cardiomyocytes ( 32 ).…”

“…Radiomics quantitatively assesses tissue heterogeneity, which is an objective measure but not visually recognizable, by reflecting the distribution of gray level values and spatial arrangement of the pixels ( 34 ). Radiomics analysis of EAT has been previously shown to be useful in identifying AF ( 23 , 24 ), differentiating AF characteristics, and predicting AF recurrence ( 14 ). These studies revealed that radiomics analysis of EAT may have the potential to provide an accurate prediction for POAF after PEA.…”

“…Although the pathogenesis of POAF remains uncertain, accumulating evidence suggests an important role in inflammatory mechanisms and mediators ( 12 , 13 ). Epicardial adipose tissue (EAT) is a special visceral adipose tissue located between the myocardium and the visceral pericardium ( 14 ). It produces numerous pro-inflammatory cytokines which can promote the development of POAF ( 15 , 16 ).…”

“…It can also provide and uncover quantitative disease characteristics that fail to be detected by observational measures ( 22 ). Radiomics analysis of EAT has been previously proven to be useful in identifying AF ( 23 , 24 ), differentiating AF characteristics, and predicting AF recurrence ( 14 ). Therefore, radiomics may provide additional information beyond EAT volume and radiodensity.…”

Explainable Machine Learning model reveals its decision-making process in identifying patients with paroxysmal atrial fibrillation at high risk for recurrence after catheter ablation

“…Moreover, ML algorithms are appropriate for processing highdimensionality data, given reasonable optimization [7]. Classi cation models based on ML, deep learning (DL) or radiomic methods to predict the outcome of AF have been reported in numerous studies [8][9][10][11][12][13][14][15].…”