To evaluate the feasibility of utilizing cardiac computer tomography (CT) images for extracting the radiomic features of the myocardium at the junction between the left atrial appendage (LAA) and the left atrium (LA) in patients with atrial fibrillation (AF) and to evaluate its asscociation with the risk of AF. A retrospective analysis was conducted on 82 cases of AF and 56 cases in the control group who underwent cardiac CT at our hospital from May 2022 to May 2023, with recorded clinical information. The morphological parameters of the LAA were measured. A radiomics model, a clincal feature model and a model combining radiomics and clinical features were constructed. The radiomics model was built by extracting radiomic features of the myocardial tissue using Pyradiomics, and employing Least absolute shrinkage and selection operator (LASSO) method for feature selection, combining random forest with support vector machine (SVM) classifier. There were 82 cases in the AF group [44 males, 65.00 (59, 70)], and 56 cases in the control group (21 males, 61.09 ± 7.18). Age, BMI, hypertension, CHA2DS-VASC score, neutrophil to lymphocyte ratio (NLR), LAA volume, LA volume, the myocardial thickness at the junction of LAA and LA, the area, circumference, short diameter, and long diameter of the LAA opening, were significantly different between the AF group and the control group (P < 0.05). After conducting multivariate logistic regression analysis, it was found that BMI, the myocardial thickness at the junction of the LAA and the LA, LA volume, NLR and CHA2DS-VASC score were related to AF. 12 radiomics features of the myocardium at the junction of the LAA and the LA were extracted and identified. ROC curve analysis confirmed that the nomogram based on radiomics scores and clinical factors can effectively predict AF (AUC 0.869). Radiomics enables the extraction of the myocardial characteristics at the junction of the LAA and the LA, which are related with AF, facilitating the assessment of its relationship with the risk of AF. The combination of radiomics with clinical characteristics enhances the evaluation capabilities significantly.
Read full abstract