Mai Peipei, Huo Huanhuan, Li Xiaona, Zhou Dingwen, He Fang, Li Yongxin, Wang Hua
Department of Ultrasonography, Luoyang Central Hospital Affiliated to Zhengzhou University, Luoyang, China.
Department of Ultrasound, The Second Affiliated Hospital, Medical School of Xi'an Jiaotong University, Xi'an, China.
Front Med (Lausanne). 2025 Aug 15;12:1661696. doi: 10.3389/fmed.2025.1661696. eCollection 2025.
Non-Valvular Atrial fibrillation (NVAF) and atrial flutter are significant contributors to left atrial appendage thrombus (LAAT) formation. This study explores the potential of machine learning (ML) models integrating transthoracic echocardiography (TTE) and clinical data for non-invasive LAAT detection and risk assessment.
A total of 698 patients with NVAF was recruited from Luoyang Central Hospital between January 2021 and May 2024, including 558 patients for retrospective analysis and 140 for prospective validation. Based on transesophageal echocardiography (TEE) results, patients were categorized into three groups: non-thrombotic, blood stasis, and thrombotic. Four ML algorithms-Random Forest, Logistic Regression (LR), Support Vector Machine, and XGBoost-were developed using TTE and clinical data to predict LAAT.
Univariate analysis identified significant predictors of LAAT, including permanent AF, heart failure, BNP, uric acid, D-dimer, mitral regurgitation, LVEF, LVED, LAD, CHA₂DS₂-VASc score, and LAA velocity ( < 0.05). The combined TTE data model outperformed independent TTE-based models but was slightly less accurate than the TEE model. Among ML algorithms, the LR model demonstrated the best performance, achieving an area under the curve (AUC) of 80.9% in the test set and 78.7% in prospective validation for the thrombotic state group. For the thrombotic group, the LR model achieved an AUC of 80.0%, closely approaching the TEE model's 84.0%.
The LR model provides a reliable non-invasive approach for LAAT screening in high-risk AF patients by integrating TTE features with clinical data, potentially reducing reliance on TEE.
非瓣膜性心房颤动（NVAF）和心房扑动是左心耳血栓（LAAT）形成的重要因素。本研究探讨了整合经胸超声心动图（TTE）和临床数据的机器学习（ML）模型用于无创LAAT检测和风险评估的潜力。
2021年1月至2024年5月期间，从洛阳中心医院招募了698例NVAF患者，其中558例用于回顾性分析，140例用于前瞻性验证。根据经食管超声心动图（TEE）结果，将患者分为三组：非血栓形成组、血瘀组和血栓形成组。使用TTE和临床数据开发了四种ML算法——随机森林、逻辑回归（LR）、支持向量机和XGBoost——来预测LAAT。
单因素分析确定了LAAT的重要预测因素，包括永久性房颤、心力衰竭、脑钠肽、尿酸、D-二聚体、二尖瓣反流、左心室射血分数、左心室舒张末期内径、左心房内径、CHA₂DS₂-VASc评分和左心耳速度（<0.05）。联合TTE数据模型优于基于独立TTE的模型，但准确性略低于TEE模型。在ML算法中，LR模型表现最佳，在测试集中血栓形成状态组的曲线下面积（AUC）为80.9%，在前瞻性验证中为78.7%。对于血栓形成组，LR模型的AUC为80.0%，与TEE模型的84.0%非常接近。
LR模型通过将TTE特征与临床数据相结合，为高危房颤患者的LAAT筛查提供了一种可靠的无创方法，有可能减少对TEE的依赖。
