目的:高功率短持续时间(HPSD)消融是房颤的有效治疗方法,但存在食管和迷走神经热损伤的风险。这项研究调查了热损伤的发生率和预测因素,采用机器学习。
方法:在莱比锡心脏中心进行了一项前瞻性观察研究,德国,排除多次消融的患者。所有患者均接受消融指数指导的HPSD消融和随后的食管胃十二指肠镜检查。机器学习算法根据心房位置对消融点进行分类,并分析消融数据。包括消融指数,专注于后壁。该研究已在clinicaltrials.gov(NCT05709756)中注册。
结果:在2021年2月至2023年8月之间,共招募了238名患者,其中18人(7.6%;9人食管,8迷走神经,1)发生热损伤,包括8个食管红斑,两个溃疡,没有瘘管。较高的平均力(15.8±3.9g与13.6±3.9g,p=0.022),消融点数量(61.50±20.45vs.48.16±19.60,p=0.007),总消融指数和最大消融指数(24114±8765vs.18894±7863,p=0.008;499±95vs.473±44,p=0.04,分别)在后壁,但不是食道位置,与热损伤发生显著相关。热损伤患者左心房和食管之间的距离明显较低(3.0±1.5mmvs4.4±2.1mm,p=0.012)和较小的心房表面积(24.9±6.5cm2vs.29.5±7.5cm2,p=0.032)。
结论:消融指数指导的HPSD消融治疗心房颤动期间的低热损伤率(7.6%)值得注意。基于机器学习的消融数据分析确定了热损伤的几种潜在预测因素。机器学习输出与损伤发展之间的相关性表明了临床工具增强程序安全性的潜力。
OBJECTIVE: High-power-short-duration (HPSD) ablation is an effective treatment for atrial fibrillation but poses risks of thermal injuries to the oesophagus and vagus nerve. This
study aims to investigate incidence and predictors of thermal injuries, employing machine learning.
RESULTS: A prospective observational
study was conducted at Leipzig Heart Centre, Germany, excluding patients with multiple prior ablations. All patients received Ablation Index-guided HPSD ablation and subsequent oesophagogastroduodenoscopy. A machine learning algorithm categorized ablation points by atrial location and analysed ablation data, including Ablation Index, focusing on the posterior wall. The
study is registered in clinicaltrials.gov (NCT05709756). Between February 2021 and August 2023, 238 patients were enrolled, of whom 18 (7.6%; nine oesophagus, eight vagus nerve, one both) developed thermal injuries, including eight oesophageal erythemata, two ulcers, and no fistula. Higher mean force (15.8 ± 3.9 g vs. 13.6 ± 3.9 g, P = 0.022), ablation point quantity (61.50 ± 20.45 vs. 48.16 ± 19.60, P = 0.007), and total and maximum Ablation Index (24 114 ± 8765 vs. 18 894 ± 7863, P = 0.008; 499 ± 95 vs. 473 ± 44, P = 0.04, respectively) at the posterior wall, but not oesophagus location, correlated significantly with thermal injury occurrence. Patients with thermal injuries had significantly lower distances between left atrium and oesophagus (3.0 ± 1.5 mm vs. 4.4 ± 2.1 mm, P = 0.012) and smaller atrial surface areas (24.9 ± 6.5 cm2 vs. 29.5 ± 7.5 cm2, P = 0.032).
CONCLUSIONS: The low thermal lesion\'s rate (7.6%) during Ablation Index-guided HPSD ablation for atrial fibrillation is noteworthy. Machine learning based ablation data analysis identified several potential predictors of thermal injuries. The correlation between machine learning output and injury development suggests the potential for a clinical tool to enhance procedural safety.