Carrick Richard T, Carruth Eric D, Gasperetti Alessio, Murray Brittney, Tichnell Crystal, Gaine Sean, Sampognaro James, Muller Steven A, Asatryan Babken, Haggerty Chris, Thiemann David, Calkins Hugh, James Cynthia A, Wu Katherine C
Heart and Vascular Institute, Johns Hopkins Hospital, Baltimore, Maryland.
Department of Genomic Health, Geisinger Medical Center, Danville, Pennsylvania.
Heart Rhythm. 2025 Apr;22(4):1080-1088. doi: 10.1016/j.hrthm.2024.08.030. Epub 2024 Aug 20.
Arrhythmogenic right ventricular cardiomyopathy (ARVC) is a rare genetic heart disease associated with life-threatening ventricular arrhythmias. Diagnosis of ARVC is based on the 2010 Task Force Criteria (TFC), application of which often requires clinical expertise at specialized centers.
The purpose of this study was to develop and validate an electrocardiogram (ECG) deep learning (DL) tool for ARVC diagnosis.
ECGs of patients referred for ARVC evaluation were used to develop (n = 551 [80.1%]) and test (n = 137 [19.9%]) an ECG-DL model for prediction of TFC-defined ARVC diagnosis. The ARVC ECG-DL model was externally validated in a cohort of patients with pathogenic or likely pathogenic (P/LP) ARVC gene variants identified through the Geisinger MyCode Community Health Initiative (N = 167).
Of 688 patients evaluated at Johns Hopkins Hospital (JHH) (57.3% male, mean age 40.2 years), 329 (47.8%) were diagnosed with ARVC. Although ARVC diagnosis made by referring cardiologist ECG interpretation was unreliable (c-statistic 0.53; confidence interval [CI] 0.52-0.53), ECG-DL discrimination in the hold-out testing cohort was excellent (0.87; 0.86-0.89) and compared favorably to that of ECG interpretation by an ARVC expert (0.85; 0.84-0.86). In the Geisinger cohort, prevalence of ARVC was lower (n = 17 [10.2%]), but ECG-DL-based identification of ARVC phenotype remained reliable (0.80; 0.77-0.83). Discrimination was further increased when ECG-DL predictions were combined with non-ECG-derived TFC in the JHH testing (c-statistic 0.940; 95% CI 0.933-0.948) and Geisinger validation (0.897; 95% CI 0.883-0.912) cohorts.
ECG-DL augments diagnosis of ARVC to the level of an ARVC expert and can differentiate true ARVC diagnosis from phenotype-mimics and at-risk family members/genotype-positive individuals.
致心律失常性右室心肌病（ARVC）是一种罕见的遗传性心脏病，与危及生命的室性心律失常相关。ARVC的诊断基于2010年工作组标准（TFC），应用该标准通常需要专业中心的临床专业知识。
本研究的目的是开发并验证一种用于ARVC诊断的心电图（ECG）深度学习（DL）工具。
将因ARVC评估而转诊患者的心电图用于开发（n = 551 [80.1%]）和测试（n = 137 [19.9%]）一个用于预测TFC定义的ARVC诊断的ECG-DL模型。ARVC ECG-DL模型在通过盖辛格MyCode社区健康倡议确定的具有致病性或可能致病性（P/LP）ARVC基因变异的患者队列中进行了外部验证（N = 167）。
在约翰霍普金斯医院（JHH）评估的688例患者中（57.3%为男性，平均年龄40.2岁），329例（47.8%）被诊断为ARVC。尽管经转诊心脏病专家进行ECG解读做出的ARVC诊断不可靠（c统计量为0.53；置信区间[CI] 0.52 - 0.53），但在保留测试队列中ECG-DL的鉴别能力极佳（0.87；0.86 - 0.89），且与ARVC专家进行的ECG解读相比更具优势（0.85；0.84 - 0.86）。在盖辛格队列中，ARVC的患病率较低（n = 17 [10.2%]），但基于ECG-DL的ARVC表型识别仍然可靠（0.80；0.77 - 0.83）。当在JHH测试（c统计量0.940；95% CI 0.933 - 0.948）和盖辛格验证（0.897；95% CI 0.883 - 0.912）队列中将ECG-DL预测与非ECG衍生的TFC相结合时，鉴别能力进一步提高。
ECG-DL将ARVC的诊断提升到了ARVC专家的水平，并且可以将真正的ARVC诊断与表型模仿者以及高危家庭成员/基因型阳性个体区分开来。
