Mahabadi Amir A, Knobeloch Jan, Backmann Viktoria, Michel Lars, Anker Markus S, Wakili Reza, Fach Christian, Anker Stefan D, Rassaf Tienush
West German Heart and Vascular Center, Department of Cardiology and Vascular Medicine, University Hospital Essen, Essen, Germany.
INSOMNIA UG, Weimar, Germany.
ESC Heart Fail. 2025 Aug;12(4):2993-3002. doi: 10.1002/ehf2.15318. Epub 2025 May 4.
Currently, there is no established screening tool for cardiac amyloidosis, leading to a delay in diagnosis in the majority of patients. We aimed to develop and validate a non-invasive and easy to use tool that allows for screening of cardiac amyloidosis based on structured evaluation of three-dimensional electrocardiograms (ECGs).
We included patients with confirmed cardiac AL or ATTR amyloidosis and controls of patients with other cardiovascular diseases but without amyloidosis into two independent cohorts: a derivation and validation cohort. All patients received three-dimensional ECGs and vector loops were categorized based on predefined patterns by two independent cardiologists. Consecutively, an AI algorithm was trained in the derivation cohort (n = 66 amyloidosis cases, n = 89 controls). This algorithm was then applied to the validation cohort (n = 33 amyloidosis cases, n = 67 controls). Overall, 99 patients with amyloidosis and 156 controls were included (mean age: 69 ± 15 years, 79% male). In the derivation cohort, the AI algorithm reached a sensitivity of 85%, a specificity of 89%, a positive predictive value of 91%, and a negative predictive value of 87%. Applying the algorithm on the independent validation cohort, a sensitivity of 79%, specificity of 82%, a positive predictive value of 61%, and a negative predictive value of 92% was reached.
We here describe a novel screening tool, which allows for reliable detection of cardiac amyloidosis.
目前，尚无用于心脏淀粉样变性的既定筛查工具，导致大多数患者诊断延迟。我们旨在开发并验证一种非侵入性且易于使用的工具，该工具能够基于对三维心电图（ECG）的结构化评估来筛查心脏淀粉样变性。
我们将确诊为心脏AL或ATTR淀粉样变性的患者以及患有其他心血管疾病但无淀粉样变性的对照患者纳入两个独立队列：一个推导队列和一个验证队列。所有患者均接受三维心电图检查，两名独立的心脏病专家根据预定义模式对向量环进行分类。随后，在推导队列（n = 66例淀粉样变性病例，n = 89例对照）中训练人工智能算法。然后将该算法应用于验证队列（n = 33例淀粉样变性病例，n = 67例对照）。总体而言，纳入了99例淀粉样变性患者和156例对照（平均年龄：69±15岁，79%为男性）。在推导队列中，人工智能算法的敏感性为85%，特异性为89%，阳性预测值为91%，阴性预测值为87%。将该算法应用于独立的验证队列时，敏感性为79%，特异性为82%，阳性预测值为61%，阴性预测值为92%。
我们在此描述了一种新型筛查工具，它能够可靠地检测心脏淀粉样变性。
