Department of Cardiovascular Diseases, Mayo Clinic, Rochester, MN.
Department of Cardiovascular Diseases, Mayo Clinic, Rochester, MN.
Mayo Clin Proc. 2021 Nov;96(11):2768-2778. doi: 10.1016/j.mayocp.2021.04.023. Epub 2021 Jul 2.
To develop an artificial intelligence (AI)-based tool to detect cardiac amyloidosis (CA) from a standard 12-lead electrocardiogram (ECG).
We collected 12-lead ECG data from 2541 patients with light chain or transthyretin CA seen at Mayo Clinic between 2000 and 2019. Cases were nearest neighbor matched for age and sex, with 2454 controls. A subset of 2997 (60%) cases and controls were used to train a deep neural network to predict the presence of CA with an internal validation set (n=999; 20%) and a randomly selected holdout testing set (n=999; 20%). We performed experiments using single-lead and 6-lead ECG subsets.
The area under the receiver operating characteristic curve (AUC) was 0.91 (CI, 0.90 to 0.93), with a positive predictive value for detecting either type of CA of 0.86. By use of a cutoff probability of 0.485 determined by the Youden index, 426 (84%) of the holdout patients with CA were detected by the model. Of the patients with CA and prediagnosis electrocardiographic studies, the AI model successfully predicted the presence of CA more than 6 months before the clinical diagnosis in 59%. The best single-lead model was V5 with an AUC of 0.86 and a precision of 0.78, with other single leads performing similarly. The 6-lead (bipolar leads) model had an AUC of 0.90 and a precision of 0.85.
An AI-driven ECG model effectively detects CA and may promote early diagnosis of this life-threatening disease.
开发一种基于人工智能（AI）的工具，以便从标准 12 导联心电图（ECG）中检测心脏淀粉样变性（CA）。
我们收集了 2000 年至 2019 年期间在梅奥诊所就诊的 2541 例轻链或转甲状腺素蛋白 CA 患者的 12 导联 ECG 数据。病例按年龄和性别进行最近邻匹配，对照组有 2454 例。使用 2997 例（60%）病例和对照组的子集来训练深度神经网络，以使用内部验证集（n=999；20%）和随机选择的保留测试集（n=999；20%）预测 CA 的存在。我们使用单导联和 6 导联 ECG 子集进行了实验。
受试者工作特征曲线下面积（AUC）为 0.91（CI，0.90 至 0.93），检测到任何类型 CA 的阳性预测值为 0.86。通过使用 Youden 指数确定的 0.485 的截断概率，模型检测到 426 例（84%）CA 患者的 CA。在有 CA 和预诊断心电图研究的患者中，AI 模型成功预测了 59%的 CA 患者在临床诊断前 6 个月以上存在 CA。最佳的单导联模型是 V5，AUC 为 0.86，精度为 0.78，其他单导联表现类似。6 导联（双极导联）模型的 AUC 为 0.90，精度为 0.85。
一种 AI 驱动的 ECG 模型可有效检测 CA，并可能促进这种危及生命疾病的早期诊断。
