ECG-Based Deep Learning and Clinical Risk Factors to Predict Atrial Fibrillation.
ECG-Based Deep Learning and Clinical Risk Factors to Predict Atrial Fibrillation.
复制标题
DOI：
10.1161/circulationaha.121.057480
复制
发表时间：
2022-01-11
期刊：
影响因子：
37.8
通讯作者：
Lubitz SA
中科院分区：
文献类型：
--
作者：
Khurshid S;Friedman S;Reeder C;Di Achille P;Diamant N;Singh P;Harrington LX;Wang X;Al-Alusi MA;Sarma G;Foulkes AS;Ellinor PT;Anderson CD;Ho JE;Philippakis AA;Batra P;Lubitz SA
人工智能（AI）支持的12导联心电图（ECGs）分析可能有助于有效估计房颤（AF）风险。然而，目前尚不清楚人工智能是否在房颤的预测准确性方面提供了有意义的、可推广的改进，超出了临床危险因素。我们训练了一个卷积神经网络（“ECG-AI”），利用马萨诸塞州总医院（MGH）接受纵向初级保健的12导联心电图推断5年房颤事件风险。然后我们拟合了三个Cox比例风险模型，每个模型由：a) ECG-AI 5年房颤概率，b)基因组流行病学房颤（CHARGE-AF）临床风险评分中的心脏和衰老队列，以及c) ECG-AI和CHARGE-AF的术语（“CH-AI”）组成。我们通过计算鉴别（受试者工作特征曲线下面积，AUROC）和内部测试集和两个外部测试集（Brigham and Women 's Hospital和UK Biobank）的校准来评估模型的性能。在英国生物银行有限的随访情况下，重新校准模型以估计2年房颤风险。我们使用显著性映射来识别对ECG- ai风险预测影响最大的ECG特征，并评估ECG- ai和CHARGE-AF线性预测因子之间的相关性。训练集包括45,770人（年龄55±17岁，53%女性，2,171 AF事件），测试集包括83,162人（年龄59±13岁，56%女性，2,424 AF事件）。使用CHARGE-AF （MGH 0.802, 95% CI 0.767-0.836; BWH 0.752, 95% CI 0.741-0.763; UK Biobank 0.732, 95% CI 0.704-0.759）和ECG-AI （MGH 0.823, 95% CI 0.790-0.856; BWH 0.747, 95% CI 0.736-0.759; UK Biobank 0.705, 95% CI 0.673-0.737）的AUROC具有可比性。使用CH-AI时AUROC最高：MGH 0.838, 95% CI 0.807 ~ 0.869；BWH 0.777, 95% ci 0.766-0.788；UK Biobank 0.746, 95% CI 0.716-0.776)。使用ECG-AI （MGH 0.0212; BWH 0.0129; UK Biobank 0.0035）和CH-AI （MGH 0.012; BWH 0.0108; UK Biobank 0.0001）校正误差较低。在显著性分析中，心电p波对AI模型预测的影响最大。ECG-AI和CHARGE-AF线性预测因子相关（Pearson r MGH 0.61, BWH 0.66, UK Biobank 0.41）。基于人工智能的12导联心电图分析与偶发性房颤的临床风险因素模型具有相似的预测效用，两种方法是互补的。ECG-AI可以有效量化未来房颤风险。
Artificial intelligence (AI)-enabled analysis of 12-lead electrocardiograms (ECGs) may facilitate efficient estimation of incident atrial fibrillation (AF) risk. However, it remains unclear whether AI provides meaningful and generalizable improvement in predictive accuracy beyond clinical risk factors for AF. We trained a convolutional neural network (“ECG-AI”) to infer 5-year incident AF risk using 12-lead ECGs in patients receiving longitudinal primary care at Massachusetts General Hospital (MGH). We then fit three Cox proportional hazards models, each composed of: a) ECG-AI 5-year AF probability, b) the Cohorts for Heart and Aging in Genomic Epidemiology AF (CHARGE-AF) clinical risk score, and c) terms for both ECG-AI and CHARGE-AF (“CH-AI”). We assessed model performance by calculating discrimination (area under the receiver operating characteristic curve, AUROC) and calibration in an internal test set and two external test sets (Brigham and Women’s Hospital and UK Biobank). Models were recalibrated to estimate 2-year AF risk in the UK Biobank given limited available follow-up. We used saliency mapping to identify ECG features most influential on ECG-AI risk predictions and assessed correlation between ECG-AI and CHARGE-AF linear predictors. The training set comprised 45,770 individuals (age 55±17 years, 53% women, 2,171 AF events), and the test sets comprised 83,162 individuals (age 59±13 years, 56% women, 2,424 AF events). AUROC was comparable using CHARGE-AF (MGH 0.802, 95% CI 0.767–0.836; BWH 0.752, 95% CI 0.741–0.763; UK Biobank 0.732, 95% CI 0.704–0.759) and ECG-AI (MGH 0.823, 95% CI 0.790–0.856; BWH 0.747, 95% CI 0.736–0.759; UK Biobank 0.705, 95% CI 0.673–0.737). AUROC was highest using CH-AI: MGH 0.838, 95% CI 0.807–0.869; BWH 0.777, 95% CI 0.766–0.788; UK Biobank 0.746, 95% CI 0.716–0.776). Calibration error was low using ECG-AI (MGH 0.0212; BWH 0.0129; UK Biobank 0.0035) and CH-AI (MGH 0.012; BWH 0.0108; UK Biobank 0.0001). In saliency analyses, the ECG P-wave had the greatest influence on AI model predictions. ECG-AI and CHARGE-AF linear predictors were correlated (Pearson r MGH 0.61, BWH 0.66, UK Biobank 0.41). AI-based analysis of 12-lead ECGs has similar predictive utility to a clinical risk factor model for incident AF and both approaches are complementary. ECG-AI may enable efficient quantification of future AF risk.