rECHOmmend:基于心电图机器学习识别未诊断结构性心脏病高风险患者
研究利用2 232 130份心电图及484 765名成人数据,训练机器学习模型预测1年内超声心动图确诊的7种结构性心脏病复合终点。模型仅用年龄、性别和心电图波形,交叉验证AUC 0.91,90%敏感度下阳性预测值42%,复合标签患病率17.9%。模拟回顾部署显示2010年无结构性心脏病患者中11%被判定高风险,其中41%一年内确诊。
要点
- 复合模型AUC 0.91,90%敏感度下PPV 42%,优于单病种模型。
- 仅需年龄、性别和心电图波形即可预测1年内结构性心脏病。
- 模拟部署中高风险心电图占11%,其中41%一年内确诊。
核心结论
- 基于心电图的机器学习复合终点模型能识别未诊断且临床显著的结构性心脏病高风险人群,性能优于单病种模型且阳性预测值更高。
研究设计与样本
- 使用1984至2021年间2 232 130份心电图,关联484 765名成人的电子健康记录和超声心动图报告,训练机器学习模型预测1年内7种超声确诊疾病的存在与否。
- 采用5折交叉验证、多中心验证(1中心训练、10个独立中心测试)及模拟回顾部署(2010年前数据训练、2010年部署)评估模型。
主要发现
- 复合rECHOmmend模型使用年龄、性别和心电图波形,AUC 0.91,90%敏感度下阳性预测值42%,复合标签患病率17.9%。
- 单病种模型AUC 0.86至0.93,阳性预测值1%至31%。
- 不同输入特征模型AUC 0.80至0.93,随特征增加而提高。
- 多中心验证汇总AUC 0.91,与交叉验证相似。
- 模拟回顾部署中,2010年无既往结构性心脏病患者的心电图中11%被分类为高风险,其中41%(占总患者4.5%)1年内发生超声确诊疾病。
关键数值与推荐
- 复合标签包括:中度或重度瓣膜病(主动脉/二尖瓣狭窄或反流、三尖瓣反流)、射血分数<50%或室间隔厚度>15 mm。
临床怎么用
- 该模型可辅助靶向筛查,对心电图高风险患者推荐超声心动图以改善结构性心脏病诊断不足。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: Timely diagnosis of structural heart disease improves patient outcomes, yet many remain underdiagnosed. While population screening with echocardiography is impractical, ECG-based prediction models can help target high-risk patients. We developed a novel ECG-based machine learning approach to predict multiple structural heart conditions, hypothesizing that a composite model would yield higher prevalence and positive predictive values to facilitate meaningful recommendations for echocardiography. METHODS: Using 2 232 130 ECGs linked to electronic health records and echocardiography reports from 484 765 adults between 1984 to 2021, we trained machine learning models to predict the presence or absence of any of 7 echocardiography-confirmed diseases within 1 year. This composite label included the following: moderate or severe valvular disease (aortic/mitral stenosis or regurgitation, tricuspid regurgitation), reduced ejection fraction <50%, or interventricular septal thickness >15 mm. We tested various combinations of input features (demographics, laboratory values, structured ECG data, ECG traces) and evaluated model performance using 5-fold cross-validation, multisite validation trained on 1 site and tested on 10 independent sites, and simulated retrospective deployment trained on pre-2010 data and deployed in 2010. RESULTS: Our composite rECHOmmend model used age, sex, and ECG traces and had a 0.91 area under the receiver operating characteristic curve and a 42% positive predictive value at 90% sensitivity, with a composite label prevalence of 17.9%. Individual disease models had area under the receiver operating characteristic curves from 0.86 to 0.93 and lower positive predictive values from 1% to 31%. Area under the receiver operating characteristic curves for models using different input features ranged from 0.80 to 0.93, increasing with additional features. Multisite validation showed similar results to cross-validation, with an aggregate area under the receiver operating characteristic curve of 0.91 across our independent test set of 10 clinical sites after training on a separate site. Our simulated retrospective deployment showed that for ECGs acquired in patients without preexisting structural heart disease in the year 2010, 11% were classified as high risk and 41% (4.5% of total patients) developed true echocardiography-confirmed disease within 1 year. CONCLUSIONS: An ECG-based machine learning model using a composite end point can identify a high-risk population for having undiagnosed, clinically significant structural heart disease while outperforming single-disease models and improving practical utility with higher positive predictive values. This approach can facilitate targeted screening with echocardiography to improve underdiagnosis of structural heart disease.
引用
- Ulloa-Cerna AE, Jing L, Pfeifer JM, et al. rECHOmmend: An ECG-Based Machine Learning Approach for Identifying Patients at Increased Risk of Undiagnosed Structural Heart Disease Detectable by Echocardiography. Circulation. 2022. PMID: 35533093. doi:10.1161/CIRCULATIONAHA.121.057869
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。