Liam Butler, Alexander Ivanov, Turgay Celik, Ibrahim Karabayir, Lokesh Chinthala, Mohammad S Tootooni, Byron C Jaeger, Luke T Patterson, Adam J Doerr, David D McManus, Robert L Davis, David Herrington, Oguz Akbilgic
{"title":"时间依赖性ECG-AI预测致死性冠心病的回顾性研究","authors":"Liam Butler, Alexander Ivanov, Turgay Celik, Ibrahim Karabayir, Lokesh Chinthala, Mohammad S Tootooni, Byron C Jaeger, Luke T Patterson, Adam J Doerr, David D McManus, Robert L Davis, David Herrington, Oguz Akbilgic","doi":"10.3390/jcdd11120395","DOIUrl":null,"url":null,"abstract":"<p><p><b>Background</b>: Fatal coronary heart disease (FCHD) affects ~650,000 people yearly in the US. Electrocardiographic artificial intelligence (ECG-AI) models can predict adverse coronary events, yet their application to FCHD is understudied. <b>Objectives</b>: The study aimed to develop ECG-AI models predicting FCHD risk from ECGs. <b>Methods (Retrospective)</b>: Data from 10 s 12-lead ECGs and demographic/clinical data from University of Tennessee Health Science Center (UTHSC) were used for model development. Of this dataset, 80% was used for training and 20% as holdout. Data from Atrium Health Wake Forest Baptist (AHWFB) were used for external validation. We developed two separate convolutional neural network models using 12-lead and Lead I ECGs as inputs, and time-dependent Cox proportional hazard models using demographic/clinical data with ECG-AI outputs. Correlation of the predictions from the 12- and 1-lead ECG-AI models was assessed. <b>Results</b>: The UTHSC cohort included data from 50,132 patients with a mean age (SD) of 62.50 (14.80) years, of whom 53.4% were males and 48.5% African American. The AHWFB cohort included data from 2305 patients with a mean age (SD) of 63.04 (16.89) years, of whom 51.0% were males and 18.8% African American. The 12-lead and Lead I ECG-AI models resulted in validation AUCs of 0.84 and 0.85, respectively. The best overall model was the Cox model using simple demographics with Lead I ECG-AI output (D1-ECG-AI-Cox), with the following results: AUC = 0.87 (0.85-0.89), accuracy = 83%, sensitivity = 69%, specificity = 89%, negative predicted value (NPV) = 92% and positive predicted value (PPV) = 55% on the AHWFB validation cohort. For this, the 2-year FCHD risk prediction accuracy was AUC = 0.91 (0.90-0.92). The 12-lead versus Lead I ECG FCHD risk prediction showed strong correlation (R = 0.74). <b>Conclusions</b>: The 2-year FCHD risk can be predicted with high accuracy from single-lead ECGs, further improving when combined with demographic information.</p>","PeriodicalId":15197,"journal":{"name":"Journal of Cardiovascular Development and Disease","volume":"11 12","pages":""},"PeriodicalIF":2.4000,"publicationDate":"2024-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11678222/pdf/","citationCount":"0","resultStr":"{\"title\":\"Time-Dependent ECG-AI Prediction of Fatal Coronary Heart Disease: A Retrospective Study.\",\"authors\":\"Liam Butler, Alexander Ivanov, Turgay Celik, Ibrahim Karabayir, Lokesh Chinthala, Mohammad S Tootooni, Byron C Jaeger, Luke T Patterson, Adam J Doerr, David D McManus, Robert L Davis, David Herrington, Oguz Akbilgic\",\"doi\":\"10.3390/jcdd11120395\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p><b>Background</b>: Fatal coronary heart disease (FCHD) affects ~650,000 people yearly in the US. Electrocardiographic artificial intelligence (ECG-AI) models can predict adverse coronary events, yet their application to FCHD is understudied. <b>Objectives</b>: The study aimed to develop ECG-AI models predicting FCHD risk from ECGs. <b>Methods (Retrospective)</b>: Data from 10 s 12-lead ECGs and demographic/clinical data from University of Tennessee Health Science Center (UTHSC) were used for model development. Of this dataset, 80% was used for training and 20% as holdout. Data from Atrium Health Wake Forest Baptist (AHWFB) were used for external validation. We developed two separate convolutional neural network models using 12-lead and Lead I ECGs as inputs, and time-dependent Cox proportional hazard models using demographic/clinical data with ECG-AI outputs. Correlation of the predictions from the 12- and 1-lead ECG-AI models was assessed. <b>Results</b>: The UTHSC cohort included data from 50,132 patients with a mean age (SD) of 62.50 (14.80) years, of whom 53.4% were males and 48.5% African American. The AHWFB cohort included data from 2305 patients with a mean age (SD) of 63.04 (16.89) years, of whom 51.0% were males and 18.8% African American. The 12-lead and Lead I ECG-AI models resulted in validation AUCs of 0.84 and 0.85, respectively. The best overall model was the Cox model using simple demographics with Lead I ECG-AI output (D1-ECG-AI-Cox), with the following results: AUC = 0.87 (0.85-0.89), accuracy = 83%, sensitivity = 69%, specificity = 89%, negative predicted value (NPV) = 92% and positive predicted value (PPV) = 55% on the AHWFB validation cohort. For this, the 2-year FCHD risk prediction accuracy was AUC = 0.91 (0.90-0.92). The 12-lead versus Lead I ECG FCHD risk prediction showed strong correlation (R = 0.74). <b>Conclusions</b>: The 2-year FCHD risk can be predicted with high accuracy from single-lead ECGs, further improving when combined with demographic information.</p>\",\"PeriodicalId\":15197,\"journal\":{\"name\":\"Journal of Cardiovascular Development and Disease\",\"volume\":\"11 12\",\"pages\":\"\"},\"PeriodicalIF\":2.4000,\"publicationDate\":\"2024-12-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11678222/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Cardiovascular Development and Disease\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.3390/jcdd11120395\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"CARDIAC & CARDIOVASCULAR SYSTEMS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Cardiovascular Development and Disease","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.3390/jcdd11120395","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}
引用次数: 0
摘要
背景：致死性冠心病（FCHD）在美国每年影响约65万人。心电图人工智能（ECG-AI）模型可以预测不良冠状动脉事件，但其在FCHD中的应用尚未得到充分研究。目的：本研究旨在建立通过心电图预测FCHD风险的ECG-AI模型。方法（回顾性）：采用10年12导联心电图数据和田纳西大学健康科学中心（UTHSC）的人口统计学/临床数据进行模型开发。在这个数据集中，80%用于训练，20%用于保留。来自Atrium Health Wake Forest Baptist （AHWFB）的数据用于外部验证。我们开发了两个独立的卷积神经网络模型，使用12导联和1导联心电图作为输入，以及使用人口统计学/临床数据和ECG-AI输出的时间相关Cox比例风险模型。评估12导联和1导联ECG-AI模型预测的相关性。结果：UTHSC队列纳入了50,132例患者的数据，平均年龄（SD）为62.50（14.80）岁，其中53.4%为男性，48.5%为非洲裔美国人。AHWFB队列包括2305例患者的数据，平均年龄（SD）为63.04（16.89）岁，其中51.0%为男性，18.8%为非洲裔美国人。12导联和1导联ECG-AI模型的验证auc分别为0.84和0.85。最佳的综合模型是使用铅I ECG-AI输出（D1-ECG-AI-Cox）的简单人口统计学Cox模型，其结果如下：AHWFB验证队列的AUC = 0.87(0.85-0.89)，准确性= 83%，灵敏度= 69%，特异性= 89%，阴性预测值(NPV) = 92%，阳性预测值(PPV) = 55%。因此，2年FCHD风险预测准确率AUC = 0.91（0.90-0.92）。12导联与1导联心电图FCHD风险预测相关性强（R = 0.74）。结论：单导联心电图可准确预测2年FCHD风险，结合人口统计学信息可进一步提高预测准确率。
Time-Dependent ECG-AI Prediction of Fatal Coronary Heart Disease: A Retrospective Study.
Background: Fatal coronary heart disease (FCHD) affects ~650,000 people yearly in the US. Electrocardiographic artificial intelligence (ECG-AI) models can predict adverse coronary events, yet their application to FCHD is understudied. Objectives: The study aimed to develop ECG-AI models predicting FCHD risk from ECGs. Methods (Retrospective): Data from 10 s 12-lead ECGs and demographic/clinical data from University of Tennessee Health Science Center (UTHSC) were used for model development. Of this dataset, 80% was used for training and 20% as holdout. Data from Atrium Health Wake Forest Baptist (AHWFB) were used for external validation. We developed two separate convolutional neural network models using 12-lead and Lead I ECGs as inputs, and time-dependent Cox proportional hazard models using demographic/clinical data with ECG-AI outputs. Correlation of the predictions from the 12- and 1-lead ECG-AI models was assessed. Results: The UTHSC cohort included data from 50,132 patients with a mean age (SD) of 62.50 (14.80) years, of whom 53.4% were males and 48.5% African American. The AHWFB cohort included data from 2305 patients with a mean age (SD) of 63.04 (16.89) years, of whom 51.0% were males and 18.8% African American. The 12-lead and Lead I ECG-AI models resulted in validation AUCs of 0.84 and 0.85, respectively. The best overall model was the Cox model using simple demographics with Lead I ECG-AI output (D1-ECG-AI-Cox), with the following results: AUC = 0.87 (0.85-0.89), accuracy = 83%, sensitivity = 69%, specificity = 89%, negative predicted value (NPV) = 92% and positive predicted value (PPV) = 55% on the AHWFB validation cohort. For this, the 2-year FCHD risk prediction accuracy was AUC = 0.91 (0.90-0.92). The 12-lead versus Lead I ECG FCHD risk prediction showed strong correlation (R = 0.74). Conclusions: The 2-year FCHD risk can be predicted with high accuracy from single-lead ECGs, further improving when combined with demographic information.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
