Sang-Hyup Lee, Kyu Lee Jeon, Yong-Joon Lee, Seng Chan You, Seung-Jun Lee, Sung-Jin Hong, Chul-Min Ahn, Jung-Sun Kim, Byeong-Keuk Kim, Young-Guk Ko, Donghoon Choi, Myeong-Ki Hong
{"title":"Development of Clinically Validated Artificial Intelligence Model for Detecting ST-segment Elevation Myocardial Infarction.","authors":"Sang-Hyup Lee, Kyu Lee Jeon, Yong-Joon Lee, Seng Chan You, Seung-Jun Lee, Sung-Jin Hong, Chul-Min Ahn, Jung-Sun Kim, Byeong-Keuk Kim, Young-Guk Ko, Donghoon Choi, Myeong-Ki Hong","doi":"10.1016/j.annemergmed.2024.06.004","DOIUrl":null,"url":null,"abstract":"<p><strong>Study objective: </strong>Although the importance of primary percutaneous coronary intervention has been emphasized for ST-segment elevation myocardial infarction (STEMI), the appropriateness of the cardiac catheterization laboratory activation remains suboptimal. This study aimed to develop a precise artificial intelligence (AI) model for the diagnosis of STEMI and accurate cardiac catheterization laboratory activation.</p><p><strong>Methods: </strong>We used electrocardiography (ECG) waveform data from a prospective percutaneous coronary intervention registry in Korea in this study. Two independent board-certified cardiologists established a criterion standard (STEMI or Not STEMI) for each ECG based on corresponding coronary angiography data. We developed a deep ensemble model by combining 5 convolutional neural networks. In addition, we performed clinical validation based on a symptom-based ECG data set, comparisons with clinical physicians, and external validation.</p><p><strong>Results: </strong>We used 18,697 ECGs for the model development data set, and 1,745 (9.3%) were STEMI. The AI model achieved an accuracy of 92.1%, sensitivity of 95.4%, and specificity of 91.8 %. The performances of the AI model were well balanced and outstanding in the clinical validation, comparison with clinical physicians, and the external validation.</p><p><strong>Conclusion: </strong>The deep ensemble AI model showed a well-balanced and outstanding performance. As visualized with gradient-weighted class activation mapping, the AI model has a reasonable explainability. Further studies with prospective validation regarding clinical benefit in a real-world setting should be warranted.</p>","PeriodicalId":8236,"journal":{"name":"Annals of emergency medicine","volume":null,"pages":null},"PeriodicalIF":5.0000,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annals of emergency medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.annemergmed.2024.06.004","RegionNum":1,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"EMERGENCY MEDICINE","Score":null,"Total":0}
引用次数: 0
Abstract
Study objective: Although the importance of primary percutaneous coronary intervention has been emphasized for ST-segment elevation myocardial infarction (STEMI), the appropriateness of the cardiac catheterization laboratory activation remains suboptimal. This study aimed to develop a precise artificial intelligence (AI) model for the diagnosis of STEMI and accurate cardiac catheterization laboratory activation.
Methods: We used electrocardiography (ECG) waveform data from a prospective percutaneous coronary intervention registry in Korea in this study. Two independent board-certified cardiologists established a criterion standard (STEMI or Not STEMI) for each ECG based on corresponding coronary angiography data. We developed a deep ensemble model by combining 5 convolutional neural networks. In addition, we performed clinical validation based on a symptom-based ECG data set, comparisons with clinical physicians, and external validation.
Results: We used 18,697 ECGs for the model development data set, and 1,745 (9.3%) were STEMI. The AI model achieved an accuracy of 92.1%, sensitivity of 95.4%, and specificity of 91.8 %. The performances of the AI model were well balanced and outstanding in the clinical validation, comparison with clinical physicians, and the external validation.
Conclusion: The deep ensemble AI model showed a well-balanced and outstanding performance. As visualized with gradient-weighted class activation mapping, the AI model has a reasonable explainability. Further studies with prospective validation regarding clinical benefit in a real-world setting should be warranted.
期刊介绍:
Annals of Emergency Medicine, the official journal of the American College of Emergency Physicians, is an international, peer-reviewed journal dedicated to improving the quality of care by publishing the highest quality science for emergency medicine and related medical specialties. Annals publishes original research, clinical reports, opinion, and educational information related to the practice, teaching, and research of emergency medicine. In addition to general emergency medicine topics, Annals regularly publishes articles on out-of-hospital emergency medical services, pediatric emergency medicine, injury and disease prevention, health policy and ethics, disaster management, toxicology, and related topics.