Artificial Intelligence-Guided Single-Lead ECG May Be a Game-Changer for Symptom-to-Balloon Time Reduction in ST-Elevated Myocardial Infarction

S. Mehta, D. Vieira, D. Zerpa, Aline Quintana, Madyan Al Troudy, L. Brena-Pastor, C. Whuking, F. Martinez, Jacques Calixte, Devarsh Desai, Surik Sedrakyan, Nataly Rendón, Gabriel Peña
{"title":"Artificial Intelligence-Guided Single-Lead ECG May Be a Game-Changer for Symptom-to-Balloon Time Reduction in ST-Elevated Myocardial Infarction","authors":"S. Mehta, D. Vieira, D. Zerpa, Aline Quintana, Madyan Al Troudy, L. Brena-Pastor, C. Whuking, F. Martinez, Jacques Calixte, Devarsh Desai, Surik Sedrakyan, Nataly Rendón, Gabriel Peña","doi":"10.33590/emjcardiol/10098409","DOIUrl":null,"url":null,"abstract":"\n \n \n Over decades, efforts to shave off life-saving minutes from ST-Elevated Myocardial Infarction (STEMI) care centred on reducing door-to-needle and door-to-balloon times. We firmly believe that symptom-to-balloon time should prove a better focus to this end. Challenges come with this goal as it heavily relies on a patient's perception and initiative to seek care, which we deem intelligent and wearable Artificial Intelligence (AI)-driven Single Lead EKG technologies as an attractive solution in modern-day cardiology.\n \n \n \n To provide an accurate, accessible, and cost-effective AI-driven Single Lead STEMI detection algorithm that can be embedded into wearable devices and employed in a self-administered fashion.\n \n \n \n Database: EKG records from Mexico, Colombia, Argentina, and Brazil from April 2014 to December 2019. Dataset: A total of 11,567 12-lead EKG records of 10[s] length with a sampling frequency of 500 Hz, including the following balanced classes: angiographically confirmed and unconfirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal and abnormal (200+ CPT codes, excluding those mentioned above). Cardiologists manually checked the label of each record to ensure precision. Pre-processing: We discard the first and last 250 samples as they may contain a standardisation pulse. The study applied a digital low pass filter of order 5 with a frequency cut-off of 35 Hz. The mean was subtracted from each Lead. Classification: The determined classes were “STEMI” (Including STEMI in different locations of the myocardium – anterior, inferior, and lateral); and “Not-STEMI” (Combination of randomly sample, branch blocks, non-specific ST-T changes, and abnormal records – 25% of each). Training and Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10, respectively. A different model was trained and tested for each Lead, using the central 4,500 samples of the records. The last dense layer outputs a probability for each report of being STEMI or Not-STEMI. Lead V2 showed the best overall results. The model was further tested through the same methodology using the best Lead with a subset of the previous data, excluding the unconfirmed STEMI EKG records (Total 7,230 12-lead EKG records for Confirmed Only STEMI dataset). Performance metrics were reported for each experiment and compared.\n \n \n \n Combined STEMI data: Accuracy: 91.2%; Sensitivity: 89.6%; Specificity: 92.9%. Confirmed STEMI Only dataset: Accuracy: 92.4%; Sensitivity: 93.4%; Specificity: 91.4% (Figure 1).\n \n \n \n By assiduously improving the quality of the model's input, we continue to assess our algorithm's performance and reliability for future clinical validation as a potential remote monitoring and early STEMI detection device.\n \n \n \n Type of funding sources: None.\n","PeriodicalId":284912,"journal":{"name":"EMJ Cardiology","volume":"33 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"EMJ Cardiology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.33590/emjcardiol/10098409","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Over decades, efforts to shave off life-saving minutes from ST-Elevated Myocardial Infarction (STEMI) care centred on reducing door-to-needle and door-to-balloon times. We firmly believe that symptom-to-balloon time should prove a better focus to this end. Challenges come with this goal as it heavily relies on a patient's perception and initiative to seek care, which we deem intelligent and wearable Artificial Intelligence (AI)-driven Single Lead EKG technologies as an attractive solution in modern-day cardiology. To provide an accurate, accessible, and cost-effective AI-driven Single Lead STEMI detection algorithm that can be embedded into wearable devices and employed in a self-administered fashion. Database: EKG records from Mexico, Colombia, Argentina, and Brazil from April 2014 to December 2019. Dataset: A total of 11,567 12-lead EKG records of 10[s] length with a sampling frequency of 500 Hz, including the following balanced classes: angiographically confirmed and unconfirmed STEMI, branch blocks, non-specific ST-T abnormalities, normal and abnormal (200+ CPT codes, excluding those mentioned above). Cardiologists manually checked the label of each record to ensure precision. Pre-processing: We discard the first and last 250 samples as they may contain a standardisation pulse. The study applied a digital low pass filter of order 5 with a frequency cut-off of 35 Hz. The mean was subtracted from each Lead. Classification: The determined classes were “STEMI” (Including STEMI in different locations of the myocardium – anterior, inferior, and lateral); and “Not-STEMI” (Combination of randomly sample, branch blocks, non-specific ST-T changes, and abnormal records – 25% of each). Training and Testing: A 1-D Convolutional Neural Network was trained and tested with a dataset proportion of 90/10, respectively. A different model was trained and tested for each Lead, using the central 4,500 samples of the records. The last dense layer outputs a probability for each report of being STEMI or Not-STEMI. Lead V2 showed the best overall results. The model was further tested through the same methodology using the best Lead with a subset of the previous data, excluding the unconfirmed STEMI EKG records (Total 7,230 12-lead EKG records for Confirmed Only STEMI dataset). Performance metrics were reported for each experiment and compared. Combined STEMI data: Accuracy: 91.2%; Sensitivity: 89.6%; Specificity: 92.9%. Confirmed STEMI Only dataset: Accuracy: 92.4%; Sensitivity: 93.4%; Specificity: 91.4% (Figure 1). By assiduously improving the quality of the model's input, we continue to assess our algorithm's performance and reliability for future clinical validation as a potential remote monitoring and early STEMI detection device. Type of funding sources: None.
人工智能引导的单导联心电图可能是缩短st段升高心肌梗死从症状到球囊时间的游戏规则改变者
几十年来,缩短st段抬高型心肌梗死(STEMI)抢救时间的努力主要集中在减少上门到针头和上门到气球的时间。我们坚信,从症状到气球的时间应该证明是为此目的更好的重点。这一目标带来了挑战,因为它严重依赖于患者的感知和主动寻求护理,我们认为智能和可穿戴人工智能(AI)驱动的单导联心电图技术是现代心脏病学中一个有吸引力的解决方案。提供一种准确、可获取且具有成本效益的人工智能驱动的单导联STEMI检测算法,该算法可嵌入可穿戴设备并以自我管理的方式使用。数据库:2014年4月至2019年12月墨西哥、哥伦比亚、阿根廷和巴西的心电图记录。数据集:共有11,567条长度为10[s]的12导联心电图记录,采样频率为500 Hz,包括以下平衡类别:血管造影确认和未确认的STEMI,分支阻滞,非特异性ST-T异常,正常和异常(200+ CPT代码,不包括上述代码)。心脏病专家手动检查每条记录的标签,以确保准确性。预处理:我们丢弃第一个和最后250个样品,因为它们可能包含一个标准化脉冲。该研究应用了一个5阶的数字低通滤波器,频率截止为35hz。从每个Lead中减去平均值。分类:确定的类型为“STEMI”(包括心肌不同部位的STEMI——前、下、外侧);和“非stemi”(随机样本、分支阻滞、非特异性ST-T变化和异常记录的组合-每种占25%)。训练和测试:1-D卷积神经网络分别以90/10的数据集比例进行训练和测试。使用记录的中心4500个样本,为每个Lead训练和测试了不同的模型。最后一个密集层输出每个报告为STEMI或非STEMI的概率。铅V2的整体效果最好。该模型通过相同的方法进一步测试,使用最佳导联和先前数据的子集,不包括未经确认的STEMI心电图记录(仅确认STEMI数据集的12导联心电图记录总数为7,230)。报告每个实验的性能指标并进行比较。STEMI联合数据:准确率:91.2%;灵敏度:89.6%;特异性:92.9%。经证实的STEMI数据集:准确率:92.4%;灵敏度:93.4%;特异性:91.4%(图1)。通过努力提高模型输入的质量,我们继续评估算法的性能和可靠性,以用于未来的临床验证,作为潜在的远程监测和早期STEMI检测设备。资金来源类型:无。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信