AI-enhanced recognition of occlusions in acute coronary syndrome (AERO-ACS): a retrospective study.

IF 2 4区医学 Q3 CARDIAC & CARDIOVASCULAR SYSTEMS

Coronary artery disease Pub Date : 2025-08-07 DOI:10.1097/MCA.0000000000001555

James W H Choi, Vincent Torelli, Alex Silverman, Sara Saravia Diaz, Darren Kong, Esha Vaish, Luka Katic, Alex Nagourney, Zara Khan, Lexi Robbins, Sean Pinney, Nitin Barman, Serdar Farhan

{"title":"AI-enhanced recognition of occlusions in acute coronary syndrome (AERO-ACS): a retrospective study.","authors":"James W H Choi, Vincent Torelli, Alex Silverman, Sara Saravia Diaz, Darren Kong, Esha Vaish, Luka Katic, Alex Nagourney, Zara Khan, Lexi Robbins, Sean Pinney, Nitin Barman, Serdar Farhan","doi":"10.1097/MCA.0000000000001555","DOIUrl":null,"url":null,"abstract":"Background: Artificial intelligence (AI) augmentation of ECG assessment has significant potential to improve patient outcomes in acute coronary syndrome.Objective: We sought to evaluate the performance of a novel AI device (PMCardio) in assessing angiographic occlusion myocardial infarction (OMI) and predicting clinical outcomes.Methods: We used a 1-year retrospective cohort of angiographic data from patients presenting with ST-elevation myocardial infarction (STEMI) and non-ST-elevation myocardial infarction (NSTEMI). The device analyzed precatheterization ECGs to identify OMI, defined as a culprit vessel with thrombolysis In myocardial infarction (TIMI) 0-2 flow or TIMI 3 flow and peak cardiac troponin I > 10.0 ng/ml.Results: A total of 217 patients were included: 72 STEMI (32%) and 145 NSTEMI (65%). Angiographic OMI was confirmed in 60 (83%) STEMI and 51 (35%) NSTEMI cases. The AI model achieved a sensitivity of 86.5%, specificity of 82.2%, and an area under the curve of 0.84. Traditional STEMI criteria had a sensitivity of 54.1% and a specificity of 88.7%. The AI model was 100% sensitive in detecting STEMI-OMI. The odds ratio for mortality in AI-detected OMI patients was 12.44 (1.56-98.98), unplanned readmissions 1.15 (0.53-2.51), and reduced ejection fraction at 1 year 0.24 (0.26-2.16).Conclusions: The AI model demonstrated higher sensitivity and similar specificity compared with traditional STEMI criteria, improving OMI detection while reducing false positives. These findings suggest potential benefits in triage accuracy and resource utilization, but further prospective validation is needed to determine its clinical impact.","PeriodicalId":10702,"journal":{"name":"Coronary artery disease","volume":" ","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2025-08-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Coronary artery disease","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1097/MCA.0000000000001555","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Background: Artificial intelligence (AI) augmentation of ECG assessment has significant potential to improve patient outcomes in acute coronary syndrome.

Objective: We sought to evaluate the performance of a novel AI device (PMCardio) in assessing angiographic occlusion myocardial infarction (OMI) and predicting clinical outcomes.

Methods: We used a 1-year retrospective cohort of angiographic data from patients presenting with ST-elevation myocardial infarction (STEMI) and non-ST-elevation myocardial infarction (NSTEMI). The device analyzed precatheterization ECGs to identify OMI, defined as a culprit vessel with thrombolysis In myocardial infarction (TIMI) 0-2 flow or TIMI 3 flow and peak cardiac troponin I > 10.0 ng/ml.

Results: A total of 217 patients were included: 72 STEMI (32%) and 145 NSTEMI (65%). Angiographic OMI was confirmed in 60 (83%) STEMI and 51 (35%) NSTEMI cases. The AI model achieved a sensitivity of 86.5%, specificity of 82.2%, and an area under the curve of 0.84. Traditional STEMI criteria had a sensitivity of 54.1% and a specificity of 88.7%. The AI model was 100% sensitive in detecting STEMI-OMI. The odds ratio for mortality in AI-detected OMI patients was 12.44 (1.56-98.98), unplanned readmissions 1.15 (0.53-2.51), and reduced ejection fraction at 1 year 0.24 (0.26-2.16).

Conclusions: The AI model demonstrated higher sensitivity and similar specificity compared with traditional STEMI criteria, improving OMI detection while reducing false positives. These findings suggest potential benefits in triage accuracy and resource utilization, but further prospective validation is needed to determine its clinical impact.

查看原文本刊更多论文

人工智能增强急性冠脉综合征（AERO-ACS）闭塞的识别：一项回顾性研究。

背景：人工智能（AI）增强心电图评估在改善急性冠状动脉综合征患者预后方面具有重要潜力。目的：我们试图评估一种新型人工智能设备（PMCardio）在评估血管造影闭塞性心肌梗死（OMI）和预测临床结果方面的性能。方法：我们对st段抬高型心肌梗死（STEMI）和非st段抬高型心肌梗死（NSTEMI）患者的血管造影数据进行了为期1年的回顾性队列研究。该设备分析导管前心电图来识别OMI， OMI被定义为心肌梗死（TIMI） 0-2流量或TIMI 3流量和心肌肌钙蛋白I峰值峰值10.0 ng/ml时溶栓的罪魁祸首血管。结果：共纳入217例患者：STEMI 72例（32%），NSTEMI 145例（65%）。60例STEMI（83%）和51例NSTEMI（35%）经血管造影证实为OMI。人工智能模型的灵敏度为86.5%，特异度为82.2%，曲线下面积为0.84。传统STEMI标准的敏感性为83.3%，特异性为66.0%。AI模型对STEMI-OMI的检测灵敏度为100%。ai检测到的OMI患者死亡率的优势比为12.44(1.56-98.98)，非计划再入院的优势比为1.15(0.53-2.51)，1年射血分数降低的优势比为0.24（0.26-2.16）。结论：AI模型与传统STEMI标准具有相似的敏感性和更高的特异性，提高了OMI的检测水平，同时减少了假阳性。这些发现表明在分诊准确性和资源利用方面有潜在的好处，但需要进一步的前瞻性验证来确定其临床影响。

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

Coronary artery disease 医学-外周血管病

CiteScore

2.50

自引率

0.00%

发文量

190

审稿时长

6-12 weeks

期刊介绍： Coronary Artery Disease welcomes reports of original research with a clinical emphasis, including observational studies, clinical trials, translational research, novel imaging, pharmacology and interventional approaches as well as advances in laboratory research that contribute to the understanding of coronary artery disease. Each issue of Coronary Artery Disease is divided into four areas of focus: Original Research articles, Review in Depth articles by leading experts in the field, Editorials and Images in Coronary Artery Disease. The Editorials will comment on selected original research published in each issue of Coronary Artery Disease, as well as highlight controversies in coronary artery disease understanding and management. Submitted artcles undergo a preliminary review by the editor. Some articles may be returned to authors without further consideration. Those being considered for publication will undergo further assessment and peer-review by the editors and those invited to do so from a reviewer pool.