Re-engineering the clinical approach to suspected cardiac chest pain assessment in the emergency department by expediting research evidence to practice using artificial intelligence. (RAPIDx AI)—a cluster randomized study design

IF 3.7 2区医学 Q1 CARDIAC & CARDIOVASCULAR SYSTEMS

American heart journal Pub Date : 2025-02-22 DOI:10.1016/j.ahj.2025.02.016

Ehsan Khan MBBS, MMed (Clin Epi) , Kristina Lambrakis BSc , Tom Briffa PhD , Louise A Cullen MBBS, PhD , Jonathon Karnon , Cynthia Papendick MBBS , Stephen Quinn PhD , Phil Tideman , Anton Van Den Hengel , Johan Verjans , Derek P Chew MBBS, MPH, PhD

{"title":"Re-engineering the clinical approach to suspected cardiac chest pain assessment in the emergency department by expediting research evidence to practice using artificial intelligence. (RAPIDx AI)—a cluster randomized study design","authors":"Ehsan Khan MBBS, MMed (Clin Epi) , Kristina Lambrakis BSc , Tom Briffa PhD , Louise A Cullen MBBS, PhD , Jonathon Karnon , Cynthia Papendick MBBS , Stephen Quinn PhD , Phil Tideman , Anton Van Den Hengel , Johan Verjans , Derek P Chew MBBS, MPH, PhD","doi":"10.1016/j.ahj.2025.02.016","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Clinical work-up for suspected cardiac chest pain is resource intensive. Despite expectations, high-sensitivity cardiac troponin assays have not made decision making easier. The impact of recently validated rapid triage protocols including the 0-hour/1-hour hs-cTn protocols on care and outcomes may be limited by the heterogeneity in interpretation of troponin profiles by clinicians. We have developed machine learning (ML) models which digitally phenotype myocardial injury and infarction with a high predictive performance and provide accurate risk assessment among patients presenting to EDs with suspected cardiac symptoms. The use of these models may support clinical decision-making and allow the synthesis of an evidence base particularly in non-T1MI patients however prospective validation is required.</div></div><div><h3>Objective</h3><div>We propose that integrating validated real-time artificial intelligence (AI) methods into clinical care may better support clinical decision-making and establish the foundation for a self-learning health system.</div></div><div><h3>Design</h3><div>This prospective, multicenter, open-label, cluster-randomized clinical trial within blinded endpoint adjudication across 12 hospitals (n = 20,000) will randomize sites to the clinical decision-support tool or continue current standard of care. The clinical decision support tool will utilize ML models to provide objective patient-specific diagnostic probabilities (ie, likelihood for Type 1 myocardial infarction [MI] versus Type 2 MI/Acute Myocardial Injury versus Chronic Myocardial Injury etc.) and prognostic assessments. The primary outcome is the composite of cardiovascular mortality, new or recurrent MI and unplanned hospital re-admission at 12 months post index presentation.</div></div><div><h3>Summary</h3><div>Supporting clinicians with a decision support tool that utilizes AI has the potential to provide better diagnostic and prognostic assessment thereby improving clinical efficiency and establish a self-learning health system continually improving risk assessment, quality and safety.</div></div><div><h3>Trial registration</h3><div>ANZCTR, Registration Number: ACTRN12620001319965, <span><span>https://www.anzctr.org.au/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":7868,"journal":{"name":"American heart journal","volume":"285 ","pages":"Pages 106-118"},"PeriodicalIF":3.7000,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"American heart journal","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0002870325000547","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CARDIAC & CARDIOVASCULAR SYSTEMS","Score":null,"Total":0}

引用次数: 0

Abstract

Background

Clinical work-up for suspected cardiac chest pain is resource intensive. Despite expectations, high-sensitivity cardiac troponin assays have not made decision making easier. The impact of recently validated rapid triage protocols including the 0-hour/1-hour hs-cTn protocols on care and outcomes may be limited by the heterogeneity in interpretation of troponin profiles by clinicians. We have developed machine learning (ML) models which digitally phenotype myocardial injury and infarction with a high predictive performance and provide accurate risk assessment among patients presenting to EDs with suspected cardiac symptoms. The use of these models may support clinical decision-making and allow the synthesis of an evidence base particularly in non-T1MI patients however prospective validation is required.

Objective

We propose that integrating validated real-time artificial intelligence (AI) methods into clinical care may better support clinical decision-making and establish the foundation for a self-learning health system.

Design

This prospective, multicenter, open-label, cluster-randomized clinical trial within blinded endpoint adjudication across 12 hospitals (n = 20,000) will randomize sites to the clinical decision-support tool or continue current standard of care. The clinical decision support tool will utilize ML models to provide objective patient-specific diagnostic probabilities (ie, likelihood for Type 1 myocardial infarction [MI] versus Type 2 MI/Acute Myocardial Injury versus Chronic Myocardial Injury etc.) and prognostic assessments. The primary outcome is the composite of cardiovascular mortality, new or recurrent MI and unplanned hospital re-admission at 12 months post index presentation.

Summary

Supporting clinicians with a decision support tool that utilizes AI has the potential to provide better diagnostic and prognostic assessment thereby improving clinical efficiency and establish a self-learning health system continually improving risk assessment, quality and safety.

Trial registration

ANZCTR, Registration Number: ACTRN12620001319965, https://www.anzctr.org.au/.

查看原文本刊更多论文

通过使用人工智能加速研究证据到实践，重新设计急诊科疑似心源性胸痛评估的临床方法。（RAPIDx AI）——一项集群随机研究设计。

背景：疑似心源性胸痛的临床检查是资源密集的。尽管期望如此，高灵敏度的心肌肌钙蛋白测定并没有使决策更容易。最近验证的快速分诊方案（包括0小时/1小时hs-cTn方案）对护理和结果的影响可能受到临床医生对肌钙蛋白谱解释的异质性的限制。我们开发了机器学习（ML）模型，该模型对心肌损伤和梗死进行数字化表型分析，具有很高的预测性能，并为出现疑似心脏症状的急诊科患者提供准确的风险评估。这些模型的使用可以支持临床决策，并允许合成证据基础，特别是在非t1mi患者中，但需要前瞻性验证。目的：将经过验证的实时人工智能（AI）方法整合到临床护理中，可以更好地支持临床决策，为自主学习的卫生系统奠定基础。设计：这项前瞻性、多中心、开放标签、集群随机临床试验在12家医院（n=20,000）中进行盲法终点裁决，将随机选择临床决策支持工具或继续当前的标准护理。临床决策支持工具将利用ML模型提供客观的患者特异性诊断概率（即1型心肌梗死与2型心肌梗死的可能性/急性心肌损伤与慢性心肌损伤等）和预后评估。主要结局是心血管死亡率、新发或复发性心肌梗死以及指数出现后12个月意外再次住院的综合结果。总结：为临床医生提供利用人工智能的决策支持工具，有可能提供更好的诊断和预后评估，从而提高临床效率，建立一个自我学习的卫生系统，不断改进风险评估、质量和安全性。试验注册号：ANZCTR，注册号：ACTRN12620001319965， https://www.anzctr.org.au/。

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

American heart journal 医学-心血管系统

CiteScore

8.20

自引率

2.10%

发文量

214

审稿时长

38 days

期刊介绍： The American Heart Journal will consider for publication suitable articles on topics pertaining to the broad discipline of cardiovascular disease. Our goal is to provide the reader primary investigation, scholarly review, and opinion concerning the practice of cardiovascular medicine. We especially encourage submission of 3 types of reports that are not frequently seen in cardiovascular journals: negative clinical studies, reports on study designs, and studies involving the organization of medical care. The Journal does not accept individual case reports or original articles involving bench laboratory or animal research.