University Hospital of Basel Reports Findings in Heart Disease (Enhancing the di agnosis of functionally relevant coronary artery disease with machine learning)
University Hospital of Basel Reports Findings in Heart Disease (Enhancing the di agnosis of functionally relevant coronary artery disease with machine learning)
巴塞尔大学医院报告心脏病的发现（通过机器学习提高功能相关冠心病的诊断）
扫码查看
点击上方二维码区域，可以放大扫码查看
摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-心脏病和糖尿病的新研究-心脏病是一篇报道的主题。根据NewsRx记者在瑞士巴塞尔的新闻报道，研究表明：“功能重建的冠状动脉疾病(fCAD)可导致过早死亡或非致死性急性心肌梗死，其早期发现是医学上最重要的一环。”这项研究的财政支持来自Alfried Krupp von Bohlen und Halba CH-Stiftung。新闻记者从巴塞尔大学医院的研究中获得了一句话：“经典检测方法的诊断准确性有限，或者患者暴露在可能有害的辐射中。在这里，我们展示了Mac Hine Learning(ML)在预测ST RESS诱导的fCAD方面如何优于心脏病学家，就接收器操作特征下面积而言（AUROC：0.71 vs 0.64.”我们提出了两种ML方法，第一种方法使用八个静态临床变量，第二种方法利用运动负荷试验的心电图信号。在fC AD的目标测试后概率<15%时，ML有助于成像程序与心脏病专家的判断相比减少15-17%。预测性能在内部时间数据和外部数据上得到验证。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Heart Disorders and Di seases - Heart Disease is the subject of a report. According to news reporting f rom Basel, Switzerland, by NewsRx journalists, research stated, "Functionally re levant coronary artery disease (fCAD) can result in premature death or nonfatal acute myocardial infarction. Its early detection is a fundamentally important ta sk in medicine." Financial support for this research came from Alfried Krupp von Bohlen und Halba ch-Stiftung. The news correspondents obtained a quote from the research from the University H ospital of Basel, "Classical detection approaches suffer from limited diagnostic accuracy or expose patients to possibly harmful radiation. Here we show how mac hine learning (ML) can outperform cardiologists in predicting the presence of st ress-induced fCAD in terms of area under the receiver operating characteristic ( AUROC: 0.71 vs. 0.64, p = 4.0E-13). We present two ML approaches, the first usin g eight static clinical variables, whereas the second leverages electrocardiogra m signals from exercise stress testing. At a target post-test probability for fC AD of <15%, ML facilitates a potential reducti on of imaging procedures by 15-17% compared to the cardiologist's judgement. Predictive performance is validated on an internal temporal data spli t as well as externally."
Key words
Basel/Switzerland/Europe/Angiology/A rterial Occlusive Diseases/Arteriosclerosis/Cardiology/Cardiovascular Disease s and Conditions/Coronary Artery/Coronary Artery Disease/Cyborgs/Diagnostics and Screening/Emerging Technologies/Health and Medicine/Heart Disease/Heart Disorders and Diseases/Machine Learning/Myocardial Ischemia
NETL
NSTL