Machine learning-based prediction of acute coronary syndrome using only the pre-hospital 12-lead electrocardiogram

被引：118

作者：

Al-Zaiti S. ^{[1
,2
,3
]}

Besomi L. ^{[4
]}

Bouzid Z. ^{[4
]}

Faramand Z. ^{[1
]}

Frisch S. ^{[1
]}

Martin-Gill C. ^{[2
,5
]}

Gregg R. ^{[6
]}

Saba S. ^{[3
,5
]}

Callaway C. ^{[2
,5
]}

Sejdić E. ^{[4
,7
,8
]}

机构：

[1] Department of Acute & Tertiary Care Nursing, University of Pittsburgh, Pittsburgh, PA

[2] Department of Emergency Medicine, University of Pittsburgh, Pittsburgh, PA

[3] Division of Cardiology, School of Medicine, University of Pittsburgh, Pittsburgh, PA

[4] Department of Electrical and Computer Engineering, University of Pittsburgh, Pittsburgh, PA

[5] University of Pittsburgh Medical Center (UPMC), Pittsburgh, PA

[6] Advanced Algorithms Development Research Center, Philips Healthcare, Andover, MA

[7] Department of Biomedical Informatics, University of Pittsburgh, Pittsburgh, PA

[8] Department of Intelligent Systems, University of Pittsburgh, Pittsburgh, PA

来源：

Nature Communications | / 11卷 / 1期

基金：

美国国家卫生研究院;

关键词：

D O I：

10.1038/s41467-020-17804-2

中图分类号：

学科分类号：

摘要：

Prompt identification of acute coronary syndrome is a challenge in clinical practice. The 12-lead electrocardiogram (ECG) is readily available during initial patient evaluation, but current rule-based interpretation approaches lack sufficient accuracy. Here we report machine learning-based methods for the prediction of underlying acute myocardial ischemia in patients with chest pain. Using 554 temporal-spatial features of the 12-lead ECG, we train and test multiple classifiers on two independent prospective patient cohorts (n = 1244). While maintaining higher negative predictive value, our final fusion model achieves 52% gain in sensitivity compared to commercial interpretation software and 37% gain in sensitivity compared to experienced clinicians. Such an ultra-early, ECG-based clinical decision support tool, when combined with the judgment of trained emergency personnel, would help to improve clinical outcomes and reduce unnecessary costs in patients with chest pain. © 2020, The Author(s).

引用

共 43 条

[1]

Benjamin E.J., Et al., Heart Disease and Stroke Statistics—2018 update: a report from the American Heart Association, Circulation, 137, pp. e67-e492, (2018)

[2]

Falk E., Nakano M., Bentzon J.F., Finn A.V., Virmani R., Update on acute coronary syndromes: the pathologists’ view, Eur. Heart J., 34, pp. 719-728, (2013)

[3]

Kumar A., Cannon C.P., Acute coronary syndromes: diagnosis and management, part I, Mayo Clin. Proc., 84, pp. 917-938, (2009)

[4]

Lusis A.J., Atherosclerosis, Nature, 407, pp. 233-241, (2000)

[5]

Nabel E.G., Braunwald E., A tale of coronary artery disease and myocardial infarction, N. Engl. J. Med., 366, pp. 54-63, (2012)

[6]

Lukas A., Antzelevitch C., Differences in the electrophysiological response of canine ventricular epicardium and endocardium to ischemia. Role of the transient outward current, Circulation, 88, pp. 2903-2915, (1993)

[7]

Al-Zaiti S.S., Callaway C.W., Kozik T.M., Carey M.G., Pelter M.M., Clinical utility of ventricular repolarization dispersion for real ‐ time detection of non ‐ ST elevation myocardial infarction in emergency departments, J. Am. Heart Assoc., 4, (2015)

[8]

Al-Zaiti S., Et al., Evaluation of beat-to-beat ventricular repolarization lability from standard 12-Lead ECG during acute myocardial ischemia, J. Electrocardiol., 50, pp. 717-724, (2017)

[9]

Al-Zaiti S., Et al., Spatial indices of repolarization correlate with non-ST elevation myocardial ischemia in patients with chest pain, Med. Biol. Eng. Comput., 56, pp. 1-12, (2018)

[10]

Baxt W.G., Skora J., Prospective validation of artificial neural network trained to identify acute myocardial infarction, Lancet, 347, pp. 12-15, (1996)

← 1 2 3 4 5 →