小柯机器人

深度神经网络可利用12导联心电图电压数据预测死亡率
2020-05-13 23:50

美国盖辛格医疗中心Brandon K. Fornwalt研究团队提出,深度神经网络可利用12导联心电图电压数据预测死亡率。这一研究成果于2020年5月11日在线发表在国际学术期刊《自然—医学》上。

研究人员认为,深度神经网络(DNN)可以根据心电图电压与时间曲线预测未来的重要临床事件,即1年内全因死亡率。通过使用大型区域卫生系统在34年中收集的心电图(ECG),研究人员使用253,397例患者中获得的1,371,662例12导联静息心电图(其中发生了99,371起事件)来训练了DNN。该模型在168,914名患者的保留测试集中获得了0.88的曲线下面积(AUC),其中发生了14,207个事件。即使在被医生解释为“正常”的大部分心电图患者(n=45,285)中,该模型在预测1年死亡率方面的表现仍然很高(AUC=0.85)。对心脏科医生的盲查表明,这些正常ECG的许多区别特征对于专家审阅者而言并不明显。

最后,Cox比例风险模型显示,在25年的随访期内,两个预测组(心电图术后1年死亡与存活)的风险比为9.5(P <0.005)。这些结果表明,即使在医师认为正常的情况下,深度学习也可以为12导联静息ECG的解释增加实质性预后信息。

据了解,心电图(ECG)是一种广泛使用的医学测试,包括从心脏表面记录收集的电压与时间的变化。

附:英文原文

Title: Prediction of mortality from 12-lead electrocardiogram voltage data using a deep neural network

Author: Sushravya Raghunath, Alvaro E. Ulloa Cerna, Linyuan Jing, David P. vanMaanen, Joshua Stough, Dustin N. Hartzel, Joseph B. Leader, H. Lester Kirchner, Martin C. Stumpe, Ashraf Hafez, Arun Nemani, Tanner Carbonati, Kipp W. Johnson, Katelyn Young, Christopher W. Good, John M. Pfeifer, Aalpen A. Patel, Brian P. Delisle, Amro Alsaid, Dominik Beer, Christopher M. Haggerty, Brandon K. Fornwalt

Issue&Volume: 2020-05-11

Abstract: The electrocardiogram (ECG) is a widely used medical test, consisting of voltage versus time traces collected from surface recordings over the heart1. Here we hypothesized that a deep neural network (DNN) can predict an important future clinical event, 1-year all-cause mortality, from ECG voltage–time traces. By using ECGs collected over a 34-year period in a large regional health system, we trained a DNN with 1,169,662 12-lead resting ECGs obtained from 253,397 patients, in which 99,371 events occurred. The model achieved an area under the curve (AUC) of 0.88 on a held-out test set of 168,914 patients, in which 14,207 events occurred. Even within the large subset of patients (n=45,285) with ECGs interpreted as ‘normal’ by a physician, the performance of the model in predicting 1-year mortality remained high (AUC=0.85). A blinded survey of cardiologists demonstrated that many of the discriminating features of these normal ECGs were not apparent to expert reviewers. Finally, a Cox proportional-hazard model revealed a hazard ratio of 9.5 (P<0.005) for the two predicted groups (dead versus alive 1 year after ECG) over a 25-year follow-up period. These results show that deep learning can add substantial prognostic information to the interpretation of 12-lead resting ECGs, even in cases that are interpreted as normal by physicians.

DOI: 10.1038/s41591-020-0870-z

Source: https://www.nature.com/articles/s41591-020-0870-z

Nature Medicine:《自然—医学》,创刊于1995年。隶属于施普林格·自然出版集团,最新IF:87.241
官方网址:https://www.nature.com/nm/
投稿链接:https://mts-nmed.nature.com/cgi-bin/main.plex


本期文章:《自然—医学》:Online/在线发表

分享到:

0