利用深度学习算法从心电图中同时识别左右心室功能障碍。

Using Deep-Learning Algorithms to Simultaneously Identify Right and Left Ventricular Dysfunction From the Electrocardiogram.

机构信息

Mount Sinai Clinical Intelligence Center, Icahn School of Medicine at Mount Sinai, New York, New York, USA; The Hasso Plattner Institute for Digital Health at Mount Sinai, Icahn School of Medicine at Mount Sinai, New York, New York, USA; Department of Genetics and Genomic Sciences, Icahn School of Medicine at Mount Sinai, New York, New York, USA.

出版信息

JACC Cardiovasc Imaging. 2022 Mar;15(3):395-410. doi: 10.1016/j.jcmg.2021.08.004. Epub 2021 Oct 13.

DOI:10.1016/j.jcmg.2021.08.004

PMID:34656465

原文链接:https://pmc.ncbi.nlm.nih.gov/articles/PMC8917975/

Abstract

OBJECTIVES

This study sought to develop DL models capable of comprehensively quantifying left and right ventricular dysfunction from ECG data in a large, diverse population.

BACKGROUND

Rapid evaluation of left and right ventricular function using deep learning (DL) on electrocardiograms (ECGs) can assist diagnostic workflow. However, DL tools to estimate right ventricular (RV) function do not exist, whereas those to estimate left ventricular (LV) function are restricted to quantification of very low LV function only.

METHODS

A multicenter study was conducted with data from 5 New York City hospitals: 4 for internal testing and 1 serving as external validation. We created novel DL models to classify left ventricular ejection fraction (LVEF) into categories derived from the latest universal definition of heart failure, estimate LVEF through regression, and predict a composite outcome of either RV systolic dysfunction or RV dilation.

RESULTS

We obtained echocardiogram LVEF estimates for 147,636 patients paired to 715,890 ECGs. We used natural language processing (NLP) to extract RV size and systolic function information from 404,502 echocardiogram reports paired to 761,510 ECGs for 148,227 patients. For LVEF classification in internal testing, area under curve (AUC) at detection of LVEF ≤40%, 40% < LVEF ≤50%, and LVEF >50% was 0.94 (95% CI: 0.94-0.94), 0.82 (95% CI: 0.81-0.83), and 0.89 (95% CI: 0.89-0.89), respectively. For external validation, these results were 0.94 (95% CI: 0.94-0.95), 0.73 (95% CI: 0.72-0.74), and 0.87 (95% CI: 0.87-0.88). For regression, the mean absolute error was 5.84% (95% CI: 5.82%-5.85%) for internal testing and 6.14% (95% CI: 6.13%-6.16%) in external validation. For prediction of the composite RV outcome, AUC was 0.84 (95% CI: 0.84-0.84) in both internal testing and external validation.

CONCLUSIONS

DL on ECG data can be used to create inexpensive screening, diagnostic, and predictive tools for both LV and RV dysfunction. Such tools may bridge the applicability of ECGs and echocardiography and enable prioritization of patients for further interventions for either sided failure progressing to biventricular disease.

摘要

目的

本研究旨在开发能够从大型多样化人群的心电图数据中全面量化左、右心室功能的深度学习（DL）模型。

背景

使用深度学习（DL）在心电图（ECG）上快速评估左、右心室功能可以辅助诊断工作流程。然而，用于评估右心室（RV）功能的 DL 工具尚不存在，而用于评估左心室（LV）功能的工具仅局限于仅对非常低的 LV 功能进行量化。

方法

这项多中心研究的数据来自纽约市的 4 家医院：4 家用于内部测试，1 家用于外部验证。我们创建了新的深度学习（DL）模型，用于将左心室射血分数（LVEF）分类为最新心力衰竭通用定义中的类别，通过回归估计 LVEF，并预测 RV 收缩功能障碍或 RV 扩张的复合结果。

结果

我们获得了 147636 名患者的超声心动图 LVEF 估计值，并与 715890 份心电图配对。我们使用自然语言处理（NLP）从 148227 名患者的 404502 份超声心动图报告中提取 RV 大小和收缩功能信息，并与 761510 份心电图配对。在内部测试中，用于检测 LVEF≤40%、40%＜LVEF≤50%和 LVEF＞50%的曲线下面积（AUC）分别为 0.94（95%CI：0.94-0.94）、0.82（95%CI：0.81-0.83）和 0.89（95%CI：0.89-0.89）。在外部验证中，这些结果分别为 0.94（95%CI：0.94-0.95）、0.73（95%CI：0.72-0.74）和 0.87（95%CI：0.87-0.88）。对于回归，内部测试的平均绝对误差为 5.84%（95%CI：5.82%-5.85%），外部验证的平均绝对误差为 6.14%（95%CI：6.13%-6.16%）。对于 RV 复合结果的预测，内部测试和外部验证的 AUC 分别为 0.84（95%CI：0.84-0.84）。