利用心电图检测贫血的深度学习算法：一项回顾性、多中心研究。

A deep learning algorithm to detect anaemia with ECGs: a retrospective, multicentre study.

机构信息

Department of Emergency Medicine, Mediplex Sejong Hospital, Incheon, South Korea; Artificial Intelligence and Big Data Research Center, Sejong Medical Research Institute, Bucheon, South Korea; Medical research team, Medical AI, Seoul, South Korea.

Medical Research and Development Center, Bodyfriend, Seoul, South Korea.

出版信息

Lancet Digit Health. 2020 Jul;2(7):e358-e367. doi: 10.1016/S2589-7500(20)30108-4. Epub 2020 Jun 23.

DOI:10.1016/S2589-7500(20)30108-4

PMID:33328095

Abstract

BACKGROUND

Anaemia is an important health-care burden globally, and screening for anaemia is crucial to prevent multi-organ injury, irreversible complications, and life-threatening adverse events. We aimed to establish whether a deep learning algorithm (DLA) that enables non-invasive anaemia screening from electrocardiograms (ECGs) might improve the detection of anaemia.

METHODS

We did a retrospective, multicentre, diagnostic study in which a DLA was developed using ECGs and then internally and externally validated. We used data from two hospitals, Sejong General Hospital (hospital A) and Mediplex Sejong Hospital (hospital B), in South Korea. Data from hospital A was for DLA development and internal validation, and data from hospital B was for external validation. We included individuals who had at least one ECG with a haemoglobin measurement within 1 h of the index ECG and excluded individuals with missing demographic, electrocardiographic, or haemoglobin information. Three types of DLA were developed with 12-lead, 6-lead (limb lead), and single-lead (lead I) ECGs to detect haemoglobin concentrations of 10 g/dL or less. The DLA was built by a convolutional neural network and used 500-Hz raw ECG, age, and sex as input data.

FINDINGS

The study period ran from Oct 1, 2016, to Sept 30, 2019, in hospital A and March 1, 2017, to Sept 30, 2019, in hospital B. 40 513 patients at hospital A and 4737 patients at hospital B were eligible for inclusion. We excluded 281 patients at hospital A and 72 patients at hospital B because of missing values for clinical information and ECG data. The development dataset comprised 57 435 ECGs from 31 898 patients, and the algorithm was internally validated with 7974 ECGs from 7974 patients. The external validation dataset included 4665 ECGs from 4665 patients. 586 (internal) and 194 (external) patients within the combined dataset were found to be anaemic. During internal and external validation, the area under the receiver operating characteristics curve (AUROC) of the DLA using a 12-lead ECG for detecting anaemia was 0·923 for internal validation and 0·901 for external validation. Using a 90% sensitivity operating point for the development data, the sensitivity, specificity, negative predictive value, and positive predictive value of internal validation were 89·8%, 81·5%, 99·4%, and 20·0%, respectively, and those of external validation were 86·1%, 76·2%, 99·2%, and 13·5%, respectively. The DLA focused on the QRS complex for deciding the presence of anaemia in a sensitivity map. The AUROCs of DLAs using 6 leads and a single lead were in the range of 0·841-0·890.

INTERPRETATION

In this study, using raw ECG data, a DLA accurately detected anaemia. The application of artificial intelligence to ECGs could enable screening for anaemia.

FUNDING

None.

摘要

背景

贫血是全球范围内一个重要的健康负担，筛查贫血对于预防多器官损伤、不可逆并发症和危及生命的不良事件至关重要。我们旨在确定一种能够通过心电图（ECG）进行非侵入性贫血筛查的深度学习算法（DLA）是否可以提高贫血的检测率。

方法

我们进行了一项回顾性、多中心、诊断研究，该研究使用 ECG 开发了一种 DLA，并对其进行了内部和外部验证。我们使用了来自韩国世宗综合医院（医院 A）和 Mediplex 世宗医院（医院 B）的两个医院的数据。医院 A 的数据用于 DLA 的开发和内部验证，医院 B 的数据用于外部验证。我们纳入了至少有一次心电图和 1 h 内血红蛋白测量值的个体，并排除了缺失人口统计学、心电图或血红蛋白信息的个体。该 DLA 使用 12 导联、6 导联（肢体导联）和单导联（导联 I）ECG 开发了三种类型，以检测血红蛋白浓度为 10 g/dL 或更低。该 DLA 通过卷积神经网络构建，并使用 500-Hz 原始 ECG、年龄和性别作为输入数据。

结果

研究期间为 2016 年 10 月 1 日至 2019 年 9 月 30 日在医院 A，以及 2017 年 3 月 1 日至 2019 年 9 月 30 日在医院 B。医院 A 有 40513 名患者和医院 B 有 4737 名患者符合纳入标准。我们排除了医院 A 的 281 名患者和医院 B 的 72 名患者，因为临床信息和心电图数据缺失。发展数据集包括来自 31898 名患者的 57435 次 ECG，算法通过来自 7974 名患者的 7974 次 ECG 进行内部验证。外部验证数据集包括来自 4665 名患者的 4665 次 ECG。在联合数据集内，有 586 名（内部）和 194 名（外部）患者被发现患有贫血。在内部和外部验证中，使用 12 导联 ECG 检测贫血的 DLA 的接收者操作特征曲线（AUROC）的 AUC 分别为 0.923 和 0.901。在开发数据中使用 90%的灵敏度工作点，内部验证的灵敏度、特异性、阴性预测值和阳性预测值分别为 89.8%、81.5%、99.4%和 20.0%，外部验证的灵敏度、特异性、阴性预测值和阳性预测值分别为 86.1%、76.2%、99.2%和 13.5%。该 DLA 专注于 QRS 复合体，用于在灵敏度图中判断是否存在贫血。使用 6 导联和单导联的 DLA 的 AUROCs 范围为 0.841-0.890。