Deep Learning Models for Predicting Left Heart Abnormalities From Single-Lead Electrocardiogram for the Development of Wearable Devices

被引：7

作者：

Sato, Masataka ^{[1
]}

Kodera, Satoshi ^{[1
]}

Setoguchi, Naoto ^{[2
]}

Tanabe, Kengo ^{[2
]}

Kushida, Shunichi ^{[3
]}

Kanda, Junji ^{[3
]}

Saji, Mike ^{[4
]}

Nanasato, Mamoru ^{[4
]}

Maki, Hisataka ^{[5
]}

Fujita, Hideo ^{[5
]}

Kato, Nahoko ^{[6
]}

Watanabe, Hiroyuki ^{[6
]}

Suzuki, Minami ^{[7
]}

Takahashi, Masao ^{[7
]}

Sawada, Naoko ^{[8
]}

Yamasaki, Masao ^{[8
]}

Sawano, Shinnosuke ^{[1
]}

Katsushika, Susumu ^{[1
]}

Shinohara, Hiroki ^{[1
]}

Takeda, Norifumi ^{[1
]}

Fujiu, Katsuhito ^{[1
,9
]}

Daimon, Masao ^{[1
]}

Akazawa, Hiroshi ^{[1
]}

Morita, Hiroyuki ^{[1
]}

Komuro, Issei ^{[1
]}

机构：

[1] Univ Tokyo Hosp, Dept Cardiovasc Med, 7-3-1 Hongo,Bunkyo Ku, Tokyo, 1138655, Japan

[2] Mitsui Mem Hosp, Div Cardiol, Tokyo, Japan

[3] Asahi Gen Hosp, Dept Cardiovasc Med, Asahi, Japan

[4] Sakakibara Heart Inst, Dept Cardiol, Fuchu, Japan

[5] Jichi Med Univ, Saitama Med Ctr, Div Cardiovasc Med, Saitama, Japan

[6] Tokyo Bay Urayasu Ichikawa Med Ctr, Dept Cardiol, Urayasu, Japan

[7] JR Tokyo Gen Hosp, Dept Cardiol, Tokyo, Japan

[8] NTT Med Ctr Tokyo, Dept Cardiol, Tokyo, Japan

[9] Univ Tokyo, Dept Adv Cardiol, Tokyo, Japan

来源：

CIRCULATION JOURNAL | 2024年 / 88卷 / 01期

关键词：

Key Words: Artificial intelligence; Electrocardiography; Single-lead ECG; Wearable device; LEFT-VENTRICULAR HYPERTROPHY; LEFT ATRIAL SIZE; ARTIFICIAL-INTELLIGENCE; SYSTOLIC DYSFUNCTION; FAILURE; RISK; CLASSIFICATION; ASSOCIATION; ENLARGEMENT; PREVALENCE;

D O I：

10.1253/circj.CJ-23-0216

中图分类号：

R5 [内科学];

学科分类号：

1002 ; 100201 ;

摘要：

Background: Left heart abnormalities are risk factors for heart failure. However, echocardiography is not always available. Electrocardiograms (ECGs), which are now available from wearable devices, have the potential to detect these abnormalities. Nevertheless, whether a model can detect left heart abnormalities from single Lead I ECG data remains unclear.Methods and Results: We developed Lead I ECG models to detect low ejection fraction (EF), wall motion abnormality, left ventricular hypertrophy (LVH), left ventricular dilatation, and left atrial dilatation. We used a dataset comprising 229,439 paired sets of ECG and echocardiography data from 8 facilities, and validated the model using external verification with data from 2 facilities. The area under the receiver operating characteristic curves of our model was 0.913 for low EF, 0.832 for wall motion abnormality, 0.797 for LVH, 0.838 for left ventricular dilatation, and 0.802 for left atrial dilatation. In interpretation tests with 12 cardiologists, the accuracy of the model was 78.3% for low EF and 68.3% for LVH. Compared with cardiologists who read the 12-lead ECGs, the model's performance was superior for LVH and similar for low EF.Conclusions: From a multicenter study dataset, we developed models to predict left heart abnormalities using Lead I on the ECG. The Lead I ECG models show superior or equivalent performance to cardiologists using 12-lead ECGs.

引用

页码：146 / +

页数：20

共 43 条

[41]

YOUDEN WJ, 1950, BIOMETRICS, V6, P172, DOI 10.1002/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO

[42]

2-3

[43] Deep learning assessment of left ventricular hypertrophy based on electrocardiogram [J].

Zhao, Xiaoli ;

Huang, Guifang ;

Wu, Lin ;

Wang, Min ;

He, Xuemin ;

Wang, Jyun-Rong ;

Zhou, Bin ;

Liu, Yong ;

Lin, Yesheng ;

Liu, Dinghui ;

Yu, Xianguan ;

Liang, Suzhen ;

Tian, Borui ;

Liu, Linxiao ;

Chen, Yanming ;

Qiu, Shuhong ;

Xie, Xujing ;

Han, Lanqing ;

Qian, Xiaoxian .

FRONTIERS IN CARDIOVASCULAR MEDICINE, 2022, 9

← 1 2 3 4 5 →