Deep learning-based analysis of 12-lead electrocardiograms in school-age children: A proof of concept study

Shuhei Toba ^1* Yoshihide Mitani ^2* Yusuke Sugitani ^3,4 Hiroyuki Ohashi ² Hirofumi Sawada ² Mami Takeoka ² Naoki Tsuboya ² Kazunobu Ohya ² Noriko Yodoya ² Takato Yamasaki ¹ Yuki Nakayama ¹ Hisato Ito ¹ Masahiro Hirayama ² Motoshi Takao ¹

• ¹ Department of Thoracic and Cardiovascular Surgery, Graduate School of Medicine, Mie University, Tsu, Mie, Japan
• ² Department of Pediatrics, Graduate School of Medicine, Mie University, Tsu, Mie, Japan
• ³ Department of Clinical Engineering, Mie University Hospital, Tsu City, Mie, Japan
• ⁴ Department of Electrical and Electronic Engineering, Mie University, Tsu, Mie, Japan

IntroductionThe diagnostic performance of automated analysis of electrocardiograms for screening children with pediatric heart diseases at risk of sudden cardiac death is unknown. In this study, we aimed to develop and validate a deep learning-based model for automated analysis of ECGs in children.MethodsWave data of 12-lead electrocardiograms were transformed into a tensor sizing 2 x 12 x 400 using signal processing methods. A deep learning-based model to classify abnormal electrocardiograms based on age, sex, and the transformed wave data was developed using electrocardiograms performed in patients at the age of 6-18 years during 2003-2006 at a tertiary referral hospital in Japan. Eighty-three percent of the patients were assigned to a training group, and 17% to a test group. The diagnostic performance of the model and a conventional algorithm (ECAPS12C, Nihon Kohden, Japan) for classifying abnormal electrocardiograms were evaluated using the cross-tabulation, McNemar’s test, and decision curve analysis.ResultsWe included 1,842 ECGs performed in 1,062 patients in this study, and 310 electrocardiograms performed in 177 patients were included in the test group. The specificity of the deep learning-based model for detecting abnormal electrocardiograms was not significantly different from that of the conventional algorithm. For detecting electrocardiograms with ST-T abnormality, complete right bundle branch block, and QRS axis abnormality, the specificity of the deep learning-based model was higher than that of the conventional algorithm at the same sensitivity.ConclusionsThe present new deep learning-based method of screening for abnormal electrocardiograms in children showed at least a similar diagnostic performance compared to that of a conventional algorithm. Further studies are warranted to develop an automated analysis of electrocardiograms in school-age children.