Deep Learning-Based Identification of Echocardiographic Abnormalities From Electrocardiograms
Background: Heart failure should be diagnosed as early as possible. Although deep learning models can predict one or more echocardiographic findings from electrocardiograms (ECGs), such analyses are not comprehensive. Objectives: This study aimed to develop a deep learning model for comprehensive pr...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | JACC: Asia |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772374724004241 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841553768154398720 |
|---|---|
| author | Goro Fujiki, MD Satoshi Kodera, MD, PhD Naoto Setoguchi, MD Kengo Tanabe, MD, PhD Kotaro Miyaji, MD, PhD Shunichi Kushida, MD, PhD Mike Saji, MD, PhD Mamoru Nanasato, MD, PhD Hisataka Maki, MD, PhD Hideo Fujita, MD, PhD Nahoko Kato, MD, PhD Hiroyuki Watanabe, MD, PhD Minami Suzuki, MD Masao Takahashi, MD, PhD Naoko Sawada, MD, PhD Jiro Ando, MD Masataka Sato, MD Shinnosuke Sawano, MD, PhD Susumu Katsushika, MD, PhD Hiroki Shinohara, MD, PhD Norifumi Takeda, MD, PhD Katsuhito Fujiu, MD, PhD Hiroshi Akazawa, MD, PhD Hiroyuki Morita, MD, PhD Issei Komuro, MD, PhD |
| author_facet | Goro Fujiki, MD Satoshi Kodera, MD, PhD Naoto Setoguchi, MD Kengo Tanabe, MD, PhD Kotaro Miyaji, MD, PhD Shunichi Kushida, MD, PhD Mike Saji, MD, PhD Mamoru Nanasato, MD, PhD Hisataka Maki, MD, PhD Hideo Fujita, MD, PhD Nahoko Kato, MD, PhD Hiroyuki Watanabe, MD, PhD Minami Suzuki, MD Masao Takahashi, MD, PhD Naoko Sawada, MD, PhD Jiro Ando, MD Masataka Sato, MD Shinnosuke Sawano, MD, PhD Susumu Katsushika, MD, PhD Hiroki Shinohara, MD, PhD Norifumi Takeda, MD, PhD Katsuhito Fujiu, MD, PhD Hiroshi Akazawa, MD, PhD Hiroyuki Morita, MD, PhD Issei Komuro, MD, PhD |
| author_sort | Goro Fujiki, MD |
| collection | DOAJ |
| description | Background: Heart failure should be diagnosed as early as possible. Although deep learning models can predict one or more echocardiographic findings from electrocardiograms (ECGs), such analyses are not comprehensive. Objectives: This study aimed to develop a deep learning model for comprehensive prediction of echocardiographic findings from ECGs. Methods: We obtained 229,439 paired ECG and echocardiography data sets from 8 centers. Six centers contributed to model development and 2 to external validation. We identified 12 echocardiographic findings related to left-sided cardiac abnormalities, valvular heart diseases, and right-sided cardiac abnormalities. These findings were predicted using convolutional neural networks, and a composite label was analyzed using logistic regression. A positive composite label indicated positivity in any of the 12 findings. Results: For the composite findings label, the area under the receiver-operating characteristic curve was 0.80 (95% CI: 0.80-0.81) on hold-out validation and 0.78 (95% CI: 0.78-0.79) on external validation. The composite findings label applying logistic regression had an area under the receiver-operating characteristic curve of 0.80 (95% CI: 0.80-0.81) with accuracy of 73.8% (95% CI: 73.2-74.4), sensitivity of 81.1% (95% CI: 80.5-81.8), and specificity of 60.7% (95% CI: 59.6-61.8). Conclusions: We have developed convolutional neural network models that predict a wide range of echocardiographic findings, including left-sided cardiac abnormalities, valvular heart diseases, and right-sided cardiac abnormalities from ECGs and created a model to predict a composite findings label by logistic regression analysis. This model has potential to serve as an adjunct for early diagnosis and treatment of previously undetected cardiac disease. |
| format | Article |
| id | doaj-art-c02b4f3f3fcd406995afdb6b0f6c0491 |
| institution | Kabale University |
| issn | 2772-3747 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | JACC: Asia |
| spelling | doaj-art-c02b4f3f3fcd406995afdb6b0f6c04912025-01-09T06:14:55ZengElsevierJACC: Asia2772-37472025-01-01518898Deep Learning-Based Identification of Echocardiographic Abnormalities From ElectrocardiogramsGoro Fujiki, MD0Satoshi Kodera, MD, PhD1Naoto Setoguchi, MD2Kengo Tanabe, MD, PhD3Kotaro Miyaji, MD, PhD4Shunichi Kushida, MD, PhD5Mike Saji, MD, PhD6Mamoru Nanasato, MD, PhD7Hisataka Maki, MD, PhD8Hideo Fujita, MD, PhD9Nahoko Kato, MD, PhD10Hiroyuki Watanabe, MD, PhD11Minami Suzuki, MD12Masao Takahashi, MD, PhD13Naoko Sawada, MD, PhD14Jiro Ando, MD15Masataka Sato, MD16Shinnosuke Sawano, MD, PhD17Susumu Katsushika, MD, PhD18Hiroki Shinohara, MD, PhD19Norifumi Takeda, MD, PhD20Katsuhito Fujiu, MD, PhD21Hiroshi Akazawa, MD, PhD22Hiroyuki Morita, MD, PhD23Issei Komuro, MD, PhD24Department of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan; Address for correspondence: Dr Satoshi Kodera, Department of Cardiovascular Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-ku, Tokyo 113-8655, Japan.Division of Cardiology, Mitsui Memorial Hospital, Tokyo, JapanDivision of Cardiology, Mitsui Memorial Hospital, Tokyo, JapanDepartment of Cardiovascular Medicine, Asahi General Hospital, Chiba, JapanDepartment of Cardiovascular Medicine, Asahi General Hospital, Chiba, JapanDepartment of Cardiology, Sakakibara Heart Institute, Tokyo, JapanDepartment of Cardiology, Sakakibara Heart Institute, Tokyo, JapanDivision of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, Omiya, JapanDivision of Cardiovascular Medicine, Saitama Medical Center, Jichi Medical University, Omiya, JapanDepartment of Cardiology, Tokyo Bay Urayasu Ichikawa Medical Center, Urayasu, JapanDepartment of Cardiology, Tokyo Bay Urayasu Ichikawa Medical Center, Urayasu, JapanDepartment of Cardiology, JR General Hospital, Tokyo, JapanDepartment of Cardiology, JR General Hospital, Tokyo, JapanDepartment of Cardiology, NTT Medical Center Tokyo, Tokyo, JapanDepartment of Cardiology, NTT Medical Center Tokyo, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, Japan; Department of Advanced Cardiology, The University of Tokyo, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, JapanDepartment of Cardiovascular Medicine, The University of Tokyo Hospital, Tokyo, JapanDepartment of Frontier Cardiovascular Science, Graduate School of Medicine, The University of Tokyo, Tokyo, Japan; International University of Health and Welfare, Tochigi, JapanBackground: Heart failure should be diagnosed as early as possible. Although deep learning models can predict one or more echocardiographic findings from electrocardiograms (ECGs), such analyses are not comprehensive. Objectives: This study aimed to develop a deep learning model for comprehensive prediction of echocardiographic findings from ECGs. Methods: We obtained 229,439 paired ECG and echocardiography data sets from 8 centers. Six centers contributed to model development and 2 to external validation. We identified 12 echocardiographic findings related to left-sided cardiac abnormalities, valvular heart diseases, and right-sided cardiac abnormalities. These findings were predicted using convolutional neural networks, and a composite label was analyzed using logistic regression. A positive composite label indicated positivity in any of the 12 findings. Results: For the composite findings label, the area under the receiver-operating characteristic curve was 0.80 (95% CI: 0.80-0.81) on hold-out validation and 0.78 (95% CI: 0.78-0.79) on external validation. The composite findings label applying logistic regression had an area under the receiver-operating characteristic curve of 0.80 (95% CI: 0.80-0.81) with accuracy of 73.8% (95% CI: 73.2-74.4), sensitivity of 81.1% (95% CI: 80.5-81.8), and specificity of 60.7% (95% CI: 59.6-61.8). Conclusions: We have developed convolutional neural network models that predict a wide range of echocardiographic findings, including left-sided cardiac abnormalities, valvular heart diseases, and right-sided cardiac abnormalities from ECGs and created a model to predict a composite findings label by logistic regression analysis. This model has potential to serve as an adjunct for early diagnosis and treatment of previously undetected cardiac disease.http://www.sciencedirect.com/science/article/pii/S2772374724004241cardiac abnormalitiesdeep learningechocardiographyelectrocardiographyvalvular heart disease |
| spellingShingle | Goro Fujiki, MD Satoshi Kodera, MD, PhD Naoto Setoguchi, MD Kengo Tanabe, MD, PhD Kotaro Miyaji, MD, PhD Shunichi Kushida, MD, PhD Mike Saji, MD, PhD Mamoru Nanasato, MD, PhD Hisataka Maki, MD, PhD Hideo Fujita, MD, PhD Nahoko Kato, MD, PhD Hiroyuki Watanabe, MD, PhD Minami Suzuki, MD Masao Takahashi, MD, PhD Naoko Sawada, MD, PhD Jiro Ando, MD Masataka Sato, MD Shinnosuke Sawano, MD, PhD Susumu Katsushika, MD, PhD Hiroki Shinohara, MD, PhD Norifumi Takeda, MD, PhD Katsuhito Fujiu, MD, PhD Hiroshi Akazawa, MD, PhD Hiroyuki Morita, MD, PhD Issei Komuro, MD, PhD Deep Learning-Based Identification of Echocardiographic Abnormalities From Electrocardiograms JACC: Asia cardiac abnormalities deep learning echocardiography electrocardiography valvular heart disease |
| title | Deep Learning-Based Identification of Echocardiographic Abnormalities From Electrocardiograms |
| title_full | Deep Learning-Based Identification of Echocardiographic Abnormalities From Electrocardiograms |
| title_fullStr | Deep Learning-Based Identification of Echocardiographic Abnormalities From Electrocardiograms |
| title_full_unstemmed | Deep Learning-Based Identification of Echocardiographic Abnormalities From Electrocardiograms |
| title_short | Deep Learning-Based Identification of Echocardiographic Abnormalities From Electrocardiograms |
| title_sort | deep learning based identification of echocardiographic abnormalities from electrocardiograms |
| topic | cardiac abnormalities deep learning echocardiography electrocardiography valvular heart disease |
| url | http://www.sciencedirect.com/science/article/pii/S2772374724004241 |
| work_keys_str_mv | AT gorofujikimd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT satoshikoderamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT naotosetoguchimd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT kengotanabemdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT kotaromiyajimdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT shunichikushidamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT mikesajimdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT mamorunanasatomdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT hisatakamakimdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT hideofujitamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT nahokokatomdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT hiroyukiwatanabemdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT minamisuzukimd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT masaotakahashimdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT naokosawadamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT jiroandomd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT masatakasatomd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT shinnosukesawanomdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT susumukatsushikamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT hirokishinoharamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT norifumitakedamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT katsuhitofujiumdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT hiroshiakazawamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT hiroyukimoritamdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms AT isseikomuromdphd deeplearningbasedidentificationofechocardiographicabnormalitiesfromelectrocardiograms |