Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study
Summary: Background: Chest radiography is a common and widely available examination. Although cardiovascular structures—such as cardiac shadows and vessels—are visible on chest radiographs, the ability of these radiographs to estimate cardiac function and valvular disease is poorly understood. Usin...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-08-01
|
| Series: | The Lancet: Digital Health |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589750023001073 |
| _version_ | 1827891602677301248 |
|---|---|
| author | Daiju Ueda, MD PhD Toshimasa Matsumoto, PhD Shoichi Ehara, MD PhD Akira Yamamoto, MD PhD Shannon L Walston, MS Asahiro Ito, MD PhD Taro Shimono, MD PhD Masatsugu Shiba, MD PhD Tohru Takeshita, MD PhD Daiju Fukuda, ProfMD PhD Yukio Miki, ProfMD PhD |
| author_facet | Daiju Ueda, MD PhD Toshimasa Matsumoto, PhD Shoichi Ehara, MD PhD Akira Yamamoto, MD PhD Shannon L Walston, MS Asahiro Ito, MD PhD Taro Shimono, MD PhD Masatsugu Shiba, MD PhD Tohru Takeshita, MD PhD Daiju Fukuda, ProfMD PhD Yukio Miki, ProfMD PhD |
| author_sort | Daiju Ueda, MD PhD |
| collection | DOAJ |
| description | Summary: Background: Chest radiography is a common and widely available examination. Although cardiovascular structures—such as cardiac shadows and vessels—are visible on chest radiographs, the ability of these radiographs to estimate cardiac function and valvular disease is poorly understood. Using datasets from multiple institutions, we aimed to develop and validate a deep-learning model to simultaneously detect valvular disease and cardiac functions from chest radiographs. Methods: In this model development and validation study, we trained, validated, and externally tested a deep learning-based model to classify left ventricular ejection fraction, tricuspid regurgitant velocity, mitral regurgitation, aortic stenosis, aortic regurgitation, mitral stenosis, tricuspid regurgitation, pulmonary regurgitation, and inferior vena cava dilation from chest radiographs. The chest radiographs and associated echocardiograms were collected from four institutions between April 1, 2013, and Dec 31, 2021: we used data from three sites (Osaka Metropolitan University Hospital, Osaka, Japan; Habikino Medical Center, Habikino, Japan; and Morimoto Hospital, Osaka, Japan) for training, validation, and internal testing, and data from one site (Kashiwara Municipal Hospital, Kashiwara, Japan) for external testing. We evaluated the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Findings: We included 22 551 radiographs associated with 22 551 echocardiograms obtained from 16 946 patients. The external test dataset featured 3311 radiographs from 2617 patients with a mean age of 72 years [SD 15], of whom 49·8% were male and 50·2% were female. The AUCs, accuracy, sensitivity, and specificity for this dataset were 0·92 (95% CI 0·90–0·95), 86% (85–87), 82% (75–87), and 86% (85–88) for classifying the left ventricular ejection fraction at a 40% cutoff, 0·85 (0·83–0·87), 75% (73–76), 83% (80–87), and 73% (71–75) for classifying the tricuspid regurgitant velocity at a 2·8 m/s cutoff, 0·89 (0·86–0·92), 85% (84–86), 82% (76–87), and 85% (84–86) for classifying mitral regurgitation at the none-mild versus moderate-severe cutoff, 0·83 (0·78–0·88), 73% (71–74), 79% (69–87), and 72% (71–74) for classifying aortic stenosis, 0·83 (0·79–0·87), 68% (67–70), 88% (81–92), and 67% (66–69) for classifying aortic regurgitation, 0·86 (0·67–1·00), 90% (89–91), 83% (36–100), and 90% (89–91) for classifying mitral stenosis, 0·92 (0·89–0·94), 83% (82–85), 87% (83–91), and 83% (82–84) for classifying tricuspid regurgitation, 0·86 (0·82–0·90), 69% (68–71), 91% (84–95), and 68% (67–70) for classifying pulmonary regurgitation, and 0·85 (0·81–0·89), 86% (85–88), 73% (65–81), and 87% (86–88) for classifying inferior vena cava dilation. Interpretation: The deep learning-based model can accurately classify cardiac functions and valvular heart diseases using information from digital chest radiographs. This model can classify values typically obtained from echocardiography in a fraction of the time, with low system requirements and the potential to be continuously available in areas where echocardiography specialists are scarce or absent. Funding: None. |
| first_indexed | 2024-03-12T21:28:09Z |
| format | Article |
| id | doaj.art-ec26624380674d6689d829160c68f226 |
| institution | Directory Open Access Journal |
| issn | 2589-7500 |
| language | English |
| last_indexed | 2024-03-12T21:28:09Z |
| publishDate | 2023-08-01 |
| publisher | Elsevier |
| record_format | Article |
| series | The Lancet: Digital Health |
| spelling | doaj.art-ec26624380674d6689d829160c68f2262023-07-28T04:26:36ZengElsevierThe Lancet: Digital Health2589-75002023-08-0158e525e533Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation studyDaiju Ueda, MD PhD0Toshimasa Matsumoto, PhD1Shoichi Ehara, MD PhD2Akira Yamamoto, MD PhD3Shannon L Walston, MS4Asahiro Ito, MD PhD5Taro Shimono, MD PhD6Masatsugu Shiba, MD PhD7Tohru Takeshita, MD PhD8Daiju Fukuda, ProfMD PhD9Yukio Miki, ProfMD PhD10Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan; Smart Life Science Lab, Center for Health Science Innovation, Osaka Metropolitan University, Osaka, Japan; Correspondence to: Dr Daiju Ueda, Department of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka 545-8585, JapanDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan; Smart Life Science Lab, Center for Health Science Innovation, Osaka Metropolitan University, Osaka, JapanDepartment of Intensive Care Medicine, Graduate School of Medicine, Osaka Metropolitan University, Osaka, JapanDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, JapanDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, JapanDepartment of Cardiovascular Medicine, Graduate School of Medicine, Osaka Metropolitan University, Osaka, JapanDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, JapanDepartment of Biofunctional Analysis, Graduate School of Medicine, Osaka Metropolitan University, Osaka, Japan; Smart Life Science Lab, Center for Health Science Innovation, Osaka Metropolitan University, Osaka, JapanDepartment of Radiology, Osaka Habikino Medical Center, Habikino, JapanDepartment of Cardiovascular Medicine, Graduate School of Medicine, Osaka Metropolitan University, Osaka, JapanDepartment of Diagnostic and Interventional Radiology, Graduate School of Medicine, Osaka Metropolitan University, Osaka, JapanSummary: Background: Chest radiography is a common and widely available examination. Although cardiovascular structures—such as cardiac shadows and vessels—are visible on chest radiographs, the ability of these radiographs to estimate cardiac function and valvular disease is poorly understood. Using datasets from multiple institutions, we aimed to develop and validate a deep-learning model to simultaneously detect valvular disease and cardiac functions from chest radiographs. Methods: In this model development and validation study, we trained, validated, and externally tested a deep learning-based model to classify left ventricular ejection fraction, tricuspid regurgitant velocity, mitral regurgitation, aortic stenosis, aortic regurgitation, mitral stenosis, tricuspid regurgitation, pulmonary regurgitation, and inferior vena cava dilation from chest radiographs. The chest radiographs and associated echocardiograms were collected from four institutions between April 1, 2013, and Dec 31, 2021: we used data from three sites (Osaka Metropolitan University Hospital, Osaka, Japan; Habikino Medical Center, Habikino, Japan; and Morimoto Hospital, Osaka, Japan) for training, validation, and internal testing, and data from one site (Kashiwara Municipal Hospital, Kashiwara, Japan) for external testing. We evaluated the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and accuracy. Findings: We included 22 551 radiographs associated with 22 551 echocardiograms obtained from 16 946 patients. The external test dataset featured 3311 radiographs from 2617 patients with a mean age of 72 years [SD 15], of whom 49·8% were male and 50·2% were female. The AUCs, accuracy, sensitivity, and specificity for this dataset were 0·92 (95% CI 0·90–0·95), 86% (85–87), 82% (75–87), and 86% (85–88) for classifying the left ventricular ejection fraction at a 40% cutoff, 0·85 (0·83–0·87), 75% (73–76), 83% (80–87), and 73% (71–75) for classifying the tricuspid regurgitant velocity at a 2·8 m/s cutoff, 0·89 (0·86–0·92), 85% (84–86), 82% (76–87), and 85% (84–86) for classifying mitral regurgitation at the none-mild versus moderate-severe cutoff, 0·83 (0·78–0·88), 73% (71–74), 79% (69–87), and 72% (71–74) for classifying aortic stenosis, 0·83 (0·79–0·87), 68% (67–70), 88% (81–92), and 67% (66–69) for classifying aortic regurgitation, 0·86 (0·67–1·00), 90% (89–91), 83% (36–100), and 90% (89–91) for classifying mitral stenosis, 0·92 (0·89–0·94), 83% (82–85), 87% (83–91), and 83% (82–84) for classifying tricuspid regurgitation, 0·86 (0·82–0·90), 69% (68–71), 91% (84–95), and 68% (67–70) for classifying pulmonary regurgitation, and 0·85 (0·81–0·89), 86% (85–88), 73% (65–81), and 87% (86–88) for classifying inferior vena cava dilation. Interpretation: The deep learning-based model can accurately classify cardiac functions and valvular heart diseases using information from digital chest radiographs. This model can classify values typically obtained from echocardiography in a fraction of the time, with low system requirements and the potential to be continuously available in areas where echocardiography specialists are scarce or absent. Funding: None.http://www.sciencedirect.com/science/article/pii/S2589750023001073 |
| spellingShingle | Daiju Ueda, MD PhD Toshimasa Matsumoto, PhD Shoichi Ehara, MD PhD Akira Yamamoto, MD PhD Shannon L Walston, MS Asahiro Ito, MD PhD Taro Shimono, MD PhD Masatsugu Shiba, MD PhD Tohru Takeshita, MD PhD Daiju Fukuda, ProfMD PhD Yukio Miki, ProfMD PhD Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study The Lancet: Digital Health |
| title | Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study |
| title_full | Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study |
| title_fullStr | Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study |
| title_full_unstemmed | Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study |
| title_short | Artificial intelligence-based model to classify cardiac functions from chest radiographs: a multi-institutional, retrospective model development and validation study |
| title_sort | artificial intelligence based model to classify cardiac functions from chest radiographs a multi institutional retrospective model development and validation study |
| url | http://www.sciencedirect.com/science/article/pii/S2589750023001073 |
| work_keys_str_mv | AT daijuuedamdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT toshimasamatsumotophd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT shoichieharamdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT akirayamamotomdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT shannonlwalstonms artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT asahiroitomdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT taroshimonomdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT masatsugushibamdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT tohrutakeshitamdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT daijufukudaprofmdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy AT yukiomikiprofmdphd artificialintelligencebasedmodeltoclassifycardiacfunctionsfromchestradiographsamultiinstitutionalretrospectivemodeldevelopmentandvalidationstudy |