Differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM model
Abstract Differential diagnosis of left ventricular hypertrophy (LVH) is often obscure on echocardiography and requires numerous additional tests. We aimed to develop a deep learning algorithm to aid in the differentiation of common etiologies of LVH (i.e. hypertensive heart disease [HHD], hypertrop...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2022-12-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-022-25467-w |
| _version_ | 1811203726372765696 |
|---|---|
| author | In-Chang Hwang Dongjun Choi You-Jung Choi Lia Ju Myeongju Kim Ji-Eun Hong Hyun-Jung Lee Yeonyee E. Yoon Jun-Bean Park Seung-Pyo Lee Hyung-Kwan Kim Yong-Jin Kim Goo-Yeong Cho |
| author_facet | In-Chang Hwang Dongjun Choi You-Jung Choi Lia Ju Myeongju Kim Ji-Eun Hong Hyun-Jung Lee Yeonyee E. Yoon Jun-Bean Park Seung-Pyo Lee Hyung-Kwan Kim Yong-Jin Kim Goo-Yeong Cho |
| author_sort | In-Chang Hwang |
| collection | DOAJ |
| description | Abstract Differential diagnosis of left ventricular hypertrophy (LVH) is often obscure on echocardiography and requires numerous additional tests. We aimed to develop a deep learning algorithm to aid in the differentiation of common etiologies of LVH (i.e. hypertensive heart disease [HHD], hypertrophic cardiomyopathy [HCM], and light-chain cardiac amyloidosis [ALCA]) on echocardiographic images. Echocardiograms in 5 standard views (parasternal long-axis, parasternal short-axis, apical 4-chamber, apical 2-chamber, and apical 3-chamber) were obtained from 930 subjects: 112 with HHD, 191 with HCM, 81 with ALCA and 546 normal subjects. The study population was divided into training (n = 620), validation (n = 155), and test sets (n = 155). A convolutional neural network-long short-term memory (CNN-LSTM) algorithm was constructed to independently classify the 3 diagnoses on each view, and the final diagnosis was made by an aggregate network based on the simultaneously predicted probabilities of HCM, HCM, and ALCA. Diagnostic performance of the algorithm was evaluated by the area under the receiver operating characteristic curve (AUC), and accuracy was evaluated by the confusion matrix. The deep learning algorithm was trained and verified using the training and validation sets, respectively. In the test set, the average AUC across the five standard views was 0.962, 0.982 and 0.996 for HHD, HCM and CA, respectively. The overall diagnostic accuracy was significantly higher for the deep learning algorithm (92.3%) than for echocardiography specialists (80.0% and 80.6%). In the present study, we developed a deep learning algorithm for the differential diagnosis of 3 common LVH etiologies (HHD, HCM and ALCA) by applying a hybrid CNN-LSTM model and aggregate network to standard echocardiographic images. The high diagnostic performance of our deep learning algorithm suggests that the use of deep learning can improve the diagnostic process in patients with LVH. |
| first_indexed | 2024-04-12T02:59:48Z |
| format | Article |
| id | doaj.art-bae2e08471134c5296ea789edfc7b003 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-12T02:59:48Z |
| publishDate | 2022-12-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-bae2e08471134c5296ea789edfc7b0032022-12-22T03:50:41ZengNature PortfolioScientific Reports2045-23222022-12-0112111210.1038/s41598-022-25467-wDifferential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM modelIn-Chang Hwang0Dongjun Choi1You-Jung Choi2Lia Ju3Myeongju Kim4Ji-Eun Hong5Hyun-Jung Lee6Yeonyee E. Yoon7Jun-Bean Park8Seung-Pyo Lee9Hyung-Kwan Kim10Yong-Jin Kim11Goo-Yeong Cho12Cardiovascular Center, Seoul National University Bundang HospitalCenter for Artificial Intelligence in Healthcare, Seoul National University Bundang HospitalDivision of Cardiology, Cardiovascular Center, Korea University Guro HospitalCardiovascular Center, Seoul National University Bundang HospitalCenter for Artificial Intelligence in Healthcare, Seoul National University Bundang HospitalCenter for Artificial Intelligence in Healthcare, Seoul National University Bundang HospitalDepartment of Internal Medicine, Seoul National University College of MedicineCardiovascular Center, Seoul National University Bundang HospitalDepartment of Internal Medicine, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University College of MedicineDepartment of Internal Medicine, Seoul National University College of MedicineCardiovascular Center, Seoul National University Bundang HospitalAbstract Differential diagnosis of left ventricular hypertrophy (LVH) is often obscure on echocardiography and requires numerous additional tests. We aimed to develop a deep learning algorithm to aid in the differentiation of common etiologies of LVH (i.e. hypertensive heart disease [HHD], hypertrophic cardiomyopathy [HCM], and light-chain cardiac amyloidosis [ALCA]) on echocardiographic images. Echocardiograms in 5 standard views (parasternal long-axis, parasternal short-axis, apical 4-chamber, apical 2-chamber, and apical 3-chamber) were obtained from 930 subjects: 112 with HHD, 191 with HCM, 81 with ALCA and 546 normal subjects. The study population was divided into training (n = 620), validation (n = 155), and test sets (n = 155). A convolutional neural network-long short-term memory (CNN-LSTM) algorithm was constructed to independently classify the 3 diagnoses on each view, and the final diagnosis was made by an aggregate network based on the simultaneously predicted probabilities of HCM, HCM, and ALCA. Diagnostic performance of the algorithm was evaluated by the area under the receiver operating characteristic curve (AUC), and accuracy was evaluated by the confusion matrix. The deep learning algorithm was trained and verified using the training and validation sets, respectively. In the test set, the average AUC across the five standard views was 0.962, 0.982 and 0.996 for HHD, HCM and CA, respectively. The overall diagnostic accuracy was significantly higher for the deep learning algorithm (92.3%) than for echocardiography specialists (80.0% and 80.6%). In the present study, we developed a deep learning algorithm for the differential diagnosis of 3 common LVH etiologies (HHD, HCM and ALCA) by applying a hybrid CNN-LSTM model and aggregate network to standard echocardiographic images. The high diagnostic performance of our deep learning algorithm suggests that the use of deep learning can improve the diagnostic process in patients with LVH.https://doi.org/10.1038/s41598-022-25467-w |
| spellingShingle | In-Chang Hwang Dongjun Choi You-Jung Choi Lia Ju Myeongju Kim Ji-Eun Hong Hyun-Jung Lee Yeonyee E. Yoon Jun-Bean Park Seung-Pyo Lee Hyung-Kwan Kim Yong-Jin Kim Goo-Yeong Cho Differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM model Scientific Reports |
| title | Differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM model |
| title_full | Differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM model |
| title_fullStr | Differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM model |
| title_full_unstemmed | Differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM model |
| title_short | Differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid CNN-LSTM model |
| title_sort | differential diagnosis of common etiologies of left ventricular hypertrophy using a hybrid cnn lstm model |
| url | https://doi.org/10.1038/s41598-022-25467-w |
| work_keys_str_mv | AT inchanghwang differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT dongjunchoi differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT youjungchoi differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT liaju differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT myeongjukim differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT jieunhong differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT hyunjunglee differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT yeonyeeeyoon differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT junbeanpark differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT seungpyolee differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT hyungkwankim differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT yongjinkim differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel AT gooyeongcho differentialdiagnosisofcommonetiologiesofleftventricularhypertrophyusingahybridcnnlstmmodel |