Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images
BackgroundStress echocardiography is an emerging tool used to detect exercise-induced pulmonary hypertension (EIPH). However, facilities that can perform stress echocardiography are limited by issues such as cost and equipment.ObjectiveWe evaluated the usefulness of a deep learning (DL) approach bas...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2022-06-01
|
| Series: | Frontiers in Cardiovascular Medicine |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fcvm.2022.891703/full |
| _version_ | 1818546348898648064 |
|---|---|
| author | Kenya Kusunose Yukina Hirata Natsumi Yamaguchi Yoshitaka Kosaka Takumasa Tsuji Jun’ichi Kotoku Masataka Sata |
| author_facet | Kenya Kusunose Yukina Hirata Natsumi Yamaguchi Yoshitaka Kosaka Takumasa Tsuji Jun’ichi Kotoku Masataka Sata |
| author_sort | Kenya Kusunose |
| collection | DOAJ |
| description | BackgroundStress echocardiography is an emerging tool used to detect exercise-induced pulmonary hypertension (EIPH). However, facilities that can perform stress echocardiography are limited by issues such as cost and equipment.ObjectiveWe evaluated the usefulness of a deep learning (DL) approach based on a chest X-ray (CXR) to predict EIPH in 6-min walk stress echocardiography.MethodsThe study enrolled 142 patients with scleroderma or mixed connective tissue disease with scleroderma features who performed a 6-min walk stress echocardiographic test. EIPH was defined by abnormal cardiac output (CO) responses that involved an increase in mean pulmonary artery pressure (mPAP). We used the previously developed AI model to predict PH and calculated PH probability in this cohort.ResultsEIPH defined as ΔmPAP/ΔCO >3.3 and exercise mPAP >25 mmHg was observed in 52 patients, while non-EIPH was observed in 90 patients. The patients with EIPH had a higher mPAP at rest than those without EIPH. The probability of PH based on the DL model was significantly higher in patients with EIPH than in those without EIPH. Multivariate analysis showed that gender, mean PAP at rest, and the probability of PH based on the DL model were independent predictors of EIPH. A model based on baseline parameters (age, gender, and mPAP at rest) was improved by adding the probability of PH predicted by the DL model (AUC: from 0.65 to 0.74; p = 0.046).ConclusionApplying the DL model based on a CXR may have a potential for detection of EIPH in the clinical setting. |
| first_indexed | 2024-12-12T07:52:00Z |
| format | Article |
| id | doaj.art-16d0ebf8f89941c49aa2e6cd4c666e20 |
| institution | Directory Open Access Journal |
| issn | 2297-055X |
| language | English |
| last_indexed | 2024-12-12T07:52:00Z |
| publishDate | 2022-06-01 |
| publisher | Frontiers Media S.A. |
| record_format | Article |
| series | Frontiers in Cardiovascular Medicine |
| spelling | doaj.art-16d0ebf8f89941c49aa2e6cd4c666e202022-12-22T00:32:25ZengFrontiers Media S.A.Frontiers in Cardiovascular Medicine2297-055X2022-06-01910.3389/fcvm.2022.891703891703Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray ImagesKenya Kusunose0Yukina Hirata1Natsumi Yamaguchi2Yoshitaka Kosaka3Takumasa Tsuji4Jun’ichi Kotoku5Masataka Sata6Department of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, JapanUltrasound Examination Center, Tokushima University Hospital, Tokushima, JapanUltrasound Examination Center, Tokushima University Hospital, Tokushima, JapanDepartment of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, JapanDepartment of Radiological Technology, Graduate School of Medical Care and Technology, Teikyo University, Tokyo, JapanDepartment of Radiological Technology, Graduate School of Medical Care and Technology, Teikyo University, Tokyo, JapanDepartment of Cardiovascular Medicine, Tokushima University Hospital, Tokushima, JapanBackgroundStress echocardiography is an emerging tool used to detect exercise-induced pulmonary hypertension (EIPH). However, facilities that can perform stress echocardiography are limited by issues such as cost and equipment.ObjectiveWe evaluated the usefulness of a deep learning (DL) approach based on a chest X-ray (CXR) to predict EIPH in 6-min walk stress echocardiography.MethodsThe study enrolled 142 patients with scleroderma or mixed connective tissue disease with scleroderma features who performed a 6-min walk stress echocardiographic test. EIPH was defined by abnormal cardiac output (CO) responses that involved an increase in mean pulmonary artery pressure (mPAP). We used the previously developed AI model to predict PH and calculated PH probability in this cohort.ResultsEIPH defined as ΔmPAP/ΔCO >3.3 and exercise mPAP >25 mmHg was observed in 52 patients, while non-EIPH was observed in 90 patients. The patients with EIPH had a higher mPAP at rest than those without EIPH. The probability of PH based on the DL model was significantly higher in patients with EIPH than in those without EIPH. Multivariate analysis showed that gender, mean PAP at rest, and the probability of PH based on the DL model were independent predictors of EIPH. A model based on baseline parameters (age, gender, and mPAP at rest) was improved by adding the probability of PH predicted by the DL model (AUC: from 0.65 to 0.74; p = 0.046).ConclusionApplying the DL model based on a CXR may have a potential for detection of EIPH in the clinical setting.https://www.frontiersin.org/articles/10.3389/fcvm.2022.891703/fullartificial intelligenceconnective tissue diseaseechocardiographyexercise pulmonary hypertensionscleroderma (SSc) |
| spellingShingle | Kenya Kusunose Yukina Hirata Natsumi Yamaguchi Yoshitaka Kosaka Takumasa Tsuji Jun’ichi Kotoku Masataka Sata Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images Frontiers in Cardiovascular Medicine artificial intelligence connective tissue disease echocardiography exercise pulmonary hypertension scleroderma (SSc) |
| title | Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images |
| title_full | Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images |
| title_fullStr | Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images |
| title_full_unstemmed | Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images |
| title_short | Deep Learning for Detection of Exercise-Induced Pulmonary Hypertension Using Chest X-Ray Images |
| title_sort | deep learning for detection of exercise induced pulmonary hypertension using chest x ray images |
| topic | artificial intelligence connective tissue disease echocardiography exercise pulmonary hypertension scleroderma (SSc) |
| url | https://www.frontiersin.org/articles/10.3389/fcvm.2022.891703/full |
| work_keys_str_mv | AT kenyakusunose deeplearningfordetectionofexerciseinducedpulmonaryhypertensionusingchestxrayimages AT yukinahirata deeplearningfordetectionofexerciseinducedpulmonaryhypertensionusingchestxrayimages AT natsumiyamaguchi deeplearningfordetectionofexerciseinducedpulmonaryhypertensionusingchestxrayimages AT yoshitakakosaka deeplearningfordetectionofexerciseinducedpulmonaryhypertensionusingchestxrayimages AT takumasatsuji deeplearningfordetectionofexerciseinducedpulmonaryhypertensionusingchestxrayimages AT junichikotoku deeplearningfordetectionofexerciseinducedpulmonaryhypertensionusingchestxrayimages AT masatakasata deeplearningfordetectionofexerciseinducedpulmonaryhypertensionusingchestxrayimages |