Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography
Abstract Cardiomyopathy often alters left ventricular geometry (LVG), impairing cardiac function. We developed a deep learning (DL) model to estimate left ventricular ejection fraction (LVEF) from echocardiographic images while accounting for LVG variability and assessed prognostic factors across LV...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-06738-8 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849769488651649024 |
|---|---|
| author | Ziwei Zhu Ke Fan Shuyuan Zhang Tingting Hu Jingyi Li Ze Zhao Ye Jin Shuyang Zhang |
| author_facet | Ziwei Zhu Ke Fan Shuyuan Zhang Tingting Hu Jingyi Li Ze Zhao Ye Jin Shuyang Zhang |
| author_sort | Ziwei Zhu |
| collection | DOAJ |
| description | Abstract Cardiomyopathy often alters left ventricular geometry (LVG), impairing cardiac function. We developed a deep learning (DL) model to estimate left ventricular ejection fraction (LVEF) from echocardiographic images while accounting for LVG variability and assessed prognostic factors across LVG subtypes. For all patients with cardiomyopathy, we computed LV volume on apical two- and four-chamber views processed with novel DeepLabV3+ algorithm and calculate EF using Simpson’s method. The model was pre-trained on public data, then validated in 120 patients classified into concentric hypertrophy (CH), eccentric hypertrophy (EH), concentric remodeling (CR), or normal geometry (NG). Outcomes included cardiac death and heart failure rehospitalization, analyzed via logistic and LASSO regression within each LVG subtype. The model achieved high LV segmentation accuracy, with an overall Dice similarity coefficient of 90.07% and IoU of 82.17%. Subgroup analysis on A4C images showed Dice/IoU values of 92.49%/86.34% (NG), 88.91%/80.11% (CR), 88.81%/80.23% (CH), and 89.75%/81.59% (EH). The mean absolute error in LVEF estimation was 4.70%, and Bland–Altman analysis showed a mean bias of 0.95 ± 4.53% (95% limits, − 7.92% to 9.82%; P = 0.002) between AI-predicted and manual LVEF measurements. Subgroup analysis revealed r2 values of 0.794 (CR), 0.526 (CH), and 0.968 (EH). During follow-up, 20 patients experienced adverse outcomes. LASSO regression identified predicted LVEF, E/e′ ratio, and age as significant predictors, with AUC values of 0.833 (CR), 0.695 (CH), and 0.938 (EH) for adverse outcomes prediction. This DL model provides accurate LVEF estimates across diverse LVG subtypes, offering a geometry-specific tool for clinical assessment and risk stratification in cardiomyopathy. |
| format | Article |
| id | doaj-art-2584597f0dfd472fa6aa1383405af7b1 |
| institution | DOAJ |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-2584597f0dfd472fa6aa1383405af7b12025-08-20T03:03:24ZengNature PortfolioScientific Reports2045-23222025-07-0115111110.1038/s41598-025-06738-8Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiographyZiwei Zhu0Ke Fan1Shuyuan Zhang2Tingting Hu3Jingyi Li4Ze Zhao5Ye Jin6Shuyang Zhang7Department of Cardiology, Peking Union Medical College Hospital (Dongdan Campus), Chinese Academy of Medical Sciences and Peking Union Medical CollegeInstitute of Computing Technology, Chinese Academy of SciencesDepartment of Cardiology, Peking Union Medical College Hospital (Dongdan Campus), Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Cardiology, Peking Union Medical College Hospital (Dongdan Campus), Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Cardiology, Peking Union Medical College Hospital (Dongdan Campus), Chinese Academy of Medical Sciences and Peking Union Medical CollegeInstitute of Computing Technology, Chinese Academy of SciencesDepartment of Cardiology, Peking Union Medical College Hospital (Dongdan Campus), Chinese Academy of Medical Sciences and Peking Union Medical CollegeDepartment of Cardiology, Peking Union Medical College Hospital (Dongdan Campus), Chinese Academy of Medical Sciences and Peking Union Medical CollegeAbstract Cardiomyopathy often alters left ventricular geometry (LVG), impairing cardiac function. We developed a deep learning (DL) model to estimate left ventricular ejection fraction (LVEF) from echocardiographic images while accounting for LVG variability and assessed prognostic factors across LVG subtypes. For all patients with cardiomyopathy, we computed LV volume on apical two- and four-chamber views processed with novel DeepLabV3+ algorithm and calculate EF using Simpson’s method. The model was pre-trained on public data, then validated in 120 patients classified into concentric hypertrophy (CH), eccentric hypertrophy (EH), concentric remodeling (CR), or normal geometry (NG). Outcomes included cardiac death and heart failure rehospitalization, analyzed via logistic and LASSO regression within each LVG subtype. The model achieved high LV segmentation accuracy, with an overall Dice similarity coefficient of 90.07% and IoU of 82.17%. Subgroup analysis on A4C images showed Dice/IoU values of 92.49%/86.34% (NG), 88.91%/80.11% (CR), 88.81%/80.23% (CH), and 89.75%/81.59% (EH). The mean absolute error in LVEF estimation was 4.70%, and Bland–Altman analysis showed a mean bias of 0.95 ± 4.53% (95% limits, − 7.92% to 9.82%; P = 0.002) between AI-predicted and manual LVEF measurements. Subgroup analysis revealed r2 values of 0.794 (CR), 0.526 (CH), and 0.968 (EH). During follow-up, 20 patients experienced adverse outcomes. LASSO regression identified predicted LVEF, E/e′ ratio, and age as significant predictors, with AUC values of 0.833 (CR), 0.695 (CH), and 0.938 (EH) for adverse outcomes prediction. This DL model provides accurate LVEF estimates across diverse LVG subtypes, offering a geometry-specific tool for clinical assessment and risk stratification in cardiomyopathy.https://doi.org/10.1038/s41598-025-06738-8Left ventricular geometry (LVG)EchocardiographyLeft ventricular ejection fraction (LVEF)Deep learning |
| spellingShingle | Ziwei Zhu Ke Fan Shuyuan Zhang Tingting Hu Jingyi Li Ze Zhao Ye Jin Shuyang Zhang Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography Scientific Reports Left ventricular geometry (LVG) Echocardiography Left ventricular ejection fraction (LVEF) Deep learning |
| title | Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography |
| title_full | Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography |
| title_fullStr | Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography |
| title_full_unstemmed | Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography |
| title_short | Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography |
| title_sort | automated ejection fraction and risk stratification in cardiomyopathy patients with diverse lv geometry using 2d echocardiography |
| topic | Left ventricular geometry (LVG) Echocardiography Left ventricular ejection fraction (LVEF) Deep learning |
| url | https://doi.org/10.1038/s41598-025-06738-8 |
| work_keys_str_mv | AT ziweizhu automatedejectionfractionandriskstratificationincardiomyopathypatientswithdiverselvgeometryusing2dechocardiography AT kefan automatedejectionfractionandriskstratificationincardiomyopathypatientswithdiverselvgeometryusing2dechocardiography AT shuyuanzhang automatedejectionfractionandriskstratificationincardiomyopathypatientswithdiverselvgeometryusing2dechocardiography AT tingtinghu automatedejectionfractionandriskstratificationincardiomyopathypatientswithdiverselvgeometryusing2dechocardiography AT jingyili automatedejectionfractionandriskstratificationincardiomyopathypatientswithdiverselvgeometryusing2dechocardiography AT zezhao automatedejectionfractionandriskstratificationincardiomyopathypatientswithdiverselvgeometryusing2dechocardiography AT yejin automatedejectionfractionandriskstratificationincardiomyopathypatientswithdiverselvgeometryusing2dechocardiography AT shuyangzhang automatedejectionfractionandriskstratificationincardiomyopathypatientswithdiverselvgeometryusing2dechocardiography |