Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography

doi:10.1038/s41598-025-06738-8

	Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography
	Zhu, Ziwei 1,2; Fan, Ke 3; Zhang, Shuyuan 1,2; Hu, Tingting 1; Li, Jingyi 1; Zhao, Ze 3; Jin, Ye 1,2,4; Zhang, Shuyang 1,2
	2025-07-01
发表期刊	SCIENTIFIC REPORTS
ISSN	2045-2322
卷号	15 期号:1 页码:11
摘要	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.
关键词	Left ventricular geometry (LVG) Echocardiography Left ventricular ejection fraction (LVEF) Deep learning
DOI	10.1038/s41598-025-06738-8
收录类别	SCI
语种	英语
资助项目	National Key R&D Program of China[2022ZD0116001] ; National High Level Hospital Clinical Research Funding[2022-PUMCH-B-098] ; CAMS Innovation Fund for Medical Sciences (CIFMS)[2021-I2M-1-003] ; The 14th Five-Year Key Research and Development Plan, Ministry of Science and Technology[2022YFC2703100]
WOS研究方向	Science & Technology - Other Topics
WOS类目	Multidisciplinary Sciences
WOS记录号	WOS:001522989300034
出版者	NATURE PORTFOLIO
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42019
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhao, Ze; Jin, Ye; Zhang, Shuyang
作者单位	1.Chinese Acad Med Sci & Peking Union Med Coll, Dept Cardiol, Peking Union Med Coll Hosp, Dongdan Campus, Beijing 100730, Peoples R China 2.Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Rare Dis Med Res Ctr, Beijing 100730, Peoples R China 3.Chinese Acad Sci, Inst Comp Technol, Rd Zhongguancun Kexueyuan 6, Beijing, Peoples R China 4.Chinese Acad Med Sci & Peking Union Med Coll, Natl Infrastruct Translat Med, Peking Union Med Coll, Ctr Digital Med & Artificial Intelligence, Beijing 100730, Peoples R China
推荐引用方式 GB/T 7714	Zhu, Ziwei,Fan, Ke,Zhang, Shuyuan,et al. Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography[J]. SCIENTIFIC REPORTS,2025,15(1):11.
APA	Zhu, Ziwei.,Fan, Ke.,Zhang, Shuyuan.,Hu, Tingting.,Li, Jingyi.,...&Zhang, Shuyang.(2025).Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography.SCIENTIFIC REPORTS,15(1),11.
MLA	Zhu, Ziwei,et al."Automated ejection fraction and risk stratification in cardiomyopathy patients with diverse LV geometry using 2D echocardiography".SCIENTIFIC REPORTS 15.1(2025):11.