BibTex format
@article{Liang:2025:eurheartj/ehaf448,
author = {Liang, Y and Sau, A and Zeidaabadi, B and Barker, J and Patlatzoglou, K and Pastika, L and Sieliwonczyk, E and Whinnett, Z and Peters, NS and Yu, Z and Liu, X and Wang, S and Lu, H and Kramer, DB and Waks, JW and Su, Y and Ge, J and Ng, FS},
doi = {eurheartj/ehaf448},
journal = {European Heart Journal},
pages = {4823--4837},
title = {Artificial intelligence-enhanced electrocardiography models for the diagnosis and prediction of future regurgitant valvular heart diseases: an international multi-center study},
url = {http://dx.doi.org/10.1093/eurheartj/ehaf448},
volume = {46},
year = {2025}
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - Background and Aims Valvular heart disease (VHD) is a significant source of morbidity and mortality, though early intervention can improve outcomes. This study aims to develop artificial intelligence-enhanced electrocardiogram (AI-ECG) models to diagnose and predict future moderate or severe regurgitant VHDs (rVHDs), including mitral regurgitation (MR), tricuspid regurgitation (TR), and aortic regurgitation (AR). Methods:The AI-ECG models were developed in a dataset of 988,618 ECG and transthoracic echocardiogram pairs from 400,882 patients from Zhongshan Hospital, Shanghai, China. The AI-ECG models used a residual convolutional neural network with a discrete-time survival loss function. External evaluation was performed in outpatients from a secondary care dataset from Beth Israel Deaconess Medical Center, Boston, USA, consisting of 34,214 patients with linked echocardiography. Results:In the internal test set, the AI-ECG models accurately predicted future significant MR (C-index 0.774, 95%CI 0.753-0.792), AR (0.691, 95%CI 0.657-0.720) and TR (0.793, 95%CI 0.777-0.808). In age- and sex-adjusted Cox models, the highest risk quartile had a hazard ratio (HR) of 7.6 (95%CI 5.8-9.9, P < 0.0001) for risk of future significant MR, compared to the lowest risk quartile. For future AR and TR, the equivalent HRs were 3.8 (95%CI 2.7-5.5) and 9.9 (95%CI 7.5-13.0), respectively. These findings were confirmed in the transnational external test set. Imaging association analyses demonstrated AI-ECG predictions were associated with subclinical chamber remodeling. Conclusions: This study developed AI-ECG models to diagnose and predict future rVHDs and validated the models in a transnational and ethnically distinct cohort. AI-ECG could be utilized to guide surveillance echocardiography in patients at risk of future rVHDs, to facilitate early detection and intervention.REGISTRATION: URL: https://www.clinicaltrials.gov; Unique identifier: NCT06475157.
AU - Liang,Y
AU - Sau,A
AU - Zeidaabadi,B
AU - Barker,J
AU - Patlatzoglou,K
AU - Pastika,L
AU - Sieliwonczyk,E
AU - Whinnett,Z
AU - Peters,NS
AU - Yu,Z
AU - Liu,X
AU - Wang,S
AU - Lu,H
AU - Kramer,DB
AU - Waks,JW
AU - Su,Y
AU - Ge,J
AU - Ng,FS
DO - eurheartj/ehaf448
EP - 4837
PY - 2025///
SN - 0195-668X
SP - 4823
TI - Artificial intelligence-enhanced electrocardiography models for the diagnosis and prediction of future regurgitant valvular heart diseases: an international multi-center study
T2 - European Heart Journal
UR - http://dx.doi.org/10.1093/eurheartj/ehaf448
VL - 46
ER -