Artificial intelligence-enhanced electrocardiography to predict regurgitant valvular heart diseases: an international study
Figures
Why the study?
Can artificial intelligence-enhanced electrocardiography predict future moderate or severe regurgitant valvular heart diseases in patients with paired ECG and echocardiography data?
Key Points
- To develop and validate artificial intelligence-enhanced electrocardiography (AI-ECG) models to diagnose and predict future moderate or severe regurgitant valvular heart diseases.
- Trained residual convolutional neural network models using 988,618 ECG and transthoracic echocardiogram pairs from 400,882 patients at Zhongshan Hospital in Shanghai, China.
- Externally validated the models using a secondary care dataset of 34,214 outpatients with linked echocardiography from Beth Israel Deaconess Medical Center in Boston, USA.
- In the internal test set, AI-ECG models predicted future significant mitral regurgitation (C-index 0.774, 95% CI 0.753–0.792), aortic regurgitation (C-index 0.691, 95% CI 0.657–0.720), and tricuspid regurgitation (C-index 0.793, 95% CI 0.777–0.808).
- Compared with the lowest-risk quartile, the highest-risk quartile had adjusted hazard ratios of 7.6 (95% CI 5.8–9.9, P < .0001) for mitral regurgitation, 3.8 (95% CI 2.7–5.5) for aortic regurgitation, and 9.9 (95% CI 7.5–13.0) for tricuspid regurgitation.
- Predictive performance was confirmed in the external transnational cohort, and predictions correlated with subclinical cardiac chamber remodeling.
Study Design
Type
Cohort (n=435,096)
Multicenter
Yes
Structured PICO
Can artificial intelligence-enhanced electrocardiography predict future moderate or severe regurgitant valvular heart diseases in patients with paired ECG and echocardiography data?
P
Population
435,096 patients with linked electrocardiography and transthoracic echocardiogram pairs from China and the USA used to develop and validate AI-ECG models for predicting regurgitant valvular heart diseases.
E
Exposure
Artificial intelligence-enhanced electrocardiography (AI-ECG) models using a residual convolutional neural network
O
Outcome
Prediction of future moderate or severe regurgitant valvular heart diseases (mitral regurgitation, tricuspid regurgitation, and aortic regurgitation)surrogate
Main Result
Hazard Ratio: 7.6 (95% CI 5.8–9.9)
p-value: p=<.0001
Ask about this paper
Answers are grounded in this paper and cite their sources.
Key expert perspectives
Captured external expert commentary on this paper, strongest first. Original sources are linked where available.
“Our hearts are incredibly complex and hard-working organs, but we rarely give them much consideration unless something goes wrong. By the time symptoms and structural changes appear in the heart, it may be too late to do much about it. Our work is harnessing AI to detect subtle changes at the earliest stage from a simple and common test, and we think this could be really transformative for doctors and patients. Rather than waiting for symptoms, or relying only on expensive and time-consuming imaging tests, we could use AI-enhanced ECGs to spot those most at risk earlier than ever before. This means that many more people could get the care they need before their hidden condition affects their quality of life or becomes life-threatening.”
“AI has enormous potential for improving healthcare around the world, but it requires huge amounts of data to train and test these algorithms. Our work is an example of the benefits of international collaboration in this fast-growing area. By training the model in an almost exclusively Chinese population and then testing in a US cohort, we can show that our AI tool has the potential to be applied in various countries and settings around the world. This ultimately means it has the potential to help even more patients.”
Implication
Artificial intelligence-enhanced electrocardiography models can accurately predict the future development of moderate or severe regurgitant valvular heart diseases, potentially guiding surveillance echocardiography.
Abstract
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 electrocardiography (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 data set 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 data set 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% confidence interval (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 < .0001) for risk of future significant MR, compared with 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 remodelling. CONCLUSIONS: This study developed AI-ECG models to diagnose and predict rVHDs and validated the models in a transnational and ethnically distinct cohort. The AI-ECG models could be utilized to guide surveillance echocardiography in patients at risk of future rVHDs, to facilitate early detection and intervention.
Discussion
No takes yet. Share an insight, caveat, or question.
Cite This Study
Liang et al. (2025) conducted a cohort in Regurgitant valvular heart diseases (n=435,096). AI-ECG model (highest risk quartile) vs. Lowest risk quartile was evaluated on Future significant mitral regurgitation (HR 7.6, 95% CI 5.8-9.9, p=<.0001).