AI algorithms applied to echocardiography achieved high accuracy in detecting and classifying aortic stenosis, with a median AUC of 0.92, sensitivity of 82.2-90%, and specificity of 88-99%.
Do artificial intelligence algorithms applied to echocardiography accurately diagnose and risk-stratify aortic stenosis?
AI algorithms applied to echocardiography show high retrospective diagnostic accuracy for aortic stenosis, but clinical integration is limited by a lack of prospective validation and model interpretability.
• Robust diagnostic performance: The AI algorithms demonstrate high accuracy in the detection and classification of aortic stenosis, achieving a median AUC of 0.92. • Superiority of multi-view models: Models integrating multiple echocardiographic views perform better than single-view models in identifying disease severity. • Gap in external validation: Only 24% of the studies analysed reported external validation data, highlighting a critical limitation for the overall reproducibility of these tools. • Interpretability barriers: The predominance of ‘black box’ architectures (72% of studies) hinders the transparency of algorithmic reasoning and its ethical integration into clinical practice. • Need for prospective studies: There is a complete lack of prospective and cost-effectiveness studies, which represents the most significant challenge for the transition of AI from an academic setting to a global clinical standard. Aortic stenosis (AS) is the most common acquired valvular heart disease worldwide, accounting for 43% of valvular diseases. It is estimated that 40–50% of patients with severe symptomatic AS do not receive intervention, resulting in a mortality rate of over 90%. Transthoracic echocardiography remains the gold standard for diagnosis, making it critical for early detection of the disease. However, it is operator-dependent and varies according to the patient’s clinical presentation. In this context, artificial intelligence algorithms, especially deep learning algorithms applied to echocardiography, are emerging as tools with the potential to automate and improve the detection of aortic stenosis. To evaluate the available evidence on the usefulness of artificial intelligence tools applied to echocardiography for the early diagnosis of aortic stenosis, identifying their performance, clinical applicability, and methodological limitations. A scoping review was conducted in four databases (PubMed, Scopus, Web of Science, and BIREME) in accordance with the PRISMA-ScR guideline, which included 25 studies between January 2020 and December 2025 that used AI systems applied to echocardiography for the early diagnosis and risk stratification of aortic stenosis. Twenty-five studies met the inclusion criteria for this review. Artificial intelligence (AI) algorithms, especially convolutional neural networks, achieved heterogeneous performance. The AUC ranged from 0.82 to 0.99; sensitivity was 82.2–90% and specificity was 88–99%. Multivision models performed better than single-vision models. Artificial intelligence algorithms perform well in detecting and classifying the severity of AS. Their performance shows high diagnostic potential in retrospective datasets, reaching metrics that emulate expert accuracy. Critical barriers remain, such as lack of external validation, interpretability, and clinical integration. Prospective multicenter studies with harmonized regulatory frameworks are needed for global validation.
Tarqui et al. (Fri,) conducted a review in Aortic stenosis (n=25). Artificial intelligence algorithms applied to echocardiography was evaluated on Diagnostic performance (AUC, sensitivity, specificity). AI algorithms applied to echocardiography achieved high accuracy in detecting and classifying aortic stenosis, with a median AUC of 0.92, sensitivity of 82.2-90%, and specificity of 88-99%.