Aug 2026· European Heart Journal, Supplement· 0 citations
Abstract
Echocardiography is the cornerstone for risk stratification, diagnosis, and monitoring of cancer therapy–related cardiac dysfunction (CTRCD)(1). Artificial intelligence (AI)–guided echocardiography has shown high accuracy and reliability in diverse cardiac populations and may reduce variability while improving workflow efficiency(2, 3). However, this technology has not yet been validated in a dedicated cohort of patients with cancer.
To evaluate the accuracy and reliability of AI-guided echocardiography in assessing left ventricular ejection fraction (LVEF) and additional parameters, compared with conventional echocardiography, in a cardio-oncology population.
This study included patients identified retrospectively from a cardio-oncology registry. Studies, that had already been analysed manually by expert sonographers and reported using AGFA PACS system, were uploaded to the US2.ai platform for automated analysis. The primary outcome was the level of agreement (LoA) between AI-guided and standard echocardiography for LVEF. Secondary outcomes included LoA for additional echocardiographic parameters and LoA between AI- LVEF and 3D LVEF. The performance of the deep learning (DL) algorithm in identifying LVEF <50% was evaluated using the area under the receiver operating characteristic curve (ROC-AUC). Subgroup analyses were performed in predefined populations clinically relevant in cardio-oncology.
A total of 282 patients were included. Mean age was 60 ± 16 years, and 61% were women. Breast cancer was the most frequent malignancy (30.5%), followed by haematological malignancies (16.7%) and gastrointestinal tumours (10.6%). Manual median 2D LVEF was 60% (IQR: 55-64) and AI-derived LVEF was 59.2% (IQR: 53-64) showing good agreement and correlation (bias: −0.138, SD: 5.38, 95% LoA: −10.7 to 10.4, ICC: 0.791, 95% CI: 0.742–0.831, Spearman ρ: 0.718,), Table 1. Comparison between 3D echocardiography LVEF and AI-derived 2D LVEF showed similar agreement with narrower limits (bias: −0.13, 95% LoA: −9.51 to 9.26). The DL algorithm accurately identified LVEF <50% (ROC-AUC: 0.918, 95% CI: 0.875–0.961), Figure 1. Subgroup analyses demonstrated consistent agreement in patients with breast cancer, body mass index >30, prior radiotherapy and pericardial effusion.
In a large real-world cardio-oncology cohort, AI-guided echocardiography demonstrated strong agreement with conventional echocardiography for LVEF assessment and high accuracy for detecting clinically relevant LV dysfunction. Performance was consistent across key subgroups, supporting the feasibility, reliability, and potential clinical value of integrating DL-based analysis into routine cardio-oncology echocardiographic workflows.Agreement between manual and AI-echo AUC-ROC curve for LVEF<50%
Echocardiography is one of the most commonly used diagnostic methods in cardiovascular diseases because it is non-invasive, widely available, and capable of providing real-time assessment of function and cardiac structure. Despite these advantages, conventional echocardiography is often limited by operator dependence, interobserver inconstancy, the time-intensive nature of manual acquisition and measurement. Recent advances in artificial intelligence (AI), particularly deep learning, have created new opportunities to automate multiple steps of the echocardiographic workflow, starting from image acquisition and view classification to chamber segmentation, functional quantification, and hemodynamic estimation. This review provides an overview of the current clinical applications of artificial intelligence (AI) throughout the echocardiographic workflow. It focuses on key areas where AI has been applied, including automated view recognition, image quality assessment, cardiac phase identification, chamber segmentation, left ventricular ejection fraction estimation, strain analysis, and prediction of hemodynamic and disease-related parameters. Major challenges limiting wider clinical implementation were also highlighted in this review, such as insufficient external validation, dependence on image quality, differences between ultrasound vendors and patient populations, limited model interpretability, and lack of clear evidence demonstrating improved patient outcomes. Several AI-based tools, particularly those for automated view classification and chamber quantification, are becoming increasingly integrated into routine clinical practice, but many more advanced applications are possible, for which research is ongoing. The successful adoption of AI in echocardiography will depend not only on continued improvements in algorithm performance, but also on rigorous clinical validation, smooth integration into existing workflows, transparent reporting of model development and evaluation, and evidence that these technologies provide meaningful benefits for patient care.
Dominika Skoczylas, Katarzyna Deleska, Wiktoria Chmura et al.· Cureus· 0 citations
The global burden of valvular heart disease (VHD) is increasingly burdensome, and precise early diagnosis combined with accurate risk stratification constitutes the core strategy for improving patient prognosis. As the first-line imaging modality for VHD assessment, echocardiography is constrained by interobserver variability and cumbersome, time-consuming data processing workflows, which prevent it from fully meeting the demands of precision medicine. In recent years, breakthroughs in artificial intelligence (AI), particularly deep learning (DL) technologies, have been reshaping the paradigm of imaging-based evaluation for VHD. This review systematically summarizes the latest advances in AI applications across the entire workflow of echocardiographic assessment in VHD: from the precise segmentation of valvular anatomical structures and identification of lesions using convolutional neural networks, to the automated grading of hemodynamic severity achieved through end-to-end learning. More importantly, this article explores how AI can surpass the limitations of traditional imaging indicators by leveraging unsupervised clustering to unearth potential high-risk phenotypes and integrating multimodal data to predict adverse outcomes. Finally, the paper critically analyzes the current challenges in data standardization, model interpretability, and clinical translation, and offers perspectives on future directions in the intersection of clinical medicine and engineering.
Xianyu Ke, Ruize Zhang, Jiawei Shi et al.· Trends in cardiovascular med...· 0 citations
Therapy-induced cardiotoxicity is the leading non-oncological cause of treatment interruption in breast cancer patients, yet early, automated risk stratification from routine cardiac imaging remains an unsolved problem. We present EchoRisk, the first curated, multicentre, longitudinal echocardiography dataset with explicit cardiotoxicity labels, released as the primary technical reference for the EchoRisk-MICCAI 2026 challenge. The dataset comprises 422 patients enrolled in the EU-funded CARDIOCARE prospective study across five European sites, yielding 2,159 echocardiography videos across 1,123 clinical exams acquired at up to five longitudinal timepoints, alongside a dedicated cohort of 280 patients with baseline imaging for early cardiotoxicity prediction. Three clinically grounded tasks are defined: automated estimation of left ventricular ejection fraction from cine video (Task 1), classification of LV dysfunction from longitudinal imaging (Task 2), and early prediction of therapy-induced cardiotoxicity from pre-therapy baseline echocardiography alone (Task 3). For each task we specify the evaluation protocol, primary and secondary metrics, and ranking procedure. We establish baseline performance using an R(2+1)D video backbone with LSTM aggregation trained from Kinetics-400 pretrained weights, demonstrating strong discriminative performance for cardiac functional assessment and LV dysfunction classification, while early cardiotoxicity prediction from a single pre-therapy video remains a significant open problem for the community. The dataset, evaluation code, and baseline implementations are publicly available to serve as a benchmark for further collaboration, comparison, and the creation of task-specific architectures in cardio-oncology.
G. Kalliatakis, G. Karanasiou, Georgios C. Manikis et al.· 1 citation
Introduction Echocardiography is critical for the diagnosis and risk stratification of hypertrophic cardiomyopathy (HCM). However, its value to predict disease progression in pre-symptomatic HCM remains to be fully explored. This study aims to assess the prognostic value of echocardiography in pre-symptomatic HCM using a fully automated machine learning (ML) pipeline to predict disease progression. Methods Echocardiographic data (B-mode acquisitions of apical 4-chamber sequences) from 260 NYHA I HCM patients, collected retrospectively from two centers, was used. An ML pipeline was built on the discovery cohort (N=212 patients) to predict disease progression, defined as a composite of NYHA class worsening and unplanned cardiovascular-related hospitalizations. A fully automated deep learning segmentation pipeline was used to delineate cardiac chambers in apical 4-chamber views and identify end-diastolic frames. Shape-based radiomic features extracted from these segmentations were used to train a survival model based on gradient-boosted trees. The ML model and a derived actionable echocardiographic marker were validated on an external cohort (N=48 patients). Results The 3-year risk of disease progression was 12% in the discovery cohort and 15% in the validation cohort. The ML model achieved a C-index of 0.66 (95% CI [0.54, 0.77], nested cross-validation folds) in the discovery cohort and 0.67 (95% CI [0.46, 0.88], 100 bootstrapped samples) in the validation cohort. Following model interpretation, the left atrioventricular coupling index (area-derived LACI) at end-diastole was derived, and used as a risk score, achieving a C-index of 0.67 (95% CI [0.58, 0.77]) and 0.72 (95% CI [0.56, 0.88]) in the discovery and validation cohorts, respectively (100 bootstrapped samples). The high-risk group, with LACI>0.51, had a 3-year risk of disease progression of 19% (95% CI [13%, 36%]) compared to 8% (95% CI [5%, 15%]) for the low-risk group LACI ≤0.51 in the discovery cohort. Conclusion A fully automated ML model identifies area-derived LACI at end-diastole as a robust feature associated with disease progression, providing improved risk stratification for pre-symptomatic HCM.
Antoine Olivier, Auriane Riou, T. D'humières et al.· Frontiers in Cardiovascular...· 0 citations
BACKGROUND
Quality control (QC) in echocardiography is crucial but is often subjective, retrospective, and labor-intensive. Artificial intelligence (AI) offers a path to objective, real-time assessment, yet many systems lack clinical interpretability and broad applicability.
PURPOSE
To develop, validate, and clinically deploy an interpretable, rule-based AI system for the real-time quality assessment of standard echocardiographic views.
MATERIALS AND METHODS
We first designed a novel, quantifiable scoring rubric for nine standard views, evaluating four key domains: visualized structures, cardiac axis, depth, and gain. This rubric was then automated using a modular AI pipeline, featuring a SlowFast-Echo model for view classification and specialized deep learning models (including SSD and U-Net) for domain-specific assessment. The system was developed on 2,966 videos from a single center, prospectively validated on a temporally distinct cohort of 1,801 videos against an expert-consensus reference standard, and externally validated across three publicly available external datasets(n=1,821 videos).
RESULTS
The view classification model achieved an average accuracy of 98.6%. In classifying overall image quality, the complete AI system demonstrated high agreement with expert consensus, achieving an accuracy of 95.0% on the prospective test set. High performance was maintained across all individual quality domains (accuracy 94.7%-98.7%). The system also showed robust generalizability from 91.7% to 92.3% accuracy across the publicly available external datasets and operated efficiently with a mean inference time of 303 ms per video, confirming its suitability for real-time clinical deployment.
CONCLUSION
We successfully developed and clinically deployed a comprehensive AI system that provides accurate, immediate, and interpretable feedback on echocardiographic quality. By translating expert criteria into an objective and automated framework for nine standard views, this tool demonstrates strong potential to standardize image acquisition, enhance diagnostic confidence, and improve the efficiency of both clinical practice and sonographer training.
Zhongqing Shi, Hanlin Cheng, Zhanru Qi et al.· Journal of the American Soci...· 0 citations
BACKGROUND
Accurate assessment of left ventricular outflow tract (LVOT) gradients is critical for hypertrophic cardiomyopathy management, yet Doppler-based measurements are technically demanding and require expertise. The objective of this work was to develop a multi-view deep learning model capable of classifying LVOT obstruction (>20 mm Hg) using routine 2-dimensional echocardiographic windows without reliance on Doppler imaging.
METHODS
We trained and externally validated a cross-attention-based video-to-video fusion framework that integrated EchoPrime-derived video representations from 3 standard transthoracic echocardiographic views to classify LVOT gradients.
RESULTS
Training was performed on a derivation cohort (N=1833) from a tertiary care system in the United States, with model performance evaluated on an internally held-out test set (N=275) and a Korean external validation cohort (N=46). Single-view baselines showed limited discrimination (external area under the receiver operating curves, 0.47-0.70). Conversely, the domain-specific foundational model (EchoPrime) achieved superior single-view performance (area under the receiver operating curves, 0.75-0.80 internal; 0.79-0.83 external), highlighting the importance of echo-specific pretraining and temporal modeling. The proposed multi-view fusion further enhanced predictive performance, with the late fusion model reaching an area under the receiver operating curve of 0.84 on the external cohort with significant population-shift.
CONCLUSIONS
These results suggest LVOT physiology is encoded in routine 2-dimensional imaging and can be leveraged for clinically relevant gradient classification without Doppler input. The proposed artificial intelligence-guided strategy demonstrates substantial cost savings compared with the screen-all approach. By integrating complementary spatial-temporal information across multiple views, our approach generalizes robustly across populations and may enable real-time decision support, extend LVOT assessment to portable or resource-limited settings, and complement Doppler-based evaluation for longitudinal hypertrophic cardiomyopathy management.
O. Crystal, J. Farina, I. Scalia et al.· Circulation Cardiovascular I...· 0 citations