European heart journal. Digital health · 2026
Automated assessment of right ventricular systolic function from coronary angiograms with video-based artificial intelligence algorithms: development, validation, comparison against humans, and prospective deployment.
СтатьяНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Fawzi Fatima Zahra, Menkovic Istok, Dostie Nicolas, Tremblay-Gravel Maxime, Parent Marie-Claude, Asslo Gabriel, Tanguay Jean-François, Marquis-Gravel Guillaume, Ansari Minhaj, Barrios Joshua P, Tison Geoffrey H, Delfrate Jacques, Avram Robert
Аннотация
AIMS: Right ventricular systolic function (RVSF) is a critical determinant of cardiovascular outcomes, yet assessment during coronary angiography remains challenging without prior imaging. We developed and validated DeepRV, a deep learning model predicting RVSF from routine coronary angiograms.
METHODS AND RESULTS: DeepRV, a video-based deep neural network, was developed using 8053 coronary angiography studies from 6923 patients at Montreal Heart Institute (2017-23), with RVSF determined by echocardiography. The model was externally validated at the University of California, San Francisco, and prospectively deployed during primary percutaneous coronary intervention (PCI) for ST-segment elevation myocardial infarction (STEMI). In the internal test set (n = 1586; 10.5% reduced RVSF), DeepRV achieved area under the receiver operating characteristic curve (AUROC) 0.80 [95% confidence interval (CI): 0.76-0.84], sensitivity 70.5%, specificity 78.5%, and negative predictive value 95.8%. External validation demonstrated AUROC 0.75 (95% CI: 0.72-0.77) on the UCSF dataset (n = 2247 studies; 30% reduced RVSF). Prospective deployment of DeepRV during STEMI cases at our institution (n = 82) achieved AUROC 0.83 (95% CI: 0.71-0.93) using post-PCI angiogram with a median 5.1 s inference time. In a human performance evaluation (n = 200), artificial intelligence (AI) assistance improved accuracy of identifying RVSF for cardiologists (72.1-77.6%) and medical students (43.5-64.0%). Artificial intelligence alone achieved the highest accuracy (79.5%) and sensitivity (70.0%), while cardiologists with AI achieved the highest specificity (84.6%).
CONCLUSION: DeepRV enables automated RVSF assessment from routine coronary angiograms and enhances diagnostic accuracy across experience levels. Real-time inference and open-weight availability support its potential as a point-of-care tool for risk stratification during coronary angiography.
METHODS AND RESULTS: DeepRV, a video-based deep neural network, was developed using 8053 coronary angiography studies from 6923 patients at Montreal Heart Institute (2017-23), with RVSF determined by echocardiography. The model was externally validated at the University of California, San Francisco, and prospectively deployed during primary percutaneous coronary intervention (PCI) for ST-segment elevation myocardial infarction (STEMI). In the internal test set (n = 1586; 10.5% reduced RVSF), DeepRV achieved area under the receiver operating characteristic curve (AUROC) 0.80 [95% confidence interval (CI): 0.76-0.84], sensitivity 70.5%, specificity 78.5%, and negative predictive value 95.8%. External validation demonstrated AUROC 0.75 (95% CI: 0.72-0.77) on the UCSF dataset (n = 2247 studies; 30% reduced RVSF). Prospective deployment of DeepRV during STEMI cases at our institution (n = 82) achieved AUROC 0.83 (95% CI: 0.71-0.93) using post-PCI angiogram with a median 5.1 s inference time. In a human performance evaluation (n = 200), artificial intelligence (AI) assistance improved accuracy of identifying RVSF for cardiologists (72.1-77.6%) and medical students (43.5-64.0%). Artificial intelligence alone achieved the highest accuracy (79.5%) and sensitivity (70.0%), while cardiologists with AI achieved the highest specificity (84.6%).
CONCLUSION: DeepRV enables automated RVSF assessment from routine coronary angiograms and enhances diagnostic accuracy across experience levels. Real-time inference and open-weight availability support its potential as a point-of-care tool for risk stratification during coronary angiography.