American heart journal · 2026
Design of Screening Cardiometabolic Opportunities Using Transformative Echocardiography Artificial Intelligence (SCOUT-Echo-AI).
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.
Eusuff Sahir, Kim Jay, Fatima Zara, Yalcinkaya Dilek, Sahashi Yuki, Sandhu Alexander, Nguyen Long H, Ambrosy Andrew P, Cheng Paul P, Chang Stephanie T, Go Alan S, Ahmad Faraz S, Cheung Amanda, Cheng Susan, Kwan Alan C, Ouyang David
Аннотация
BACKGROUND: Steatotic liver disease (SLD) is highly prevalent among individuals with cardiovascular disease, but often remains undiagnosed until advanced sequelae such as fibrotic liver disease and hepatocellular carcinoma develop. Transthoracic echocardiography routinely captures incidental subcostal views of the liver that are not used clinically. The EchoNet-Liver algorithm uses artificial intelligence (AI) to predict the presence of liver disease based on routine clinical echocardiograms. Prospective evaluation in real-world practice is needed to understand the clinical utility and impact of AI-enabled opportunistic liver disease screening.
METHODS: The SCOUT-Echo-AI study is a single-arm, prospective, multicenter, open-label pragmatic interventional trial that will be conducted across six diverse U.S. healthcare systems (Kaiser Permanente Northern California, Stanford Healthcare, Cedars-Sinai Medical Center, University of California Los Angeles, Northwestern Medicine, and Massachusetts General Brigham). Routine echocardiograms will be analyzed by the EchoNet-Liver AI algorithm with an estimated enrollment of ∼3,000 patients. Treating clinicians or participants themselves will be notified of potential undiagnosed liver disease with site-specific workflows in place to ensure routine clinical care for definitive case confirmation. Primary outcomes will be SLD and fibrotic liver disease detection rates and positive predictive values within 12 months of AI identification. Pre-specified secondary outcomes will assess diagnostic accuracy against other gold-standard modalities, treatment initiation, time to diagnosis, and impact on other clinical events. Outcomes will be compared against historical usual-care and contemporary below-threshold cohorts.
CONCLUSION: SCOUT-Echo-AI is a prospective multicenter study evaluating the real-world impact of AI-enabled opportunistic liver disease screening using routine echocardiography.
METHODS: The SCOUT-Echo-AI study is a single-arm, prospective, multicenter, open-label pragmatic interventional trial that will be conducted across six diverse U.S. healthcare systems (Kaiser Permanente Northern California, Stanford Healthcare, Cedars-Sinai Medical Center, University of California Los Angeles, Northwestern Medicine, and Massachusetts General Brigham). Routine echocardiograms will be analyzed by the EchoNet-Liver AI algorithm with an estimated enrollment of ∼3,000 patients. Treating clinicians or participants themselves will be notified of potential undiagnosed liver disease with site-specific workflows in place to ensure routine clinical care for definitive case confirmation. Primary outcomes will be SLD and fibrotic liver disease detection rates and positive predictive values within 12 months of AI identification. Pre-specified secondary outcomes will assess diagnostic accuracy against other gold-standard modalities, treatment initiation, time to diagnosis, and impact on other clinical events. Outcomes will be compared against historical usual-care and contemporary below-threshold cohorts.
CONCLUSION: SCOUT-Echo-AI is a prospective multicenter study evaluating the real-world impact of AI-enabled opportunistic liver disease screening using routine echocardiography.