Automated Echocardiographic Detection of Congenital Heart Disease Using Artificial Intelligence
EchoFocus-CHD is a multi-task AI model that automatically detects 12 critical and 8 non-critical congenital heart lesions on standard echocardiography. On an external cohort the model matched expert interpretation — with the promise of extending scarce paediatric echo expertise beyond academic centres. A concrete example of where AI-assisted imaging can rapidly deliver clinical value in primary care and smaller hospitals.
Summary
Background: Delayed or missed diagnosis of congenital heart disease (CHD) contributes to excess pediatric mortality worldwide. Echocardiography (echo) is central to diagnosing and triaging CHD, yet expert interpretation remains a scarce and maldistributed global resource. Artificial intelligence (AI) offers the potential to democratize diagnostics and extend expert-level interpretation beyond large academic centers, but its application in CHD remains underexplored.Methods: We developed EchoFocus-CHD, an AI-enabled model for automated detection of 12 critical and 8 non-critical CHD lesions, individually and as composites. The composite critical CHD outcome was the primary endpoint. The model expands on a multi-task, view-agnostic architecture (PanEcho) with a transformer encoder to improve focus on relevant echo views. The model was internally trained (80%) and tested (20%) on the first echo per patient from Boston Children’s Hospital (BCH), with further evaluation on a referral cohort
Join us
Join the Global Primary Care Cardio Network. Membership is free.
Would you like to tell us more about yourself?
Interests
We will send you an email with a link to confirm your registration.
