The algorithm was trained on more than 1 million echocardiograms and their corresponding clinical interpretations. Most previous AI models were trained on tens of thousands of examples, David Ouyang, MD, a corresponding author of the study, said in an April 30 health system news release.
The AI, described in Nature Medicine, suggests the model can identify the same patient across multiple videos, studies and time points and recognize clinically important changes in a patient’s heart. It can assess cardiac function using heart images, identify implanted devices from echocardiogram images and can develop preliminary text interpretation of echocardiogram images.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
