Study to test if non-specialists can capture quality echos using AI
A new study aims to evaluate whether medical professionals with no ultrasound experience can use artificial intelligence (AI) software to capture high-quality echocardiograms, potentially opening the door to greater testing in primary care settings.
"Deep learning will have a profound impact on cardiac imaging in the future, and the ability to simplify acquisition will be a tremendous advance to bring echocardiograms to the point-of-care in primary care offices," Patrick M. McCarthy, MD, the study’s principal investigator and the chief of cardiac surgery at Northwestern Memorial Hospital, said in a press release.
The trial is the first to test whether AI-guided ultrasound can be acquired by certified medical assistants, whose clinical duties are typically limited to taking patient medical histories and performing basic laboratory tests, according to the release.
Northwestern Medicine partnered with Bay Labs for the study, which is funded in part by a $25 million gift from the Bluhm Family Charitable Foundation formed by Chicago philanthropist and real estate developer Neil G. Bluhm. The first participant has been enrolled and the investigators plan to include about 1,200 patients from multiple Northwestern Medicine sites.
Bay Labs’ EchoGPS—which is the ultrasound guidance software that will be tested into the study—is currently available only for investigational use. The company’s EchoMD application, approved by the FDA in June, automates clip selection and the calculation of left ventricular ejection fraction from captured images.
"The EchoGPS and EchoMD product suite has the potential to transform how cardiovascular care can be delivered in healthcare systems," Charles Cadieu, Bay Labs’ co-founder and CEO, said in the release. "Incorporating our AI software with deep learning technology into clinical practice could allow non-specialist medical professionals to acquire images to support cardiologist interpretation and clinical decision-making and may lead to improved patient outcomes through earlier detection and monitoring."
The study—dubbed “SHAPE: Seeing the Heart with AI Powered Echo”—will specifically test whether those non-specialists can acquire diagnostic quality echocardiograms with EchoGPS. It will also evaluate whether those images can be reviewed by cardiologists along with EchoMD results to detect more patients with heart disease compared to a standard physical exam with electrocardiography.
Daniel joined TriMed’s Chicago editorial team in 2017 as a Cardiovascular Business writer. He previously worked as a writer for daily newspapers in North Dakota and Indiana.