Butterfly Network (NYSE:BFLY) today announced its role in new research utilizing AI and machine learning (ML) to detect aortic stenosis (AS).
The study demonstrated ML models’ potential to support early AS detection using handheld ultrasound devices. Investigators at Tufts Medical Center conducted the study and published findings in European Heart Journal – Imaging Methods and Practice.
Butterfly said findings proved that an ML model fine-tuned for use on its Butterfly iQ+ devices can achieve high accuracy in identifying AS. Outcomes support the value of ML model development and portable screening for earlier detection of the life-threatening condition.
The study validated that ML trained on hospital-grade ultrasound performed well when adapted to the Butterfly device.
Additionally, Butterfly Network says it released the latest expansion of its Butterfly ScanLab AI-powered ultrasound education app. This expansion — the Aorta Exam Protocol — utilizes animations, anatomical labeling and a quality indicator. It teaches users how to scan the abdominal aorta and recognize normal anatomy.
With this training, users can use point-of-care ultrasound (POCUS) to detect life-threatening conditions like abdominal aortic aneurysms (AAA) and dissections. The company designed it for ease of use on an iPad and included it in every Butterfly membership, compatible with existing probes.
“Early detection saves lives, but access to imaging remains a major barrier. This work is about democratizing diagnostics,” said Joseph DeVivo, president, CEO, and chair of Butterfly Network. With AI and education working hand in hand, we’re empowering more providers to deliver proactive care in places that were never possible before.”
