FDA Says AI for CTEPH Pattern Recognition Is Breakthrough Device

Samara Rosenfeld
DECEMBER 03, 2018

This image has been altered. Licensed by Minerva Studio - stock.adobe.com.

The U.S. Food and Drug Administration (FDA) granted breakthrough device designation to the artificial intelligence (AI) software for chronic thromboembolic pulmonary hypertension (CTEPH) pattern recognition being developed by Bayer and Merck.
 
Software development of the AI system relies on using deep learning by identifying signs of CTEPH in CTPA scans, according to a release. The AI software processes image findings of cardiovascular, lung perfusion and pulmonary vessel analyses in combination with the patient’s history of pulmonary embolism (PE).

>> WATCH: PX: Can AI Be Smarter Than Humans?
 
CTEPH is a rare form of pulmonary hypertension that affects an estimated eight to 40 people per million. It is difficult to diagnose, as its symptoms are similar to other lung diseases. Computed tomography pulmonary angiography (CTPA) and ventilation/ perfusion scans (V/Q scans) are diagnostic models used to detect CTEPH.
 
Because radiologists often have the first opportunity to identify CTEPH in patients, it’s vital to recognize CTEPH indicators on CTPA images.
 
The FDA’s breakthrough device program is designed to help patients with life-threatening or irreversibly debilitating diseases have timely access to devices and breakthrough technology by expediting their development, assessment and review.
 
“Bayer is looking forward to leveraging our expertise in radiology to develop a software to support radiologists and treating physicians in the complex diagnostic decision-making process of this rare disease,” said Olaf Weber, DVM, head of radiology research and development for Bayer AG’s Pharmaceuticals Division.
 
Weber hopes that awareness of CTEPH and AI software for clinical decision support will eventually assist in diagnosing patients more quickly and reliably, allowing earlier treatment.
 
According to the release, one out of every 25 people who had a PE could go on to develop CTEPH. Symptoms include shortness of breath, edema, fatigue and chest pain, which are similar to more common diseases, often resulting in a delayed diagnosis of CTEPH.
 
If successful, the AI software could be deployed via Bayer’s Radimetrics, an informatics technology platform that connects contrast medium with injector and scan information to provide important insights.

“Bayer and (Merck) are in a worldwide collaboration in the field of sGC (soluble guanylate cyclase) modulators with the goal to fully evaluate this therapeutic class in areas of unmet medical need,” the release said.

Get the best insights in healthcare analytics directly to your inbox.

Related
AI Struggles Across Health Systems, Needs Wide-Range Testing
How AI Is Shaking Up Healthcare, Beyond Diagnostics
Why Data and Analytics Could See the Biggest Increase in Technology Spend in 2018
 

SHARE THIS SHARE THIS
12
Become a contributor