Bunkerhill Health Secures FDA Clearance for AI Tool to Detect Mitral Annular Calcification on Routine CT Scans

Bunkerhill Health, a San Francisco-based biotechnology company, has received FDA clearance for its new artificial intelligence algorithm, Bunkerhill MAC, designed to detect and quantify mitral annular calcification (MAC) on routine, non-gated CT scans. The clearance marks a first-of-its-kind approval, making Bunkerhill MAC the first AI model authorized by the FDA to identify MAC—a known marker of cardiovascular risk.

Developed using imaging data from more than 25 academic medical centers, the AI tool aims to make the identification of MAC more consistent and scalable, especially since the condition is often underrecognized despite its clinical importance.

“MAC may be missed on imaging, but it carries prognostic value for cardiovascular risk and procedural outcomes,” said Dr. Alexander Sandhu, assistant professor of cardiology at Stanford University School of Medicine, which contributed data to the development of the algorithm. “A tool that can automatically identify and quantify MAC on routine chest CT scans gives us a way to capture this information consistently and at scale, which could help guide decision-making and research across cardiology and structural heart care.”

The technology is now part of Carebricks, Bunkerhill Health’s generative AI platform that integrates various clinical AI models into standard workflows. Carebricks is already being used at major health systems, including Cleveland Clinic and Mayo Clinic, and is designed to support a wide range of applications such as referral prioritization and identifying actionable clinical findings.

“FDA clearance of this algorithm is a landmark not just for Bunkerhill, but for how we use routine data to advance cardiac care,” said Nishith Khandwala, co-founder and CEO of Bunkerhill Health. “By making MAC quantification available at scale through routine CT scans, we’re giving clinicians a new tool to better understand risk and tailor patient care, all embedded seamlessly into the workflows they already use.”

MAC, which involves calcium buildup in the ring-like structure surrounding the mitral valve, has been linked to worse outcomes in cardiovascular interventions. Its early detection can influence procedural planning, risk assessment, and long-term patient management. Until now, quantifying MAC has required specialized imaging or was often noted incidentally.

Bunkerhill Health, founded in 2021 by Khandwala and David Eng, grew out of Stanford University’s Center for Artificial Intelligence in Medicine and Imaging. The company has drawn significant investment from backers including Sequoia Capital, Optum Ventures, and SciFi VC.

With FDA clearance secured, Bunkerhill MAC positions itself as a powerful example of how routine imaging data can be leveraged with AI to unlock new insights and improve cardiovascular care—without disrupting existing clinical workflows.