Vara has secured a European CE mark for an autonomous, artificial intelligence (AI)-powered breast cancer screening triage tool – marking the first time a device of this nature has secured an authorisation globally.
Designated as a Class IIb medical device under the EU’s medical device regulation (MDR), Vara’s designed its newly CE-marked autonomous triage tool to facilitate organised population screening. This means the technology can identify and stratify images based on if the breast is considered normal or needs further assessment by a radiologist.
Go deeper with GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
To ensure autonomous triage is safe for use in healthcare, Vara created a specific safety system suitable for the job, which the company says played a foundational role in its CE certification. Dubbed ATMON, this technology allows for the real-time supervision of the autonomous AI to ensure accuracy, and is based on seven years of continuous, real-world monitoring.
European regulators authorised Vara’s autonomous triage system based on the results of the prospective PRAIM study (NCT04778670), in which the tool’s breast cancer detection rate was proven “noninferior and even statistically superior” to the control group. The study evaluated the triage system’s screening potential across 461,818 asymptomatic women aged between 50 and 69 years of age across 12 sites in Germany.
Following ATMON’s CE certification, Vara will roll out the autonomous triaging tool to screening programmes across Europe. Alongside this, the company will also license out ATMON independently of the autonomous triage system – meaning healthcare providers could potentially integrate the safety technology when using another autonomous AI breast cancer screening tool.
“Studies have shown that AI can improve cancer detection. But even the best AI model’s performance can shift once it operates outside the controlled conditions of a study,” said Jonas Muff, CEO and co-founder of Vara.
“For AI to deliver its positive impact on patient outcomes, we need to notice when this happens. We believe our ATMON system can be a template for deploying AI safely across healthcare,” Muff added.
AI’s role in cancer screening to expand
Vara secures this CE mark as AI increasingly makes its foray into the healthcare space, with some promising that the technology can counter the shortage of trained screening and diagnostic specialists in areas like oncology, while facilitating early disease detection to improve treatment outcomes.
While AI-assisted breast cancer screening is becoming more commonplace across Europe and the US, some have raised concerns around the technology’s accuracy in the face of model shift – a phenomenon where the reliability of an AI system decreases as the technology is exposed to data different than what it was trained on.
Despite these concerns, GlobalData predicts that AI-powered digital health solutions such as screening systems will play a pivotal role in championing the digital transformation of oncology, contributing to the segment’s 6% compound annual growth rate (CAGR) in Europe between 2025 and 2035.
Previously, Shamreen Parween, medical devices analyst at GlobalData, noted that AI-driven software plays a key role in enhancing clinical imaging by “enabling more efficient and standardised image analysis,” helping to identify imaging finding that may otherwise remain overlooked.
“The continued expansion of AI-enabled digital health solutions, supported by growing regulatory approvals, and sustained investment in digital health platforms, is expected to drive adoption across parts of Europe,” Parween commented, adding that these developments could further build the role of digital health in creating a more connected, data-driven, and patient-centric healthcare ecosystem.
