Vara’s mission is to make data-driven breast cancer screening accessible to everyone, everywhere. To that end, we’ve built an intelligent platform that brings state-of-the-art artificial intelligence to routine breast screening, and we’re working with entrepreneurs and healthcare providers worldwide to bring a data-driven, standardized breast cancer screening approach to the countries that need it the most to need.
Better breast cancer screening is every woman’s right, yet millions are left behind by a lack of effective, organized programs. Of the 700,000 global deaths caused by breast cancer each year, ~70% occur in low- and middle-income countries. In part due to an inability to diagnose early, resulting from a lack of technology, awareness and specialized screening radiologists.
By toning down much of the human subjectivity associated with reading mammography results—and reducing the repetitive work that radiologists routinely face—we make such screenings more effective, personal, and accessible. Regardless of the existing infrastructure. This approach allows us to provide quality healthcare focused on delivering the best, measurable outcomes for women everywhere.
What do you think makes this company unique?
Our technology, approach, clinical experience and mindset make Vara unique.
First, Vara is not just an algorithm, it is a full-stack platform. It integrates AI and automation into every step of the breast cancer screening workflow. It consolidates previously fragmented processes into one place, with a focus on improving efficiencies, enabling remote collaboration, and democratizing access to better screening programs.
Second, Vara AI takes a complementary rather than competitive approach to radiologists. Other AI solutions focus on one-size-fits-all models to replace radiologists. It has been shown that such approaches are lacking. Instead, our Decision Referral Pathway supports radiologists. It pre-screens normal mammograms, pre-populates structured reports, and post-screens mammograms for potentially missed exams, all with very high reliability. We’re refining the way the AI and individual radiologists interact to optimize joint performance and enable screening radiologists to focus their attention on potentially suspicious exams.
Third, the Vara platform captures real-world data in clinical use. Vara was developed together with screening radiologists in one of the world’s leading population-based national breast cancer screening programs in Germany. It has been trained and evaluated on more than 7 million images to date – one of the largest datasets of its kind in the world – and our AI is continuously monitored to provide screening radiologists with key performance metrics. For each woman diagnosed via Vara, we follow the patient’s care pathway after screening to assess the impact of AI on population health metrics such as recall rates, biopsy results, and mortality.
Finally, we are challenging the health care status quo. We believe in personal responsibility, flat hierarchies, direct and transparent communication and a culture of respect. This mindset and team culture has enabled us to build, establish and scale our full-stack platform in just under three years.
How has the company developed in recent years?
The decision-referal approach of the Vara AI platform is now used in 30% of all screening units in Germany. As part of our global mission, we recently established screening units in Mexico and Greece in partnership with local healthcare providers in those regions. With such partners, we demonstrate how we can leverage existing healthcare infrastructure to enable them to leapfrog their current setup to a state-of-the-art, standardized screening service.
Our team has doubled to 30, and we have appointed global experts in radiology, including Professor Katja Pinker-Domenig, who became our Senior Medical Advisor, and Stephan Dreier as Chief Revenue Officer. We also have collaborations with renowned academic institutions in the US and Europe, such as Memorial Sloan Kettering Cancer Center, University of Cambridge, Karolinska Institute and Cancer Registry of Norway.
In particular, Vara’s AI performance shows promise in terms of reproducibility and generalization. We have two important peer-reviewed publications under review, both large retrospective studies, and we have just started the first prospective study in Germany to show the effect of Vara in routine clinical practice.
What can we expect from Vara in the future?
Over the next four years, we aim to open 1,000 screening centers in countries that currently do not offer screening. Together with partners, this means continuing to scale our platform across Latin America while seeking new partnerships with healthcare providers in other regions.
We have and will continue to deepen the capabilities of our AI by developing it to not only read the current mammography exam, but also to review previous exams for even more performance gains. This will help us in our long-term vision of detecting any deadly breast cancer early.
https://techround.co.uk/interviews/a-chat-with-jonas-muff-vara/?utm_source=rss&utm_medium=rss&utm_campaign=a-chat-with-jonas-muff-vara A conversation with Jonas Muff, CEO of the AI Breast Cancer Screening Platform: Vara