Altis project uses AI to predict cancer progression

TORONTO – Altis Labs, Inc., a computational imaging company accelerating clinical trials with AI, announced that it is leading an international coalition focused on the development and implementation of digital twins in clinical trials. This initiative seeks to transform clinical trial design by speeding up timelines and reducing failure rates associated with bringing novel, efficacious cancer treatments to patients in need.

Altis’ computational imaging platform, Nota, allows biopharma sponsors to manage and automatically analyze imaging data from past and current clinical trials using prognostic AI models.

Clinical development teams use these AI models to predict disease progression for each patient enrolled in their clinical trial, generating a computational control arm of digital twins.

AstraZeneca and Bayer Pharmaceuticals are incorporating these predictions into their statistical analyses to quantify treatment effect earlier and more accurately, enabling prioritization of their most promising drug candidates to increase probability of late-stage success and reduce time to market.

“With a track record of building and operationalizing the world’s largest real-world cancer imaging database for AI research in collaboration with Canada’s top cancer centers and leading biopharma sponsors, we’re excited to leverage our cutting-edge AI tools to help improve patient outcomes,” says Felix Baldauf-Lenschen (pictured), founder and CEO of Altis.

The coalition is made up of Canadian health systems and leading academic institutions including Trillium Health Partners (THP) and the University of Calgary (UofC). Dr. Benjamin Fine, a radiologist and clinician scientist at THP’s Institute for Better Health (IBH), is leading this initiative via the AI Deployment and Evaluation (AIDE) Lab.

Oncologist and clinician scientist Dr. Omar Khan leads the project at the University of Calgary. Canadian data enabling company, SapienSecure is providing NLP tools for this initiative.

Global biopharmaceutical companies AstraZeneca and Bayer Pharmaceuticals are also participating in the initiative and are receiving early access to the AI models via Nota for four of their clinical trials.

This $5.7 million project leverages support from DIGITAL, Canada’s Global Innovation Cluster for digital technologies.

“Using AI-based digital twins to generate efficacy insight from imaging scans beyond reductionist tumor measurements that our industry has had to rely on for far too long is where we see so much potential to transform clinical development,” said Charles Glaus, PhD, who is senior director in Research and Early Development, Oncology, at Bayer Pharmaceuticals.

“We were drawn to work with Altis and their clinical partners based on their high quality data, published deep learning applications, and strong focus on what ultimately matters; that patients live longer and better lives.”

Guenter Schmidt, vice president of Image Data Sciences at AstraZeneca, noted “Clinical trials are crucial to help inform the effectiveness of therapies and also biological insights that further support our understanding of the underlying disease. It’s our responsibility to act on that insight and prioritize bringing the knowledge to the clinical and research community, as soon as possible. Advanced AI-based patient models such as digital twins will contribute to increasing the insight generated from clinical trial data.”

“This initiative brings together Canada’s homegrown AI technology and health systems to lead the implementation of state-of-the-art clinical research tools,” said Sally Daub, co-founder and chair of Altis. “Our goal is to transform therapeutic development and improve the quality, access, and cost-effectiveness of cancer care in Canada.”

About Altis Labs
Altis Labs is the computational imaging company advancing precision medicine. We believe that medical imaging is the richest source of untapped clinical insight. Biopharma companies use our software platform, Nota, to accelerate and de-risk all stages of clinical development by more accurately stratifying patients and quantifying treatment effect earlier. Trained on over 182 million real-world images with associated diagnostics, treatment information, and outcomes, AI models hosted on Nota predict clinically meaningful outcomes from existing imaging scans. Altis is proudly headquartered in Toronto, Canada. To learn more, visit www.altislabs.com.