Altis Labs Unveils New AI-Powered External Control Arm Product Offering at ISPOR 2025

AI-matched digital twins for MYSTIC trial participants emulated the control arm and overall survival treatment effects.

MONTREAL, QUEBEC, CANADA, May 15, 2025 /EINPresswire.com/ -- Altis Labs, Inc. (“Altis”) will present findings at ISPOR 2025 demonstrating how real-world digital twins (rwDTs) can replicate control arm outcomes in AstraZeneca’s randomized controlled Phase 3 MYSTIC trial in metastatic non-small cell lung cancer (mNSCLC). These results support the launch of Altis’ new product offering that enables clinical development teams to generate external controls with AI applied to comprehensive real-world imaging + clinical + outcomes data.

Altis applied MYSTIC’s eligibility criteria to its multimodal real-world data to identify historical patients treated with relevant standard-of-care (SOC) treatment. AI models processed the real-world baseline CT scans and quantified thousands of spatial imaging biomarkers representing total tumor burden, body composition, and other prognostic features. Using baseline imaging characteristics of each MYSTIC subject, “matching” rwDTs were identified to generate an External Control Arms (ECAs).
AstraZeneca independently evaluated the survival outcomes of the ECAs and compared them to the MYSTIC trial arms, concluding that the ECAs successfully emulated the actual control arm and yielded consistent treatment effect estimates.

“CT Imaging – a 3D reconstruction of the entire patient anatomy – is the most comprehensive data modality already being used in clinical care and oncology trials,” said Felix Baldauf-Lenschen, CEO of Altis. “It’s no surprise that AI applied to this rich data alone can match patients’ baseline characteristics to emulate efficacy readouts.”

"These findings highlight the potential for imaging-based digital twins to serve as robust external comparators in oncology clinical trials," said the presenting author, Dr. Omar Khan, a Clinical Assistant Professor in the Cumming School of Medicine at the University of Calgary and Medical Oncologist at the Arthur J.E. Child Comprehensive Cancer Centre. "This approach is particularly relevant to help enhance single-arm trials, where comparative evidence is often limited."

Altis’ ECA: A New Tool for Smarter Evidence Generation
The newly launched ECA product enables sponsors to generate external controls using their clinical trial imaging data and Altis’ real-world imaging data + associated survival outcomes. Sponsors can use these ECAs in various ways:
• Benchmarking efficacy signal in single-arm trials
• Augmenting a control arm to increase statistical power in RCTs
• Real-world external comparators to inform reimbursement strategy

Altis’ models are trained on a proprietary dataset of over 200,000 cancer patients with longitudinal imaging, demographic, diagnostic, treatment, and survival outcomes data, enabling robust matching.

The full results are featured at ISPOR 2025, Poster MSR147: Evaluating Imaging Artificial Intelligence (AI) Matching Real-World Digital Twins (rwDTs) Into an External Control Arm (ECA) for MYSTIC: A Phase 3 Clinical Trial in Metastatic Non-Small Cell Lung Cancer (mNSCLC).

About Altis Labs
Altis Labs is the computational imaging company accelerating clinical trials with AI. Altis has trained proprietary AI models on the industry's largest multimodal training database spanning over 200 million longitudinal images linked to clinical, molecular, and outcomes data. Top 20 biopharmas use Altis’ AI models to more confidently analyze data from phase 1-4 clinical trials so that they can bring the most effective novel treatments to patients sooner.

For more information, visit www.altislabs.com, follow @AltisLabs on social media, or email info@altislabs.com.

Felix Baldauf-Lenschen
Altis Labs, Inc.
email us here
Visit us on social media:
LinkedIn
X