AUS
NZ
UK
CA
USA
FRA
GER
ESP
ITA
NLD
PRT
SWE
GRC
IND
POL
BRA
ZAF
RUS
CHN
UAE
Altis's AI Model Outperforms RECIST 1.1 in Predicting Overall Survival
The results, showcased at the European Lung Cancer Congress (ELCC) 2025 in Paris, demonstrate that IPRO-Δ enhanced survival prediction compared to standard RECIST 1.1 blinded independent central review.
IPRO-Δ Enhances Prediction of Overall Survival in aNSCLC
The analysis done independently by AstraZeneca details imaging and survival data from patients enrolled in the control arm of the MYSTIC trial. By applying IPRO-Δ to baseline and initial follow-up (week 6) CT imaging:
• Responders per IPRO-Δ had significantly better OS compared to subjects with IPRO-Δ stable disease (HR=0.54, 95% CI: 0.31-0.92), while responders per RECIST 1.1 had no better OS than subjects with RECIST stable disease (HR=1.10, 95% CI: 0.70, 1.77).
• Stable disease subjects per RECIST 1.1 were further stratified into subgroups by IPRO-Δ, revealing better association with OS.
• IPRO-Δ may provide a more clinically meaningful imaging endpoint in aNSCLC trials while offering instantaneous, objective, and reproducible quantifications from readily available imaging data.
"Our collaboration with AstraZeneca underscores the power of AI-based endpoints to improve early estimation of treatment effects," said Felix Baldauf-Lenschen, CEO of Altis Labs. "These findings showcase IPRO-Δ’s potential to accelerate clinical development with a stronger predictor of OS, the gold standard measure of efficacy in solid tumor trials."
Altis trained IPRO-Δ to predict survival from radiology scans using its proprietary, multimodal database spanning 200,000+ cancer patients with longitudinally linked imaging, clinical, molecular, treatment, and 500,000+ patient years of outcomes data. When applied to scans acquired in clinical trial settings, IPRO-Δ offers drug developers a novel measure to estimate treatment effects using existing data.
Advancing AI in Oncology Drug Development
The findings support the growing evidence that AI-powered imaging endpoints have the potential to enhance drug developers’ ability to objectively predict differences in long-term outcomes of clinical trial subjects.
The results will be presented at ELCC 2025, Poster 103P: Enhancing survival prediction in advanced non-small cell lung cancer: A comparison of artificial intelligence (AI)-derived prognostication and RECIST assessments in the MYSTIC Phase 3 trial.
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 biopharma 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 [email protected].
Felix Baldauf-Lenschen
Altis Labs, Inc.
email us here
Legal Disclaimer:
EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.
