Chicago, Illinois: May 29-June 2, 2026. Altis Labs, Inc. ("Altis") is announcing results presented at the American Society of Clinical Oncology (ASCO) Annual Meeting 2026 evaluating whether the depth of response measured by Imaging-based Prognostication (IPRO)-α correlates with overall survival (OS) in patients with advanced non-small cell lung cancer (aNSCLC). IPRO-α is a fully automated AI model that generates a survival prediction from a thoracic CT scan.

The study evaluated IPRO-α in an external real-world dataset of 85 aNSCLC patients treated with first-line (1L) pembrolizumab monotherapy at 17 cancer centers, each with a baseline scan and a week 8 (± 4 weeks) scan after treatment initiation. Median patient age was 68 years (IQR 62–75), 42.3% (n=36) were male, and median OS for the cohort was 20.4 months (95% CI 10.5–28.3). Patients were grouped by percent change from baseline (CFB) in IPRO-α: no response (≤0%), intermediate response (0–40%), and high response (>40%). After landmarking at the week 8 scan, Kaplan–Meier and Cox proportional hazards analyses compared OS in the intermediate and high response groups against the no response group.

Key findings:

• No response (≤0% CFB): mOS 10.5 months (95% CI 9.1–23.7).
• Intermediate response (0–40% CFB), 22 patients (25.9%): mOS 27.0 months (95% CI 13.3–60.6), HR 0.57 (95% CI 0.32–1.00, p=0.05).
• High response (>40% CFB), 8 patients (9.4%): mOS 50.8 months (95% CI 14.6–not reached), HR 0.36 (95% CI 0.15–0.90, p=0.029).
• OS increased with the depth of IPRO-α response, with greater improvements in IPRO-α associated with progressively longer OS.

RECIST 1.1 defines response and progression in randomized clinical trials (RCTs). These results indicate that IPRO-α response detects an OS signal as early as week 8, and support its potential as an outcome measure and early endpoint in this population. Future work will focus on validation in RCTs and comparisons to RECIST-based surrogate endpoints.

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, treatment, and outcomes data. Top 20 biopharmas use Altis' AI models to more confidently analyze data from phase 1–4 clinical trials and 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.

‍