Abstract 736: Deep learning response score using baseline and 12-week RECIST chest CTs enhances overall survival (OS) prediction in advanced NSCLC: external validation in a trial with dostarlimab

Background: Early response assessment and identification of patients (pts) with NSCLC likely to derive long-term benefit from immune checkpoint inhibitors (ICIs) are crucial for treatment planning and drug development. Methods: We developed a deep learning pipeline using a large multi-institute real-world dataset to generate a serial CT response score (SerialCTRS) from paired pre-treatment and 12wk scans, estimating probability of 1y OS. External validation applied SerialCTRS to an expansion cohort of a single-arm phase 1 clinical trial of dostarlimab as ≥2L therapy for advanced NSCLC (GARNET [cohort E], NCT02715284). OS hazard ratios (HRs) of SerialCTRS were compared to tumor volume change derived from manual segmentations and 12 wk RECIST 1.1 overall response using the same input scans. Results: Of 67 clinical trial pts, 49 were evaluable for all 3 models predicting OS. Matching group sizes to RECIST overall response, 13 pts (26%, the number with RECIST PD) had low probability of 1y OS (SerialCTRS 0.12-0.64), 21 pts (43%, number with SD) had medium probability (0.64-0.82), and 15 pts (31%, analogous to CR/PR) had high probability of 1y OS (0.83-0.90). HRs of adjacent categories predicting OS showed superior performance of SerialCTRS, especially for SD/medium vs CR/PR/high probability (HR 2.68 [95% CI 1.09-6.59]; Table). Continuous SerialCTRS predicted OS with a concordance index of 0.717 (0.733 in subset with RECIST 12 wk SD) and remained a significant predictor of OS in bivariable survival models controlling for known predictors of OS such as age, ECOG, stage at diagnosis (all n=54), and best overall response from previous therapy (n=49). Conclusions: Deep learning-based SerialCTRS, without manual annotation, improved prediction of OS vs RECIST and tumor volume change in the NSCLC cohort of the GARNET trial. Citation Format: Brenda F. Kurland, Chiharu Sako, Jing He, Marius de Groot, Taly G. Schmidt, Arpan A. Patel, Dwight H. Owen, Arya Amini, Brendan D. Curti, Ronan J. Kelly, Ray D. Page, Aurelie Swalduz, Jean-Paul Beregi, Jan Chrusciel, Stephane Sanchez, Richard Rosenberg, Jakob Weiss, An Liu, Olivier Gevaert, George R. Simon, Ravi B. Parikh, Alma Hart, Petr Jordan, Jasper van der Aart. Deep learning response score using baseline and 12-week RECIST chest CTs enhances overall survival (OS) prediction in advanced NSCLC: external validation in a trial with dostarlimab [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2025; Part 1 (Regular Abstracts); 2025 Apr 25-30; Chicago, IL. Philadelphia (PA): AACR; Cancer Res 2025;85(8_Suppl_1):Abstract nr 736.