AbstractBackground:Sum of longest diameters (SLD) of target lesions per response evaluation criteria in solid tumors (RECIST) 1.1 is the standard measure of baseline (BL) disease burden, which plays an important prognostic role. Fully automated, artificial intelligence (AI) derived measures from BL computed tomography (CT) scans like imaging-based prognostication (IPRO) and lung volumetric tumor burden (VTB), generated by AI models trained on real-world imaging data, have shown promising association with overall survival (OS).Methods:BL CT scans acquired in MYSTIC (NCT02453282) were combined across trial arms and retrospectively analyzed. Patients with consent were included in this study. We compared the prognostic association of manually derived SLD with AI derived IPRO and lung VTB using concordance index (c-index), Kaplan-Meier methods, time-dependent area under the curve (TD-AUC), and standardized hazard ratios (HRs) from Cox proportional hazards models.Results:BL CT scans of 672 patients had available quantifications for comparative analysis. Median OS (mOS) was 12.2 months, 194 patients (29%) were female, 106 (16%) were non-smokers, 193 (29%) had squamous cell carcinoma and 201 (30%) had PD-L1 > 50%. SLD, IPRO, and lung VTB, yielded c-indexes of 0.56 (95% CI: 0.54-0.59), 0.61 (0.59-0.64), and 0.57 (0.54-0.60), respectively. Results are shown in Table 1.Conclusions:BL IPRO has greater association with OS than SLD, and VTB shows similar prognostic association as SLD. AI derived quantifications offer enhanced stratification and may provide an efficient way to analyze treatment effects.Citation Format:Harish RaviPrakash, Qin Li, Kedar Patwardhan, John Riskas, Shahid Haider, Oleksandra Samodorova, Jay Hennessy, Vignesh Sivan, Felix Baldauf-Lenschen, Omar Khan Comparing prognostic association of manual vs. artificial intelligence derived quantifications from baseline computed tomography scans in MYSTIC, a global phase 3 trial for treatment of metastatic non-small cell lung cancer [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 5781.