Abstract 624: Associations between G8 geriatric screening score, Charlson Comorbidity Index, AI-based age phenotype, and overall survival in older adults with stage I-II NSCLC

Abstract Purpose: Comprehensive geriatric assessment improves outcomes among older adults with early-stage non-small cell lung cancer (NSCLC), but may be unfeasible in some settings. We therefore evaluated whether a geriatric vulnerability model incorporating retrospectively abstracted G8 score (G8), Charlson Comorbidity Index (CCI), and FaceAge, a novel AI-based aging measure, was associated with all-cause mortality or falls risk among older adults undergoing stereotactic body radiation therapy (SBRT) for stage I-II NSCLC. Methods: We reviewed the records of patients aged ≥65 with stage I-II NSCLC undergoing SBRT at our institution from 06/01/09-03/31/23. We abstracted demographics, performance status (Eastern Cooperative Oncology Group (ECOG) score), oncologic history, G8 and CCI domains, falls risk (Morse Fall Scale or Strategies to Reduce Injuries and Develop Confidence in Elders (STRIDE) screening tool), and time-to-death from any cause. We used facial photographs collected at SBRT simulation to calculate FaceAge, an AI-based estimate of biological age which uses deep learning facial analysis to capture differences in individual aging rates. We examined associations between a vulnerability model incorporating 1) G8, 2) CCI, and 3) FaceAge as independent factors and the outcomes of 1) all-cause mortality and 2) falls risk. Cox and logistic regression models were adjusted for age, sex, cancer stage, performance status, and covariates significant to p<0.10 in univariate analyses. Results: Among 708 patients (median age 76.2 years, 60.7% female, median stage IA), performance status limitations (median ECOG 1, IQR 1-2), high comorbidity burden (median CCI 7, IQR 6-8), and poor G8 scores (median 12.5, IQR 11.5-13.5) were common. Patients also commonly had elevated FaceAges, appearing a median of 2.6 years older than their chronological age. In an adjusted Cox regression model, worse performance on all three geriatric vulnerability measures was independently associated with higher all-cause mortality (HRFaceAge 1.04, 95% confidence interval (CI)FaceAge 1.02-1.06, p=0.002; HRG8=1.15, 95%CIG8=1.08-1.22, p<0.001; HRCCI = 1.14, 95%CICCI=1.06-1.22, p<0.001). In an adjusted logistic regression model, only worse performance on the G8 was associated with elevated falls risk (HR=1.19, 95%CI 1.05-1.35, p=0.006). Conclusions: In older adults with stage I-II NSCLC, a multimodal geriatric vulnerability measure was associated with all-cause mortality, identifying patients who might benefit from additional services. G8, but not FaceAge or CCI, also was associated with falls risk. All models leveraged solely data already collected as part of routine care, suggesting implementation could be accomplished in health systems without added burden. Citation Format: Leah L. Thompson, Priya M. Amin, Sanjana Shah, Sarah M. Lipson, Grace Lee, Nancy Anabaraonye, Austin T. Gregg, Sharon Jiang, Emilie Baxter, Caterina Florissi, John He, Anurag Saraf, Ryan D. Nipp, Dennis Bontempi, Hugo JWL Aerts, Fridolin Haugg, Raymond H. Mak. Associations between G8 geriatric screening score, Charlson Comorbidity Index, AI-based age phenotype, and overall survival in older adults with stage I-II NSCLC [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 624.