NCOG-48. CT SCAN COMPOSITE SCORE CAN IDENTIFY GLIOBLASTOMA PATIENTS WITH WORSE OUTCOMES

Abstract OBJECTIVE Obesity is a risk factor for many cancer types including glioblastoma multiforme (GBM). We used CT body composition analyses to construct a sex-specific composite score that would optimally predict overall survival in GBM. METHODS Using a retrospective institutional cohort, we performed single slice (L3) and volumetric (L1-L5) automated body segmentation analyses on abdominal and pelvic computed tomography (CT) scans performed within 1 month of diagnosis of GBM. Multivariable Cox proportional hazards models were then used to identify variables that were independently associated with GBM overall survival. Lastly, a learning-tree algorithm was implemented to identify the relative importance of body composition metrics using a XGBoost-powered learning model. These weights were used to create sex-specific composite CT scan scores of protective and predisposing factor with relation to GBM survival. A log-rank pairwise t-test was used to compared GBM survival across patient groups stratified based on these CT composite scores. RESULTS Higher relative inter/intramuscular adipose tissue volume (HR(95%CI):1.9(1.01-3.06), p=0.02), visceral adipose tissue volume (HR(95%CI):2.1(1.04-4.1), p=0.04) and aortic calcification volume (HR(95%CI):2.6(1.2-5.5), p<0.001) were associated with lower GBM overall survival, while higher subcutaneous adipose tissue volume (HR(95%CI):0.4(0.2-0.8), p=0.02), iliopsoas muscle volume (HR(95%CI):0.4(0.2-0.9), p<0.001), and trabecular bone density (HR(95%CI):0.4(0.1-0.8), p=0.003) were predictive of higher GBM OS (p-value of all tests <0.05). Using quartiles of the CT scan composite predisposing and protective scores, we were able to stratify male and female participants with significantly different outcomes with regards to GBM OS (Figure). Male and female participants with higher burden of predisposing factors had significantly lower chances of survival compared to those with lower cumulative burden of these factors (Figure, p-value Q4 vs. Q1 males< 0.01 and 0.001 in females) CONCLUSION Using automated body segmentation analysis we optimized a CT scan composite score that was able to stratify GBM patients with worse overall survival.