SURG-32. A NOVEL MACHINE LEARNING APPROACH FOR MODELING THE PREDICTIVE VALUE OF COMORBIDITY INDICES IN PITUITARY SURGERY

Abstract

Abstract Although pituitary adenomas (PAs) are common intracranial tumors, literature evaluating the utility of comorbidity indices for predicting perioperative complications in patients undergoing pituitary surgery remains limited, thereby hindering the development of complex models that aim to identify high-risk patient populations. Accordingly, we utilized comparative modeling strategies to evaluate the predictive validity of various comorbidity indices and combinations thereof in predicting key pituitary surgery outcomes. The Nationwide Readmissions Database was used to identify patients who underwent transsphenoidal pituitary tumor operations (n=19,653) in 2016-2017. Patient frailty was assessed using the Johns Hopkins Adjusted Clinical Groups (JHACG). Charlson Comorbidity Index (CCI) and Elixhauser Comorbidity Index (ECI) were calculated for each patient. Five sets of generalized linear mixed-effects models were developed, using 1) Frailty, 2) CCI, 3) ECI, 4) Frailty+CCI, or 5) Frailty+ECI as the primary predictor. Complications investigated included inpatient mortality, non-routine discharge (e.g., to locations other than home) , length of stay (LOS) within the top quartile, cost within the top quartile, and one-year readmission rates. Postoperative mortality occurred in 73 patients (0.4%), one year readmission was reported in 2,994 patients (15.2%),and non-routine discharge occurred in 2,176 (11.1%) patients. The mean adjusted all-payer cost for the procedure was $25,553.85±$26,518.91 (Top Quartile: $28,261.20) and mean LOS was 4.8 days±7.4 days (Top Quartile: 5.0 days). The model using frailty+ECI as the primary predictor consistently outperformed other models, with statistically significant p-values as determined by comparing their AUCs, for most complications. For prediction of mortality, however the Frailty+ECI model (AUC:0.831) was not better than the ECI model alone (AUC:0.831;p=0.95). For prediction of readmission the Frailty+ECI model (AUC:0.617) was not better than the frailty model alone (AUC:0.606;p=0.10) or the Frailty+CCI model (AUC:0.610;p=0.29). Knowledge gained from these models may help neurosurgeons identify high-risk patients requiring additional clinical attention or specific resource utilization prior to surgical planning.