Abstract

Anticipating post-discharge complications following neurosurgery remains difficult. The LACE index, based on four hospitalization descriptors, stratifies patients by risk of 30-day post-discharge adverse events but has not been validated in a procedure-specific manner in neurosurgery. Our study sought to explore the utility of the LACE index in cranial neurosurgery population and to develop an enhanced model, LACE-Cranial.The Optum Clinformatics Database was used to identify cranial neurosurgery admissions (2004-2017). Procedures were grouped as trauma/hematoma/ICP, open vascular, functional/pain, skull base, tumor, or endovascular. Adverse events were defined as post-discharge death/readmission. LACE-Cranial was developed using a logistic regression framework incorporating an expanded feature set in addition to the original LACE components.A total of 40,431 admissions were included. Predictions of 30-day readmissions was best for skull-base (AUC=0.636) and tumor (AUC=0.63) admissions but was generally poor. Predictive ability of 30-day mortality was best for functional/pain admissions (AUC=0.957) and poorest for trauma/hematoma/ICP admissions (AUC=0.613). Across procedure types except for functional/pain, a high-risk LACE score was associated with higher post-discharge bundled payment costs. Incorporating features identified to contribute independent predictive value, the LACE-Cranial model achieved procedure-specific 30-day mortality AUCs ranging from 0.904 to 0.98. Prediction of 30-day and 90-day readmissions was also improved, with tumor and skull base cases achieving 90-day readmission AUCs of 0.718 and 0.717, respectively.While the unmodified LACE index demonstrates inconsistent classification performance, the enhanced LACE-Cranial model offers excellent prediction of short-term post-discharge mortality across procedure groups and significantly improved anticipation of short-term post-discharge readmissions.

View details for DOI 10.1016/j.wneu.2020.10.103

View details for PubMedID 33127572