Citation

Thompson CM, Phillips MH, Bessey PQ, Higginson S, Hoarle K, Phillips B, Weber JM, Weichmann-Murata E, Mandell SP. J. Burn Care Res. 2022; ePub(ePub): ePub.

Copyright

(Copyright © 2022, American Burn Association, Publisher Lippincott Williams and Wilkins)

DOI

10.1093/jbcr/irac103

PMID

35986490

Abstract

Length of stay is a frequently reported outcome after a burn injury. Length of stay benchmarking will benefit individual burn centers as a way to measure their performance & set expectations for patients. We sought to create a nationwide, risk-adjusted model to allow for length of stay benchmarking based on data from a national burn registry. Using data from the American Burn Association's Burn Care Quality Platform, we queried admissions from 7/2015-6/2020 & identified 130,729 records reported by 103 centers. Using 22 predictor variables, comparisons of unpenalized linear regression & Gradient boosted (CatBoost) regressor models were performed by measuring the R 2 & concordance correlation coefficient on the application of the model to the test dataset. The CatBoost model applied to bootstrapped versions of the entire dataset was used to calculate O/E ratios for individual burn centers. Analyses were run on 3 cohorts: all patients, 10-20% TBSA, >20% TBSA. The CatBoost model outperformed the linear regression model with a test R 2 of 0.67 & CCC of 0.81 compared to the linear model with R 2=0.50, CCC=0.68. The CatBoost was also less biased for higher & lower length of stay durations. Gradient boosted regression models provided greater model performance than traditional regression analysis. Using national burn data, we can predict length of stay across contributing burn centers while accounting for patient & center characteristics, producing more meaningful O/E ratios. These models provide a risk-adjusted LOS benchmarking using a robust data source, the first of its kind, for burn centers.

Language: en

Keywords

length of stay; quality improvement; benchmarking