文献速递烧伤

利用全国烧伤登记数据库构建风险校正住院时长基准模型

Using a National Burn Registry to Develop a Model for Risk-Adjusted Length of Stay Benchmarking.
PubMed 文献 · J Burn Care Res · 2023-01-01

研究基于美国烧伤协会烧伤护理质量平台2015年7月至2020年6月的130729条记录、103个中心数据,用22个预测变量比较线性回归与CatBoost梯度提升模型预测烧伤住院时长。CatBoost测试集R2为0.67、一致性相关系数为0.81,优于线性模型的R2=0.50、一致性相关系数=0.68,并据此计算各中心观察值与预期值比值。

要点

  • CatBoost模型测试集R2=0.67、一致性相关系数=0.81,线性模型R2=0.50、一致性相关系数=0.68。
  • 分析覆盖全部患者、10-20% TBSA、>20% TBSA三个队列。
  • 作者称该风险校正住院时长基准模型为同类首个。

核心结论

  • 梯度提升回归模型性能优于传统回归分析,可基于全国烧伤数据预测各参与中心住院时长并生成更有意义的观察值与预期值比值。
  • 作者称该风险校正住院时长基准模型利用稳健数据源,为烧伤中心同类首个。

研究设计与样本

  • 基于美国烧伤协会烧伤护理质量平台,查询2015年7月至2020年6月入院记录,共130729条、来自103个中心。
  • 使用22个预测变量,比较未惩罚线性回归与梯度提升(CatBoost)回归模型,以测试数据集R2和一致性相关系数评价。
  • 分析在全部患者、10-20% TBSA、>20% TBSA三个队列进行。

主要发现

  • CatBoost模型测试集R2=0.67、一致性相关系数=0.81,线性模型R2=0.50、一致性相关系数=0.68。
  • CatBoost对较长和较短住院时长的偏倚也更小。
  • 将CatBoost模型应用于全数据集的bootstrap版本,计算各烧伤中心的观察值与预期值比值。

临床怎么用

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Length of stay (LOS) is a frequently reported outcome after a burn injury. LOS benchmarking will benefit individual burn centers as a way to measure their performance and set expectations for patients. We sought to create a nationwide, risk-adjusted model to allow for LOS benchmarking based on the data from a national burn registry. Using data from the American Burn Association's Burn Care Quality Platform, we queried admissions from 7/2015 to 6/2020 and identified 130,729 records reported by 103 centers. Using 22 predictor variables, comparisons of unpenalized linear regression and Gradient boosted (CatBoost) regressor models were performed by measuring the R2 and concordance correlation coefficient on the application of the model to the test dataset. The CatBoost model applied to the 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 R2 of 0.67 and CCC of 0.81 compared with the linear model with R2=0.50, CCC=0.68. The CatBoost was also less biased for higher and lower LOS durations. Gradient-boosted regression models provided greater model performance than traditional regression analysis. Using national burn data, we can predict LOS across contributing burn centers while accounting for patient and 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.

来源:J Burn Care Res,查看原文。版权归原作者所有。

引用

  1. Thompson CM, Phillips MH, Bessey PQ, et al. Using a National Burn Registry to Develop a Model for Risk-Adjusted Length of Stay Benchmarking. J Burn Care Res. 2023. PMID: 35986490. doi:10.1093/jbcr/irac103

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。