日本全国烧伤登记数据中住院时长简易预测模型的开发与验证
基于日本烧伤学会2011年全国烧伤登记数据,纳入成年存活住院患者,采用广义估计方程(GEE)构建含年龄、烧伤面积(%TBSA)、吸入性损伤及其交互项的预测模型并简化,在验证队列中评估性能。简易日本模型性能与GEE模型相当且优于美国Taylor模型,支持早期资源规划与烧伤照护基准。
要点
- 简易日本模型:有吸入伤时LOS=0.3×年龄+3×%TBSA-8,无吸入伤时LOS=0.3×年龄+2×%TBSA-1。
- 简易模型R²为0.175(95%CI 0.124-0.230),RMSE 49.0,MAE 22.0,平均残差-0.77。
- 简易模型性能与GEE模型相当,且优于Taylor模型(R² 0.012)。
核心结论
- 建立了简易日本模型预测烧伤患者住院时长,性能优于基于美国背景的Taylor模型。
- 该模型可支持烧伤照护的早期资源规划和基准制定。
研究设计与样本
- 回顾性研究,使用日本烧伤学会2011年全国烧伤登记数据,纳入成年存活住院患者。
- 在推导队列中基于广义估计方程(GEE)构建含年龄、%TBSA、吸入性损伤及其交互项的模型,并建立简化模型。
- 在验证队列中使用平均残差、决定系数(R²)、均方根误差(RMSE)和平均绝对误差(MAE)评估模型性能。
主要发现
- 简易日本模型:有吸入伤时LOS=0.3×年龄+3×%TBSA-8;无吸入伤时LOS=0.3×年龄+2×%TBSA-1。
- 简易模型R²为0.175(95%CI 0.124-0.230),RMSE 49.0,MAE 22.0,平均残差-0.77。
- GEE模型R²为0.175(95%CI 0.125-0.229),RMSE 49.0,MAE 22.3,平均残差-1.4。
- Taylor模型R²为0.012(95%CI -0.025-0.047),RMSE 53.6,MAE 23.6,平均残差20.0。
临床怎么用
- 可基于患者年龄、%TBSA和吸入性损伤状态使用简易公式估算住院时长。
- 模型有助于烧伤照护的早期资源规划和床位安排。
- 可作为烧伤照护质量与效率的基准工具。
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
BACKGROUND: Length of hospital stay (LOS) during burn care affects discharge planning and resource allocation. A simplified model (Taylor's model) was developed in the US; however, its applicability in other countries remains unclear. This study validated this model using a Japanese national registry and developed a simple prediction model applicable to Japan. METHODS: This retrospective study, conducted using the Japan Society for Burn Injury Burn Registry 2011, included adult patients who survived hospitalization. Using a derivation cohort, we constructed a model based on generalized estimating equations (GEE) using age, % total body surface area burned (TBSA), inhalation injury, and their interactions. A simplified model was then established using GEE. Model performance was assessed in a validation cohort using the mean residual (observed-predicted), coefficient of determination (R²), root mean squared error (RMSE), and mean absolute error (MAE). RESULTS: The performance of our Simplified Japanese Model [LOS = 0.3 × Age + 3 × %TBSA - 8 (with inhalation injury); or 0.3 × Age + 2 × %TBSA - 1 (without inhalation injury)] [R², 0.175 (95% CI, 0.124-0.230); RMSE, 49.0; MAE, 22.0; mean residual, -0.77] was comparable to that of the GEE model [R², 0.175 (95% CI, 0.125-0.229); RMSE, 49.0; MAE, 22.3; mean residual, -1.4] and superior to that of the Taylor model [R², 0.012 (95% CI, -0.025-0.047); RMSE, 53.6; MAE, 23.6; mean residual, 20.0]. CONCLUSION: We established a Simplified Japanese Model to predict LOS that outperformed the US-based model based on the Japanese context. The model supports early resource planning and benchmarks for burn care patients.
引用
- Watanabe T, Iwagami M, Inoue Y, et al. Development and validation of a simple prediction model for length of hospital stay in a nationwide Japanese burn registry. Burns. 2026. PMID: 41886975. doi:10.1016/j.burns.2026.107952
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。