文献速递烧伤创面修复

基于机器学习的住院烧伤患儿发热与不良临床事件预测模型

Machine Learning-Based Predictive Model for Fever and Adverse Clinical Events in Hospitalized Pediatric Burn Patients.
PubMed 文献 · J Burn Care Res · 2026-01-01

本研究回顾性分析2012至2022年一家三级中心收治的595例烧伤患儿,采用随机森林算法构建预测发热(>38.5°C)、转入儿科重症监护室(PICU)和需要手术干预的模型。模型F1分数分别为0.81±0.037、0.88±0.091和0.81±0.027,AUC分别为0.96、0.97和0.95。特征重要性分析显示低龄、低体重、女性和头颈部烧伤部位是关键预测因素。

要点

  • 随机森林模型对烧伤患儿发热、PICU转入和手术需求的预测AUC均≥0.95。
  • 低龄、低体重、女性和头颈部烧伤是发热及不良结局的关键预测因素。
  • 模型可用于早期风险分层,指导监测强度和资源规划,但需前瞻性验证。

核心结论

  • 基于随机森林的机器学习模型对住院烧伤患儿发热、PICU转入和手术需求具有高预测准确性。
  • 该模型有望用于早期风险分层,指导监测强度、诊断警觉性和资源规划。
  • 模型-informed工作流程能否改善结局尚需前瞻性评估。

研究设计与样本

  • 回顾性分析2012至2022年一家三级中心收治的595例烧伤患儿。
  • 提取人口学、烧伤特征、临床干预、实验室值和结局数据。
  • 采用多重插补和bootstrap采样生成合成数据以处理缺失值和类别不平衡。
  • 随机森林模型训练预测三个终点:发热(>38.5°C)、转入PICU和需要手术干预。

主要发现

  • 患儿平均年龄4.27岁(范围0.2-18.1),平均总体表面积5.49%(范围0.3-45.0)。
  • 随机森林模型F1分数:发热0.81±0.037,PICU转入0.88±0.091,手术0.81±0.027。
  • AUC值分别为0.96、0.97和0.95。
  • 特征重要性分析识别低龄、低体重、女性和头颈部烧伤部位为关键预测因素。

临床怎么用

  • 可利用模型对住院烧伤患儿进行早期风险分层,识别发热和不良临床事件高风险患者。
  • 根据风险分层调整监测强度、诊断检查和资源规划。
  • 模型应用前需在前瞻性研究中验证其临床效用。

局限性

  • 回顾性单中心研究设计。
  • 需前瞻性评估以确定模型-informed工作流程是否改善结局。

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

Systemic inflammation after pediatric burn injury frequently causes fever, complicating early recognition of infectious complications. Improved risk-stratification may help identify patients at risk for adverse clinical events during hospitalization. This study aimed to develop and validate a machine learning (ML)-based model using a Random Forest (RF) algorithm to predict fever and related adverse outcomes in hospitalized pediatric burn patients. We conducted a retrospective analysis of 595 pediatric burn patients admitted to a tertiary center between 2012 and 2022. Extracted data included demographics, burn characteristics, clinical interventions, laboratory values, and outcomes. RF models were trained to predict three key endpoints: fever (>38.5°C), transfer to pediatric intensive care unit (PICU), and need for surgical intervention. To address missing data and class imbalance, we employed multiple imputation techniques and generated synthetic data through bootstrap sampling to improve model robustness. The patient cohort had a mean age of 4.27 (range: 0.2-18.1) years and an average total body surface area of 5.49 (range: 0.3-45.0). The RF models demonstrated high predictive accuracy, with F1-scores of 0.81 ± 0.037 (fever), 0.88 ± 0.091 (PICU transfer), and 0.81 ± 0.027 (surgery). Area Under the Curve values were 0.96, 0.97, and 0.95, respectively. Feature importance analysis identified younger age, lower body weight, female sex, and head and neck burn location as key predictors. These ML-based RF models demonstrate strong potential for early risk-stratification of fever and high-risk trajectories in hospitalized pediatric burn patients, guiding monitoring intensity, diagnostic vigilance, and resource planning. Prospective evaluation is needed to determine whether model-informed workflows improve outcomes.

来源:J Burn Care Res,查看原文。版权归原作者所有。

引用

  1. Har-Shai L, Gershov S, Lagziel T, et al. Machine Learning-Based Predictive Model for Fever and Adverse Clinical Events in Hospitalized Pediatric Burn Patients. J Burn Care Res. 2026. PMID: 42102144. doi:10.1093/jbcr/irag074

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。