Li Haisheng, Zhen Ni, Lin Shixu, Li Ning, Zhang Yumei, Luo Wei, Zhang Zhenzhen, Wang Xingang, Han Chunmao, Yuan Zhiqiang, Luo Gaoxing
Institute of Burn Research, Southwest Hospital, State Key Laboratory of Trauma and Chemical Poisoning, Third Military Medical University (Army Medical University), Chongqing 400038, China.
School of Public Health, Zhejiang University School of Medicine, Hangzhou, Zhejiang 310009, China.
Burns Trauma. 2025 May 13;13:tkaf010. doi: 10.1093/burnst/tkaf010. eCollection 2025.
Airway obstruction is a common emergency in acute burns with high mortality. Tracheostomy is the most effective method to keep patency of airway and start mechanical ventilation. However, the indication of tracheostomy is challenging and controversial. We aimed to develop and validate a deployable machine learning (ML)-based decision support system to predict the necessity of tracheostomy for acute burn patients.
We enrolled 1011 burn patients from Southwest Hospital (2018-20) for model development and feature selection. The final model was validated on an independent internal cross-temporal cohort (2021, = 274) and an external cross-institutional cohort (Second Affiliated Hospital of Zhejiang University School of Medicine 2020-21, = 376). To improve the model's deployment and interpretability, an ML-based nomogram, an online calculator, and an abbreviated scale were constructed and validated.
The optimal model was the eXtreme Gradient Boosting classifier (XGB), which achieved an AUROC of 0.973 and AUPRC of 0.879 in training dataset, and AUROCs of greater than 0.95 in both cross-temporal and cross-institutional validation. Moreover, it kept stable discriminatory ability in validation subgroups stratified by sex, age, burn area, and inhalation injury (AUROC ranging 0.903-0.990). The analysis of calibration curve, decision curve, and score distribution proved the feasibility and reliability of the ML-based nomogram, abbreviated scale (BETS), and online calculator.
The developed system has strong predictive ability and generalizability in cross-temporal and cross-institutional evaluations. The nomogram, online calculator, and abbreviated scale based on ML show comparable prediction performance and can be deployed in broader application scenarios, especially in resource-limited clinical environments.
气道梗阻是急性烧伤常见的紧急情况，死亡率高。气管切开术是保持气道通畅并启动机械通气的最有效方法。然而，气管切开术的指征具有挑战性且存在争议。我们旨在开发并验证一种基于机器学习（ML）的可部署决策支持系统，以预测急性烧伤患者气管切开术的必要性。
我们纳入了西南医院（2018 - 20年）的1011例烧伤患者进行模型开发和特征选择。最终模型在一个独立的内部跨时间队列（2021年，n = 274）和一个外部跨机构队列（浙江大学医学院附属第二医院2020 - 21年，n = 376）上进行了验证。为了提高模型的可部署性和可解释性，构建并验证了基于ML的列线图、在线计算器和简化量表。
最佳模型是极端梯度提升分类器（XGB），其在训练数据集中的曲线下面积（AUROC）为0.973，精确召回率曲线下面积（AUPRC）为0.879，在跨时间和跨机构验证中的AUROC均大于0.95。此外，在按性别、年龄、烧伤面积和吸入性损伤分层的验证亚组中，其鉴别能力保持稳定（AUROC范围为0.903 - 0.990）。校准曲线、决策曲线和分数分布分析证明了基于ML的列线图、简化量表（BETS）和在线计算器的可行性和可靠性。
所开发的系统在跨时间和跨机构评估中具有强大的预测能力和通用性。基于ML的列线图、在线计算器和简化量表显示出可比的预测性能，可部署在更广泛的应用场景中，特别是在资源有限的临床环境中。
