Wang Ruoran, Cai Linrui, Liu Yan, Zhang Jing, Ou Xiaofeng, Xu Jianguo
Department of Neurosurgery, West China Hospital, Sichuan University, Chengdu, Sichuan province, China.
Institute of Drug Clinical Trial·GCP, West China Second University Hospital, Sichuan University, Chengdu, China; Diseases of Women and Children, Sichuan University, Ministry of Education, Chengdu, China.
Heart Lung. 2023 Nov-Dec;62:225-232. doi: 10.1016/j.hrtlng.2023.08.002. Epub 2023 Aug 16.
Ventilator associated pneumonia (VAP) is a common complication and associated with poor prognosis of traumatic brain injury (TBI) patients.
This study was conducted to explore the predictive performance of different machine-learning algorithms for VAP in TBI patients.
TBI patients receiving mechanical ventilation more than 48 hours from the Medical Information Mart for Intensive Care-III (MIMIC-III) database were eligible for the study. The VAP was confirmed based on the ICD-9 code. Included patients were separated to the training cohort and the validation cohort with a ratio of 7:3. Predictive models based on different machine learning algorithms were developed using 5-fold cross validation in the training cohort and then verified in the validation cohort by evaluating the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, accuracy and F score.
786 TBI patients from the MIMIC-III were finally included with the VAP incidence of 44.0%. The random forest performed the best on predicting VAP in the training cohort with a AUC of 1.000. The XGBoost and AdaBoost were ranked the second and the third with a AUC of 0.915 and 0.789 in the training cohort. While the AdaBoost performed the best on predicting VAP in the validation cohort with a AUC of 0.706. The XGBoost and random forest were ranked the second and the third with the AUC of 0.685 and 0.683 in the validation cohort. Generally, the random forest and XGBoost were likely to be over-fitting while the AdaBoost was relatively stable in predicting the VAP.
The AdaBoost performed well and stably on predicting the VAP in TBI patients. Developing programs using AdaBoost in portable electronic devices may effectively assist physicians in assessing the risk of VAP in TBI.
呼吸机相关性肺炎（VAP）是创伤性脑损伤（TBI）患者常见的并发症，且与预后不良相关。
本研究旨在探讨不同机器学习算法对TBI患者VAP的预测性能。
从重症监护医学信息数据库三期（MIMIC-III）中选取机械通气超过48小时的TBI患者纳入研究。VAP根据国际疾病分类第九版（ICD-9）编码确诊。纳入患者按7:3的比例分为训练队列和验证队列。在训练队列中采用5折交叉验证法建立基于不同机器学习算法的预测模型，然后在验证队列中通过评估受试者工作特征曲线下面积（AUC）、灵敏度、特异度、准确度和F分数进行验证。
最终纳入MIMIC-III数据库中的786例TBI患者，VAP发生率为44.0%。随机森林在训练队列中对VAP的预测表现最佳，AUC为1.000。XGBoost和AdaBoost分别排第二和第三，训练队列中的AUC分别为0.915和0.789。而在验证队列中，AdaBoost对VAP的预测表现最佳，AUC为0.706。XGBoost和随机森林分别排第二和第三，验证队列中的AUC分别为0.685和0.683。总体而言，随机森林和XGBoost在预测VAP时可能存在过拟合，而AdaBoost相对稳定。
AdaBoost在预测TBI患者VAP方面表现良好且稳定。在便携式电子设备中使用AdaBoost开发程序可能有效地协助医生评估TBI患者发生VAP的风险。
