基于决策树法构建气管切开术后拔管失败的风险预测模型

A risk prediction model for extubation failure after tracheotomy was constructed based on the decision tree method

摘要

目的 探讨气管切开患者术后拔管失败的危险因素，并构建基于决策树算法的风险预测模型。方法 回顾性选取2022年2月至2024年4月在南京医科大学第一附属医院住院治疗的215例气管切开患者作为研究对象，根据术后是否成功拔除气切套管分为拔管成功组(176例)和拔管失败组(39例)，采用Logistic回归分析并筛选气管切开患者术后拔管失败的相关因素，采用R软件构建决策树模型。结果 logistic回归分析显示，年龄≥60岁、格拉斯哥昏迷评分(glasgow coma scale，GCS)评分≤8分、咳嗽效力分级0~2级、无吞咽反射、有吞咽功能障碍、血红蛋白均异常是气管切开术后拔管失败的独立危险因素(P<0.05)；5折交叉验证预测正确率为72.4%；决策树模型显示，吞咽反射是气管切开患者术后拔管失败的最重要影响因素，信息增益为0.32；Logistic回归模型和决策树模型对术后拔管失败风险的预测效能良好，受试者工作特征(receiver operating characteristic curve，ROC)曲线下面积分别为0.848和0.823。结论 基于决策树构建的风险预测模型可有效预测气管切开术后拔管失败风险。

Abstract

Objective To identify the risk factors for extubation failure in patients after tracheotomy and to construct a risk prediction model based on a decision tree algorithm. Methods A total of 215 patients with tracheotomy who were hospitalized in the First Affiliated Hospital of Nanjing Medical University from February 2022 to April 2024 were retrospectively selected as the research subjects. They were divided into the successful extubation group (176 cases) and the failed extubation group (39 cases) according to whether the tracheotomy cannulas were successfully removed after the operation. Logistic regression was used to analyze and screen the related factors of postoperative extubation failure in patients with tracheotomy, and the decision tree model was constructed using R language software. Results The extubation failure rate was 18.14%; Logistic regression analysis showed that age ≥60 years, Glasgow Coma Scale (GCS) score ≤8, cough effectiveness grade 0~2, absent swallowing reflex, swallowing dysfunction, and abnormal hemoglobin levels were all independent risk factors for extubation failure after tracheotomy (P<0.05); Decision tree modeling identified swallowing reflex as the most influential factor for extubation failure in tracheotomy patients, with an information gain of 0.32; Both the logistic regression model and the decision tree model demonstrated good predictive performance for postoperative extubation failure risk, with areas under the receiver operating characteristic (ROC) curve of 0.848 and 0.823, respectively. Conclusion The construction of a risk prediction model, based on decision trees, has proven effective in the prediction of extubation failure subsequent to tracheotomy.

关键词

气管切开 / 拔管 / 危险因素 / 预测模型

Key words

Tracheotomy / Pull the tube / Risk factors / Prediction model

参考文献

[1] Jia ZY, Yi Y, Liu JH, et al. Epidemiology of hepatitis E virus in China: results from the third national viral hepatitis prevalence survey, 2005-2006[J]. PLoS One, 2014, 9(10): e110837. DOI: 10.1371/journal.pone.0110837

[2] Toker A, Hayanga JA, Dhamija A, et al. Tracheotomy, closure of long-term tracheostomy and standard tracheal segmental resections[J]. J Thorac Dis, 2020, 12(10): 6185-6197. DOI: 10.21037/jtd.2020.02.41

[3] Ustrell S, Simmons JK, Henkle G, et al. Revision tracheotomy complicated by history of follicular B-cell lymphoma[J]. Ear Nose Throat J, 2023, 102(9_suppl): 16S-19S. DOI: 10.1177/01455613231189229

[4] 陈萍, 王芳, 张文静. 影响气管切开重症患者拔管的风险因素及预防护理策略[J]. 齐鲁护理杂志, 2024, 30(2): 99-102. DOI: 10.3969/j.issn.1006-7256.2024.02.032

[5] 丁克元, 李贤英, 王捷, 等. GCS评分、咳嗽效力评级与颅脑疾病气管切开术后拔管成功的关系[J]. 临床误诊误治, 2023, 36(7): 97-100.

[6] 董旭, 冯涛, 刘庆, 等. 重症康复科颈脊髓损伤合并膈肌功能障碍患者并发肺部感染高危因素的回顾性研究[J]. 宁夏医学杂志, 2023, 45(6): 514-516. DOI: 10.13621/j.1001-5949.2023.06.0514

[7] 高敏, 韩小彤, 张兴文, 等. 探讨中重型颅脑损伤机械通气患者拔管的预测因素[J]. 中国呼吸与危重监护杂志, 2023, 22(4): 274-280. DOI: 10.7507/1671-6205.202209066

[8] 高胜浩, 李琳璨, 张晓菊, 等. 有创-无创机械通气降级治疗策略在气管切开呼吸机依赖患者中的应用效果研究[J]. 中国全科医学, 2021, 24(5): 571-576. DOI: 10.12114/j.issn.1007-9572.2020.00.511

[9] 韩奇, 刘倩, 林明泉, 等. 气管切开患者拔管评估研究进展[J]. 吉林医药学院学报, 2024, 45(4): 291-295

[10] 胡银, 青晨, 袁梅, 等. 神经外科病人气管切开拔管影响因素及拔管指征的研究进展[J]. 护理研究, 2025, 39(3): 488-494. DOI: 10.12102/j.issn.1009-6493.2025.03.022

[11] 李勍, 姜宏英, 周婷, 等. 气管切开术后拔管困难患者成功拔除气切套管的相关因素分析[J]. 中国康复医学杂志, 2023, 38(9): 1227-1232. DOI: 10.3969/j.issn.1001-1242.2023.09.008

[12] 李秋怡. 气管切开患者拔管的临床预测模型构建与验证[D]. 昆明医科大学, 2023: 56

[13] 戚婷, 刘冬, 王崇. 气管切开神经重症患者早期成功拔管的相关因素分析[J]. 临床医学研究与实践, 2025, 10(1): 63-66

[14] 唐志明, 温红梅, 许自阳, 等. 喉镜吞咽功能评估指导气管切开合并吞咽障碍患者拔管的应用分析[J]. 中华物理医学与康复杂志, 2020, 42(10): 886-889. DOI: 10.3760/cma.j.issn.0254-1424.2020.10.005

[15] 王华, 张丰珍, 龙婷, 等. 后颅窝肿瘤术后儿童气管切开原因及预后转归分析[J]. 山东大学耳鼻喉眼学报, 2025, 39(4): 168-173. DOI: 10.6040/j.issn.1673-3770.0.2025.028

[16] 王佳, 丁磊, 陈佳俊. 危重症气管插管病人非计划性拔管风险预测模型的构建与检验[J]. 全科护理, 2025, 23(21): 4114-4118. DOI: 10.12104/j.issn.1674-4748.2025.21.024