基于随机森林模型的小儿重症肺炎支原体肺炎风险因素分析的应用研究

doi:10.20274/j.cnki.issn.1674-3865.2026.01.014

摘要/Abstract

摘要：

目的本研究旨在通过随机森林模型分析小儿重症肺炎支原体肺炎（MPP）的风险因素，为临床早期识别和干预提供依据。方法选择2024年1～12月黎川县人民医院收治住院的小儿MPP患者198例的临床资料，其中133例为非重症组，65例为重症组。对两组患者的临床特征进行比较，并采用单因素Logistic回归分析和随机森林模型评估各变量对重症MPP的影响。随机森林模型的构建包括特征重要性分析和受试者工作特征(ROC)曲线评估。结果在临床特征比较中，两组在年龄和性别分布上差异无统计学意义（P>0.05），重症组在发热病程、白细胞计数、C反应蛋白、红细胞沉降率、降钙素原、白细胞介素-6、乳酸脱氢酶、肌酸激酶同工酶等指标上均显著高于非重症组，差异有统计学意义（P<0.05）。同时，重症组中高热和喘息的发生率显著高于非重症组，差异有统计学意义（P<0.05）。单因素Logistic回归分析显示，高热、发热病程、喘息、白细胞计数、C反应蛋白、红细胞沉降率、降钙素原、白细胞介素-6、乳酸脱氢酶、肌酸激酶同工酶均与重症MPP风险有显著关联。随机森林模型分析显示，模型的错误率在决策树数目为45时最低，危险因素的重要性排序依次是发热病程、白细胞计数、年龄、是否高热、肌酸激酶同工酶、红细胞沉降率、C反应蛋白、红细胞计数、白细胞介素-6、乳酸脱氢酶、降钙素原、是否喘息、血小板计数、性别。ROC曲线分析显示，随机森林模型的ROC曲线下面积为0.882，灵敏度为75.68%，特异度为93.33%。结论本研究通过单因素Logistic回归分析和随机森林模型，识别了发热病程、高热、喘息、白细胞计数等变量作为小儿重症MPP的风险因素。这些结果为临床早期识别和干预重症MPP提供了重要参考，有助于改善患儿的预后。

关键词: 重症肺炎, 肺炎支原体肺炎, 风险因素, 随机森林模型, Logistic回归分析, 儿童

Abstract:

Objective To identify risk factors for severe pediatric Mycoplasma pneumoniae pneumonia using a random forest model and to provide evidence for clinical recognition and intervention. Methods Clinical data of 198 children hospitalized for Mycoplasma pneumoniae pneumonia in our hospital between January and December 2024 were collected; 133 were classified as non-severe and 65 as severe. Clinical characteristics were compared between the two groups. Univariate Logistic regression analysis and a random forest model were employed to evaluate the impact of each variable on severe Mycoplasma pneumoniae pneumonia. The construction of random forest model included feature importance analysis and ROC curve assessment. Results No statistically significant differences were observed in age or gender distribution between the groups(P>0.05). The severe group showed significantly higher levels of fever duration, WBC, CRP, ESR, PCT, IL-6, LDH, and CK-MB than the non-severe group(P<0.05). The incidence of high fever and wheezing was also significantly higher in the severe group(P<0.05). Univariate logistic regression indicated that high fever, fever duration, wheezing, WBC, CRP, ESR, PCT, IL-6, LDH, and CK-MB were significantly associated with the risk of severe Mycoplasma pneumoniae pneumonia. The random forest model analysis revealed the lowest error rate when the number of decision trees was 45. The descending order of risk factor importance was fever duration, WBC, age, presence of high fever, CK-MB, ESR, CRP, RBC, IL-6, LDH, PCT, presence of wheezing, PLT, and gender. ROC curve analysis demonstrated an AUC of 0.882 of the random forest model, with a sensitivity of 75.68% and a specificity of 93.33%. Conclusion Through univariate Logistic regression and the random forest model, this study identifies fever duration, high fever, wheezing, and WBC as key risk factors for severe pediatric Mycoplasma pneumoniae pneumonia. These findings offer valuable reference for early clinical identification and intervention of severe Mycoplasma pneumoniae pneumonia, helping to improve the outcomes of affected children.

Key words: Severe pneumonia, Mycoplasma pneumoniae pneumonia, Risk factors, Random forest model, Logistic regression analysis, Child

中图分类号:

R725.6

孔森, 张亮, 廖楠, 涂光. 基于随机森林模型的小儿重症肺炎支原体肺炎风险因素分析的应用研究[J]. 中国中西医结合儿科学, 2026, 18(1): 71-76.

Sen KONG, Liang ZHANG, Nan LIAO, Guang TU. Application research on risk factor analysis of severe Mycoplasma pneumoniae pneumonia in children based on random forest model[J]. Chinese Pediatrics of Integrated Traditional and Western Medicine, 2026, 18(1): 71-76.

图/表 5

表1

表2

图1

图2

图3

参考文献 31

[1]	Yan C, Xue GH, Zhao HQ, et al. Current status of Mycoplasma pneumoniae infection in China[J]. World J Pediatr, 2024, 20(1): 1-4.
[2]	孙明朗,张秋愉.小儿重症肺炎支原体肺炎发生临床危险因素分析[J].岭南急诊医学杂志,2024,29(2):159-161.
[3]	Yang S, Lu S, Guo Y, et al. A comparative study of general and severe Mycoplasma pneumoniae pneumonia in children[J]. BMC Infect Dis, 2024, 24(1): 449.
[4]	Roh EJ, Lee MH, Lee JY, et al. Analysis of national surveillance of respiratory pathogens for community-acquired pneumonia in children and adolescents[J]. BMC Infect Dis, 2022, 22(1): 330.
[5]	Yu F, Li C, Liu M, et al. Aerosol inhalation of ambroxol hydrochloride combined with terbutaline can promote recovery of children with severe pneumonia[J]. Am J Transl Res, 2021, 13(5): 5019-5026.
[6]	Lee KL, Lee CM, Yang TL, et al. Severe Mycoplasma pneumoniae pneumonia requiring intensive care in children, 2010-2019[J]. J Formos Med Assoc, 2021, 120(1 Pt 1): 281-291.
[7]	王亨,徐玮涵,刘金荣,等. 儿童重症肺炎支原体肺炎的临床表型分析[J]. 中华儿科杂志,2024,62(7):669-675.
[8]	Lee JK, Seong MW, Yun KW, et al. Association of tandem repeat number variabilities in subunit S of the type I restriction-modification system with macrolide resistance in Mycoplasma pneumoniae [J]. J Clin Med, 2022, 11(3): 715.
[9]	Li J, Luu LDW, Wang X, et al. Metabolomic analysis reveals potential biomarkers and the underlying pathogenesis involved in Mycoplasma pneumoniae pneumonia[J]. Emerg Microbes Infect, 2022, 11(1): 593-605.
[10]	Huang X, Gu H, Wu R, et al. Chest imaging classification in Mycoplasma pneumoniae pneumonia is associated with its clinical features and outcomes[J]. Respir Med, 2024, 221: 107480.
[11]	杨华,杜佳宜,杨美俊,等.血清CXCL10联合高分辨CT影像学特征对小儿重症支原体肺炎的预测价值[J].中国实验诊断学,2024,28(12):1411-1416.
[12]	王耀邦,沙宁,杨娟,等.血清PCT、CRP及IL-4水平预测小儿支原体肺炎病情严重程度的价值[J].中外医学研究,2024,22(2):69-72.
[13]	冉静,张若林,冯娜,等.血液流变学检测在小儿肺炎支原体肺炎病情判断中的应用[J].吉林医学,2023,44(10):2706-2710.
[14]	Meyer Sauteur PM, Unger WWJ, van Rossum AMC, et al. The art and science of diagnosing Mycoplasma pneumoniae infection[J]. Pediatr Infect Dis J, 2018, 37(11): 1192-1195.
[15]	徐慧双,李敏,韩香,等.产后输血量的高危因素评估和风险评分模型的建立[J].中国妇幼健康研究,2024,35(12):1-11.
[16]	钱翠平,黄晓碧,赵胜,等.儿童川崎病冠状动脉损伤危险因素Logistic回归分析[J].安徽医科大学学报,2023,58(3):490-494.
[17]	中华医学会儿科学分会呼吸学组, 中华儿科杂志编辑委员会, 中国医药教育协会儿科专业委员会, 等. 儿童社区获得性肺炎管理指南(2024修订)[J]. 中华儿科杂志, 2024(10): 920-930.
[18]	陈昌秀,于海容,李建,等.重症支原体肺炎影响因素分析[J].实用心脑肺血管病杂志,2021,29(S1):108-110.
[19]	袁江,德桂荣.炎性指标和胸部影像动态监测在小儿支原体肺炎临床诊治中的意义[J].中国妇幼保健,2019,34(10):2297-2300.
[20]	赵枫.小儿重症支原体肺炎高危因素分析[J].基层医学论坛,2017,21(32):4486-4487.
[21]	葛柳源, 任少敏. 小儿重症肺炎支原体肺炎临床相关因素分析[J]. 内蒙古医学杂志, 2017,49(6): 672-674.
[22]	黄艳,宋凤华.布地奈德雾化吸入联合阿奇霉素治疗小儿肺炎支原体肺炎的效果分析[J].医药前沿,2024,14(11):55-57.
[23]	Liu F, Chen L, Wang MY, et al. Exploring high-risk factors for the prediction of severe Mycoplasma pneumonia in children[J]. Transl Pediatr, 2024, 13(11): 2003-2011.
[24]	Luo XQ, Luo J, Wang CJ, et al. Clinical features of severe Mycoplasma pneumoniae pneumonia with pulmonary complications in childhood: a retrospective study[J]. Pediatr Pulmonol, 2023, 58(10): 2815-2822.
[25]	侯丽丽. 儿童重症社区获得性肺炎支原体肺炎临床资料分析[D]. 广州: 广州医科大学, 2022.
[26]	He W, Yin J, Wan Y. Correlations of different serological parameters with the severity and prognosis of pneumonia in children infected with Mycoplasma pneumoniae[J]. Clin Lab, 2022, 68(12).
[27]	罗自豪,耿刚,王艳红,等.儿童肺炎支原体肺炎合并塑型性支气管炎危险因素的系统评价和Meta分析[J].中国中西医结合儿科学,2024,16(6):500-508.
[28]	张立霞,朱峰,李传景,等.重症肺炎支原体肺炎患儿CRP、LDH等实验室指标的预警价值及支气管镜下特点[J].中华全科医学,2024,22(7):1098-1101.
[29]	李伟平,李志勇.CRP,PCT,SAA,LDH,CK-MB对肺炎支原体肺炎病情判断的临床应用价值[J].潍坊医学院学报,2018,40(6):430-433.
[30]	Zhang YX, Li Y, Wang Y, et al. Prospective cohort study on the clinical significance of interferon-γ, D-dimer, LDH, and CRP tests in children with severe Mycoplasma pneumonia[J]. Medicine(Baltimore), 2024, 103(41): e39665.
[31]	王洁,杨青,幸超群,等.基于随机森林模型的产妇母乳喂养动机影响因素分析[J].军事护理,2024,41(12):35-38.

变量	总计（n=198）	非重症组（n=133）	重症组（n=65）	χ²或t或Z值	P值
年龄（岁）	5.45±2.02	5.47±2.01	5.40±2.05	-0.241	0.810
性别[n（%）]				0.063	0.802
男	100（50.5）	68（51.1）	32（49.2）
女	98（49.5）	65（48.9）	33（50.8）
高热[n（%）]				32.457	<0.001
是	78（39.4）	34（25.6）	44（67.7）
否	120（60.6）	99（74.4）	21（32.3）
发热病程[M（P₂₅,P₇₅），d]	2.0（1.0,4.0）	2.0（1.0,3.0）	4.0（3.0,5.0）	-7.509	<0.001
喘息[n（%）]				5.602	0.018
是	95（48.0）	56（42.1）	39（60.0）
否	103（52.0）	77（57.9）	26（40.0）
白细胞计数（×10⁹/L）	4.14±0.87	3.94±0.84	4.56±0.81	4.935	<0.001
红细胞计数（×10¹²/L）	4.21±0.13	4.21±0.12	4.22±0.14	0.408	0.684
血小板计数（×10⁹/L）	199.41±10.89	198.89±10.81	200.49±11.07	0.947	0.331
C反应蛋白（mg/L）	11.54±5.21	10.95±5.19	12.72±5.07	2.267	0.024
红细胞沉降率（mm/h）	20.19±6.71	19.39±6.79	21.83±6.28	2.432	0.016
降钙素原（μg/L）	0.48±0.23	0.45±0.23	0.54±0.24	2.586	0.010
白细胞介素-6（ng/L）	13.57±5.74	12.88±5.71	14.98±5.58	2.455	0.015
乳酸脱氢酶（U/L）	183.78±27.80	180.32±27.35	190.86±27.59	2.539	0.012
肌酸激酶同工酶（U/L）	26.13±4.40	25.50±4.24	27.42±4.45	2.929	0.004

变量	OR值(95%CI)	P值
高热	6.10(3.19~11.68)	<0.001
发热病程	2.65(1.98~3.54)	<0.001
喘息	2.06(1.13~3.77)	0.019
白细胞计数	2.45(1.65~3.64)	<0.001
C反应蛋白	1.07(1.01~1.13)	0.026
红细胞沉降率	1.06(1.01~1.11)	0.017
降钙素原	5.10(1.44~18.12)	0.012
白细胞介素-6	1.07(1.01~1.12)	0.016
乳酸脱氢酶	1.01(1.00~1.02)	0.013
肌酸激酶同工酶	1.11(1.03~1.19)	0.005