切换至 "中华医学电子期刊资源库"
高级检索
中华肺部疾病杂志(电子版)

中华肺部疾病杂志(电子版) ›› 2025, Vol. 18 ›› Issue (06) : 917 -922. doi: 10.3877/cma.j.issn.1674-6902.2025.06.011

论著

肺泡灌洗液中炎症因子对重症肺炎患者痰栓风险的预测分析
刘宝德1, 郑娉娉1,†(), 肖宇翔1, 沈凌2, 王柳盛2, 张维2   
  1. 1310006　杭州，杭州市第一人民医院急诊科
    2310006　杭州，杭州市第一人民医院呼吸科
  • 收稿日期:2025-08-08 出版日期:2025-12-25
  • 通信作者: 郑娉娉
  • 基金资助:
    浙江省中医药科技计划项目(2025ZL453)

Predictive analysis of inflammatory factors in alveolar lavage fluid on the risk of phlegm embolism in patients with severe pneumonia

Baode Liu1, Pingping Zheng1,†(), Yuxiang Xiao1, Ling Shen2, Liusheng Wang2, Wei Zhang2   

  1. 1Emergency Department of Hangzhou First People′s Hospital, Hangzhou 310006, China
    2Department of Respiratory Medicine, Hangzhou First People′s Hospital, Hangzhou 310006, China
  • Received:2025-08-08 Published:2025-12-25
  • Corresponding author: Pingping Zheng
全文 ( ) 下载PDF ( ) 导出引用
引用本文：

刘宝德, 郑娉娉, 肖宇翔, 沈凌, 王柳盛, 张维. 肺泡灌洗液中炎症因子对重症肺炎患者痰栓风险的预测分析[J/OL]. 中华肺部疾病杂志(电子版), 2025, 18(06): 917-922.

Baode Liu, Pingping Zheng, Yuxiang Xiao, Ling Shen, Liusheng Wang, Wei Zhang. Predictive analysis of inflammatory factors in alveolar lavage fluid on the risk of phlegm embolism in patients with severe pneumonia[J/OL]. Chinese Journal of Lung Diseases(Electronic Edition), 2025, 18(06): 917-922.

目的

探讨肺泡灌洗液(bronchoalveolar lavage fluid, BALF)中炎症因子对重症肺炎患者痰栓风险的预测。

方法

选取2020年12月至2024年12月我院收治的78例重症肺炎患者为对象，根据支气管镜检查是否痰栓分组，痰栓32例为观察组，未痰栓46例为对照组。检测BALF中炎症因子水平，采用Logistic回归分析筛选与重症肺炎痰栓风险相关特征变量，基于人工智能(artificial intelligence, AI)构建预测重症肺炎痰栓风险模型，通过受试者工作特征(receiver operating characteristic, ROC)曲线分析验证。

结果

观察组BALF中白细胞介素-4(interleukin-4, IL-4)(20.66±4.12)pg/ml、白细胞介素-6(interleukin-6, IL-6)(116.35±16.75)pg/ml、白细胞介素-8(interleukin-8, IL-8)(213.68±20.19)pg/ml、白细胞介素-10(interleukin-10, IL-10)(32.83±4.74)pg/ml、肿瘤坏死因子-α(tumor necrosis factor-α，TNF-α) (64.59±8.22)pg/ml、C反应蛋白(C-reactive protein, CRP)(38.72±5.68)mg/L高于对照组的IL-4(18.35±3.27)pg/ml、IL-6(105.14±15.22)pg/ml、IL-8(213.68±20.19)pg/ml、IL-10(29.16±4.09)pg/ml、TNF-α(58.32±7.15)pg/ml、CRP(31.56±4.84)mg/L(t＝2.645、3.017、4.286、3.555、3.493、5.812；P<0.05)。多因素Logistic回归分析显示，胸腔积液(OR＝1.439)、第1秒用力呼气容积(forced expiratory volume in 1 second, FEV1)(OR＝0.844)、中性粒细胞(OR＝1.737)、CRP(OR＝2.015)、IL-6(OR＝1.600)、IL-8(OR＝1.575)、IL-10(OR＝1.233)、TNF-α(OR＝1.131)是重症肺炎痰栓的危险因素(P<0.05)；ROC分析显示，曲线下面积(area under the curve, AUC)为0.904，敏感性为75.00%，特异性为93.48%，Youden指数为0.685，高于单项BALF炎症因子。

结论

基于AI的BALF炎症因子模型可预测重症肺炎患者痰栓风险，有助于早期识别痰栓高风险患者、制订个性化治疗方案。

关键词: 重症肺炎, 肺泡灌洗液, 炎症因子, 痰栓风险, 人工智能
Objective

To explore the predictive value of inflammatory factors in bronchoalveolar lavage fluid (BALF) for the risk of sputum plugs in patients with severe pneumonia.

Methods

Seventy-eight patients with severe pneumonia admitted to our hospital from December 2020 to December 2024 were selected as subjects. They were divided into groups based on the presence or absence of sputum plugs found during bronchoscopy: 32 cases with sputum plugs formed the observation group, and 46 cases without sputum plugs formed the control group. Levels of inflammatory factors in BALF were detected. Logistic regression analysis was used to screen characteristic variables associated with the risk of sputum plugs in severe pneumonia. An AI-based model was constructed to predict the risk of sputum plugs in severe pneumonia, and its performance was validated by receiver operating characteristic (ROC) curve analysis.

Results

The levels of interleukin-4 (IL-4) (20.66±4.12) pg/ml, interleukin-6 (IL-6) (116.35±16.75) pg/ml, interleukin-8 (IL-8) (213.68±20.19) pg/ml, interleukin-10 (IL-10) (32.83±4.74) pg/ml, tumor necrosis factor-α (TNF-α) (64.59±8.22) pg/ml and C-reactive protein(CRP)(38.72±5.68)mg/L in the BALF of the observation group were higher than those in the control group IL-4 (18.35±3.27) pg/ml, IL-6 (105.14±15.22) pg/ml, IL-8 (213.68±20.19) pg/ml, IL-10 (29.16±4.09) pg/ml, TNF-α (58.32±7.15) pg/ml and CRP(31.56±4.84)mg/L (t=2.645, 3.017, 4.286, 3.555, 3.493, 5.812; P<0.05). Multivariate logistic regression analysis showed that pleural effusion (OR=1.439), forced expiratory volume in 1 second(FEV1) (OR=0.844), neutrophils (OR=1.737), CRP (OR=2.015), IL-6 (OR=1.600), IL-8 (OR=1.575), IL-10(OR=1.233), and TNF-α(OR=1.131) were risk factors for sputum plugs in severe pneumonia (P<0.05). ROC curve analysis showed that the area under the curve (AUC) was 0.904, sensitivity was 75.00%, specificity was 93.48%, and the Youden index was 0.685, which was higher than that of any single BALF inflammatory factor.

Conclusion

The AI-based model utilizing BALF inflammatory factors can predict the risk of sputum plugs in patients with severe pneumonia, aiding in the early identification of high-risk patients and the formulation of personalized treatment plans.

Key words: Severe pneumonia, Bronchoalveolar lavage fluid, Inflammatory factors, Risk of phlegm embolism, Artificial intelligence
表1 两组重症肺炎患者资料结果比较
临床资料 观察组(n＝32) 对照组(n＝46) χ2/t值 P值
胸腔积液[n(%)] 15(46.88) 11(23.91) 4.478 0.034
肺功能(±s)        
FEV1(L) 1.09±0.12 1.27±0.18 5.298 0.000
FVC(L) 1.64±0.17 1.76±0.20 2.850 0.006
PEF(L/s) 1.76±0.24 1.84±0.29 1.328 0.188
实验室指标(±s)        
PaO2(mmHg) 61.62±9.23 62.13±8.52 0.674 0.502
PaO2/FiO2 180.74±32.73 182.53±39.26 0.560 0.578
白细胞计数(×109/L) 11.49±1.65 11.63±1.27 0.404 0.688
中性粒细胞(%) 61.45±4.87 56.36±5.12 4.445 0.000
PLT(×109/L) 313.49±30.26 310.01±23.84 0.544 0.589
CRP(mg/L) 38.72±5.68 31.56±4.84 5.812 0.000
PCT(ng/L) 41.24±3.87 40.58±4.21 0.714 0.477
肺实变[n(%)] 18(56.25) 15(32.61) 4.321 0.038
BALF炎症因子(±s)        
IL-1(pg/ml) 37.18±6.05 35.26±5.31 1.449 0.153
IL-4(pg/ml) 20.66±4.12 18.35±3.27 2.645 0.011
IL-6(pg/ml) 116.35±16.75 105.14±15.22 3.017 0.004
IL-8(pg/ml) 213.68±20.19 194.34±18.72 4.286 0.000
IL-10(pg/ml) 32.83±4.74 29.16±4.09 3.555 0.001
TNF-α(pg/ml) 64.59±8.22 58.32±7.15 3.493 0.001
图1 重症肺炎患者典型胸部CT影像图。图A、B为观察组患者胸部CT；图C、D为对照组患者胸部CT
表2 重症肺炎患者痰栓风险多因素Logistic回归分析
影响因素 β 标准误 Wald P值 OR 95%CI
下限 上限
年龄 0.052 0.272 0.037 0.848 1.053 0.618 1.795
胸腔积液 0.364 0.180 4.105 0.043 1.439 1.012 2.045
肺实变 0.299 0.160 3.474 0.062 1.349 0.985 1.847
FEV1 －0.170 0.071 5.653 0.017 0.844 0.734 0.971
FVC －0.034 0.045 0.563 0.453 0.967 0.885 1.056
中性粒细胞 0.552 0.274 4.066 0.044 1.737 1.016 2.972
CRP 0.701 0.308 5.180 0.023 2.015 1.102 3.684
IL-4 0.196 0.208 0.887 0.346 1.216 0.809 1.829
IL-6 0.470 0.233 4.085 0.043 1.600 1.014 2.525
IL-8 0.454 0.209 4.726 0.030 1.575 1.046 2.373
IL-10 0.210 0.083 6.403 0.011 1.233 1.048 1.451
TNF-α 0.123 0.049 6.286 0.012 1.131 1.027 1.246
表3 重症肺炎患者痰栓风险ROC曲线分析
相关指标 AUC 敏感性(%) 特异性(%) 95%CI Youden指数
IL-6 0.738 78.12 69.57 0.626~0.831 0.477
IL-8 0.764 62.50 80.43 0.655~0.853 0.429
IL-10 0.800 75.00 80.43 0.694~0.882 0.554
TNF-α 0.789 59.38 93.48 0.682~0.873 0.529
AI辅助模型 0.904 75.00 93.48 0.815~0.959 0.685
1
Liu YN, Zhang YF, Xu Q, et al. Infection and co-infection patterns of community-acquired pneumonia in patients of different ages in China from 2009 to 2020: a national surveillance study[J]. Lancet Microbe, 2023, 4(5): e330-e339.
2
Anderson R, Feldman C. The global burden of community-acquired pneumonia in adults, encompassing invasive pneumococcal disease and the prevalence of its associated cardiovascular events, with a focus on pneumolysin and macrolide antibiotics in pathogenesis and therapy[J]. Int J Mol Sci, 2023, 24(13): 11038.
3
Martin-loeches I, Reyes LF, Rodriguez A. Severe community-acquired pneumonia (sCAP): advances in management and future directions[J]. Thorax, 2025, 80(8): 565-575.
4
何敏，孙一茜，高永霞，等. 经鼻高流量吸氧结合叩背排痰在重症肺炎中的临床应用[J/OL]. 中华肺部疾病杂志(电子版), 2025, 18(1): 168-170.
5
Qu J, Zhang J, Chen Y, et al. Aetiology of severe community acquired pneumonia in adults identified by combined detection methods: a multi-centre prospective study in China[J]. Emerg Microbes Infect, 2022，11(1): 556-566.
6
Rueda ZV, Aguilar Y, Maya MA, et al. Etiology and the challenge of diagnostic testing of community-acquired pneumonia in children and adolescents[J]. BMC Pediatr, 2022, 22(1): 169.
7
Wu X, Sun T, He H, et al. Effect of Metagenomic next-generation sequencing on clinical outcomes of patients with severe community-acquired pneumonia in the ICU: A multicenter, randomized controlled trial[J]. Chest, 2025, 167(2): 362-373.
8
Peng B, Li J, Chen M, et al. Clinical value of glucocorticoids for severe community-acquired pneumonia: A systematic review and meta-analysis based on randomized controlled trials[J]. Medicine (Baltimore), 2023, 102(46): e36047.
9
Zhang P, Liu B, Zhang S, et al. Clinical application of targeted next-generation sequencing in severe pneumonia: a retrospective review[J]. Crit Care, 2024, 28(1): 225.
10
SS L, HB L. Severe mycoplasma pneumoniae pneumonia combined with cold agglutinin disease and pulmonary embolism in childhood: A case report and review of the literature[J]. Afr J Reprod Health, 2024, 28(11): 205-215.
11
Saleem M M, Usman A, Saleem A, et al. Post-traumatic pulmonary embolism in the setting of cough-variant asthma[J]. Radiol Case Rep, 2024, 19(12): 6225-6229.
12
Van Der Velden B, Kuijf H J, Gilhuijs K, et al. Explainable artificial intelligence (XAI) in deep learning-based medical image analysis[J]. Med Image Anal, 2022, 79: 102470.
13
Dack E, Christe A, Fontanellaz M, et al. Artificial intelligence and interstitial lung disease: diagnosis and prognosis[J]. Invest Radiol, 2023, 58(8): 602-609.
14
Choi Y H, Kim D H, Jeon E T, et al. Cluster analysis of thoracic muscle mass using artificial intelligence in severe pneumonia[J]. Sci Rep, 2024, 14(1): 16912.
15
Zaeri N. Artificial intelligence and machine learning responses to COVID-19 related inquiries[J]. J Med Eng Technol, 2023, 47(6): 301-320.
16
中国医师协会急诊医师分会. 中国急诊重症肺炎临床实践专家共识[J]. 中国急救医学，2016, 36(2): 97-107.
17
Yang J, Li J, Zhang L, et al. Highly diverse sputum microbiota correlates with the disease severity in patients with community-acquired pneumonia: a longitudinal cohort study[J]. Respir Res, 2024, 25(1): 223.
18
韩丽颖，丁思悦，王春玲. 肺康复联合营养干预对矽肺合并慢阻肺患者应用效果[J]. 工业卫生与职业病，2021, 47(1): 78-80.
19
Wang LL, Lu HW, Li LL, et al. Pseudomonas aeruginosa isolation is an important predictor for recurrent hemoptysis after bronchial artery embolization in patients with idiopathic bronchiectasis: a multicenter cohort study[J]. Respir Res, 2023, 24(1): 84.
20
金龙，黄璇，黄超，等. 肺炎支原体感染形成痰栓的危险因素分析[J]. 安徽医学，2024, 45(9): 1146-1150.
21
Green A, Cockroft JL, Kaufman RA, et al. Utility of induced sputum in assessing bacterial etiology for community-acquired pneumonia in hospitalized children[J]. J Pediatric Infect Dis Soc, 2022, 11(6): 274-282.
22
Waagsbø B, Buset EM, Longva JÅ，et al. Diagnostic stewardship aiming at expectorated or induced sputum promotes microbial diagnosis in community-acquired pneumonia[J]. BMC Infect Dis, 2022, 22(1): 203.
23
Paulsson M, Thelaus L, Riesbeck K, et al. Heparin-binding protein in lower airway samples as a biomarker for pneumonia[J]. Respir Res, 2021, 22(1): 174.
24
于燕兴，梅喜庆，刘凤娟，等. 高通量测序重症肺炎肺泡灌洗液病原体的临床应用[J/OL]. 中华肺部疾病杂志(电子版), 2024, 17(5): 785-788.
25
Heitz M, Levrat A, Lazarevic V, et al. Metagenomics for the microbiological diagnosis of hospital-acquired pneumonia and ventilator-associated pneumonia (HAP/VAP) in intensive care unit (ICU): a proof-of-concept study[J]. Respir Res, 2023, 24(1): 285.
26
Pinilla-gonzalez A, Lara-cantón I, Torrejón-rodríguez L, et al. Early molecular markers of ventilator-associated pneumonia in bronchoalveolar lavage in preterm infants[J]. Pediatr Res, 2023, 93(6): 1559-1565.
27
Chrzan R, Wizner B, Sydor W, et al. Artificial intelligence guided HRCT assessment predicts the severity of COVID-19 pneumonia based on clinical parameters[J]. BMC Infect Dis, 2023, 23(1): 314.
28
Mcgonagle D, Sharif K, O′Regan A, et al. The role of cytokines including interleukin-6 in COVID-19 induced pneumonia and macrophage activation syndrome-like disease[J]. Autoimmun Rev, 2020, 19(6): 102537.
29
Qin C, Ma H, Hu M, et al. Performance of artificial intelligence in predicting the prognossis of severe COVID-19: a systematic review and meta-analysis[J]. Front Public Health, 2024, 12: 1371852.
30
Barbieri MA, Battini V, Sessa M. Artificial intelligence for the optimal management of community-acquired pneumonia[J]. Curr Opin Pulm Med, 2024, 30(3): 252-257.
[1] 周欣, 梁豪进, 邓振宇, 肖菊花, 周小军. 基于人工智能技术评价江西省孕11~13+6周产前超声筛查质量现状及提出能力提升对策[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(09): 850-857.
[2] 张振奇, 齐艺涵, 王璐, 胡紫玥, 李婷婷, 卢漫. 大语言模型DeepSeek-R1在甲状腺超声报告质量控制中的初步应用[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(09): 832-837.
[3] 江瑶, 蒋程, 余翔, 谭莹, 温昕, 温慧莹, 彭桂艳, 李胜利. 基于注意力机制改进的子宫解剖结构检测与分割多任务模型的性能评估[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(08): 703-710.
[4] 陈明朗, 许凯, 黄稚熙, 梁博诚, 贺杰, 黄海珊, 马微波, 谭莹, 邹志英, 刘晓棠, 彭桂艳, 陈家希, 钟晓红. MobileNetV4：面向产前超声的主动脉弓分支异常智能诊断研究[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(08): 711-720.
[5] 杨丽仙, 黄稚熙, 梁博诚, 欧阳淑媛, 陈明朗, 赵英丽, 马薇波, 缪敬, 王磊, 袁鹰. 基于产前时序超声数据的新生儿出生体重智能预测[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(08): 721-732.
[6] 刘晴晴, 俞劲, 徐玮泽, 张志伟, 潘晓华, 舒强, 叶菁菁. OBICnet图像分类模型在小儿先天性心脏病超声筛查中的应用价值[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(08): 754-760.
[7] 傅小芳, 杨青翰, 孙昌琴, 豆梦杰, 胡峻溥, 孙灏, 吕发勤. 基于YOLO 11的肢体长骨骨折断端超声检测模型的临床价值[J/OL]. 中华医学超声杂志（电子版）, 2025, 22(06): 541-546.
[8] 毛俊, 蔡兆伦, 尹晓南, 沈朝勇, 张波. 影像组学预测模型在胃肠间质瘤诊断及预后中的研究进展[J/OL]. 中华普通外科学文献(电子版), 2025, 19(06): 421-425.
[9] 左泽平, 宇洪涛, 朱金海, 钱俊杰, 徐秀民, 王一行, 梁朝朝, 郝宗耀. 智能无线腔镜在超微通道经皮肾镜取石术中的临床应用[J/OL]. 中华腔镜泌尿外科杂志(电子版), 2025, 19(06): 736-741.
[10] 嵇振岭. 疝与腹壁外科补片研发国外进展[J/OL]. 中华疝和腹壁外科杂志(电子版), 2025, 19(06): 614-622.
[11] 王春, 许斌, 刘丹, 陶承志, 林欢, 张海涛. 支气管肺泡灌洗液PTPN2水平与矽肺患者疾病严重程度和肺功能的关系研究[J/OL]. 中华肺部疾病杂志(电子版), 2025, 18(06): 904-910.
[12] 谢钰嵘, 唐流康, 陈明政, 王伟利, 缪文学, 谢峰. 人工智能在肝胆外科临床教学中的应用[J/OL]. 中华肝脏外科手术学电子杂志, 2025, 14(06): 822-827.
[13] 江学良. 人工智能在炎症性肠病诊疗中的研究进展与应用展望[J/OL]. 中华消化病与影像杂志(电子版), 2025, 15(06): 680-680.
[14] 常芳媛, 乔春梅, 王欣, 王博冉, 赵梓孚, 李春歌, 王晓磊. 多模态超声及人工智能在细菌性和非细菌性关节炎中应用的研究进展[J/OL]. 中华临床医师杂志(电子版), 2025, 19(08): 606-611.
[15] 高兴梅, 周洁容, 杨溢, 张孟祥, 张仲谋, 李斌. 重症肺炎患者血磷水平轨迹与短期预后之间的关系[J/OL]. 中华临床医师杂志(电子版), 2025, 19(07): 479-485.
阅读次数
全文


摘要

版权所有 中华医学会 中华医学电子音像出版社有限责任公司  京ICP备14006079号-1  网络出版服务许可证：(署)网出证(京)字第075号

AI
小
编
AI小编
你好！我是《中华医学电子期刊资源库》AI小编，有什么可以帮您的吗？