白细胞介素家族对局部与脓毒性系统性炎症反应综合征的诊断价值  

The diagnostic value of interleukin family for local and septic systemic inflammatory response syndrome

作　　者：方丽霞 FANG Li-xia(Clinical Laboratory,Anji County Hospital of Traditional Chinese Medicine,Anji,Zhejiang 313300,China)

机构地区：[1]浙江省湖州市安吉县中医院检验科,浙江安吉313300

出　　处：《中国卫生检验杂志》2022年第5期569-573,共5页Chinese Journal of Health Laboratory Technology

摘　　要：目的评价白细胞介素家族非脓毒性系统性炎症反应综合征(SIRS)/脓毒性SIRS鉴别诊断中的价值。方法选取2018年9月—2020年7月38例对照组志愿者、95例非脓毒性SIRS患者以及106例脓毒症患者,检测常用炎症指标白细胞计数、中性粒细胞计数、血清hs-CRP、PCT、SAA,以及白细胞介素IL-1α、IL-1β、IL-2、IL-4、IL-5、IL-6、IL-8、IL-10、IL-12、IL-17的表达,并依据以上指标,首先使用Logistic回归算法构建非脓毒性SIRS、脓毒性SIRS以及两者鉴别诊断的模型,并使用曲线下面积(AUC)评估模型的性能。同时分别选取白细胞介素指标、白细胞介素+常用指标,使用随机森林算法对以上指标的重要性进行排序,并选取重要的指标,使用Logistic回归算法构建新的诊断模型。结果在单独应用以上15种指标诊断脓毒症、非脓毒性SIRS以及两者的鉴别诊断,模型的AUC均<0.72,联合应用白细胞介素指标后,AUC达到75.5%,联合应用常用指标后AUC达到82.0%。而在使用随机森林算法对变量重要性进行筛选后,基于白细胞介素指标的诊断模型的AUC为90.8%,联合应用常用指标后AUC为93.4%。结论通过重要性筛选构建的、基于IL-5、IL-6、IL-4、IL-1β、PCT构建的非脓毒性SIRS/脓毒性SIRS鉴别诊断模型具有很好的效能。Objective To evaluate the value of interleukin family in differential diagnosis of non-infectious systemic inflammatory response syndrome(SIRS)/sepsis.Methods A total of 38 cases of control donor,95 cases of non-infectious SIRS and106 cases of sepsis patients were collected for the detection of commonly used inflammatory indicators:white blood cell count,neutrophil count,hs-CRP,PCT,SAA in serum,and IL-1α,IL-1β,IL-2,IL-4,IL-5,IL-6,IL-8,IL-10,IL-12,IL-17 from interleukin family.Based on the indicators above,Logistic regression algorithm was adopted to build the diagnosis and differential diagnosis of non-infectious SIRS and sepsis,and the AUC is used to evaluate the performance of the model.Meanwhile,combining interleukin,interleukin and common indicators,random forest algorithm was used to rank the importance of the above indicators,and important indicators were selected.Logistics regression algorithm was used to construct a new diagnostic model.Results In the diagnosis of sepsis,non-sepsis SIRS and their differential diagnosis by using the above 15 indexes alone,the AUC of the model is less than 0.72.After combining interleukin,the AUC of the model reached75.5%,combined with common indicators,the AUC of the model reached 82.0%.After using the random forest algorithm to rank the importance of variables,the AUC of the diagnosis model based on the interleukin index reaches 90.8%,and the AUC reaches 93.4%after combined with common indexes.Conclusion The non-infectious SIRS/sepsis differential diagnosis model based on IL-5,IL-6,IL-4,IL-1βand PCT constructed by important indicators which ranked by importance has good efficacy.

关 键 词：系统性炎症反应综合征 脓毒症 白细胞介素家族 鉴别诊断 

分 类 号：R631[医药卫生—外科学]