Establishment and verification of a diagnostic model of liver cirrhosis with spontaneous bacterial peritonitis

Shoushu XIANG; Juntao TAN; Yuanjiu WEN; Chao TAN; Jun GONG; Wenlong ZHAO

doi:10.16016/j.1000-5404.202104100

您当前的位置：

首页 >

文章列表页 >

Establishment and verification of a diagnostic model of liver cirrhosis with spontaneous bacterial peritonitis

Clinical Medicine | 更新时间：2026-01-09

- Establishment and verification of a diagnostic model of liver cirrhosis with spontaneous bacterial peritonitis
- Journal of Third Military Medical University Vol. 43, Issue 20, Pages: 2226-2234(2021)
- 作者机构：
  
  1.400016 重庆，重庆医科大学医学信息学院
  2.400038 重庆，陆军军医大学(第三军医大学)全科医学系
- 作者简介：
- 基金信息：
  
  Supported by the Intelligent Medicine Research Project of Chongqing Medical University(重庆医科大学智慧医学项目)
- DOI：10.16016/j.1000-5404.202104100
  CLC： R195.4;R572.2;R575.2
- Received：16 April 2021，
  
  Revised：2021-07-05，
  
  Published：30 October 2021
- 稿件说明：
移动端阅览
Shoushu XIANG, Juntao TAN, Yuanjiu WEN, et al. Establishment and verification of a diagnostic model of liver cirrhosis with spontaneous bacterial peritonitis[J]. Journal of Third Military Medical University, 2021, 43(20): 2226-2234.
DOI：

Shoushu XIANG, Juntao TAN, Yuanjiu WEN, et al. Establishment and verification of a diagnostic model of liver cirrhosis with spontaneous bacterial peritonitis[J]. Journal of Third Military Medical University, 2021, 43(20): 2226-2234. DOI： 10.16016/j.1000-5404.202104100.

摘要

目的

筛选肝硬化伴自发性细菌性腹膜炎(spontaneous bacterial peritonitis，SBP) 的影响因素，建立肝硬化伴SBP的诊断模型。

方法

收集重庆A、B两家三甲医院2015年7月至2019年12月肝硬化患者7 461例，根据患者住院期间是否发生SBP分为SBP组(1 173例)和非SBP组(6 288例)。随机抽取A院70%(3 776例)患者作为训练集，剩余30%(1 619例)作为内部验证集，B院患者(2 066例)作为外部验证集。通过单因素分析和Logistic回归分析筛选变量，建立Logistic回归、随机森林、决策树、XGBoost和优化Logistic回归模型。在内部验证和外部验证中，比较并验证模型对肝硬化伴SBP的诊断价值。

结果

机器学习算法均提示指标失代偿(

=5.354，95%

: 3.770-7.803)，淋巴细胞百分比(

=0.951，95%

: 0.939-0.962)、总胆红素(

=1.003，95%

: 1.002-1.004)、C反应蛋白是否异常(

=1.626，95%

: 1.310-2.017)、国际标准化比值(

=1.346，95%

: 1.091-1.681)、前白蛋白(

=0.990，95%

: 0.987-0.993)、终末期肝病模型评分(model for end stage liver disease，MELD) (

=1.038，95%

: 1.015-1.063)为显著性因素，优化Logistic内部验证的AUC为0.860，灵敏度0.872，特异度0.719；外部验证的AUC为0.818；灵敏度为0.662，特异度为0.812。经过delong test检测优化Logistic回归模型和其余模型的AUC差异无统计学意义。

结论

基于机器学习算法建立的肝硬化合并SBP风险预测模型具有较高的诊断价值，其中优化Logistic回归模型的诊断效能在内部验证和外部验证中均表现良好，可为临床诊断SBP提供参考。

Abstract

Objective

To screen the influencing factors of liver cirrhosis with spontaneous bacterial peritonitis (SBP) so as to establish and verify a diagnostic model of cirrhosis with SBP.

Methods

A total of 7 461 patients with liver cirrhosis were collected from 2 Grade-A hospitals in Chongqing (Hospital A and B) between July 2015 and December 2019. According to the occurrence of SBP during hospitalization

they were divided into SBP (

=1 173) and non-SBP (

=6 288) groups. A total of 3 776 patients (70%) from Hospital A were randomly selected as the training set

while the remaining 1 619 patients (30%) and the 2 066 patients from hospital B were subjected as the internal and external validation sets respectively. Univariate and logistic analyses were used to screen variables

and logistic regression

random forest (RF)

decision tree (DT) and XGBoost models were subsequently established using the training set. Then

the optimized logistic regression model was built on the basis of the above 4 models. Finally

the 5 models were applied in the internal and external verification sets for eval

uating and comparing the diagnostic value of different models for cirrhosis with SBP.

Results

The machine learning algorithm suggested that the 7 common influencing factors with significance in all models were as follows: decompensation stage (

=5.354

95%

: 3.770-7.803)

lymphocyte percentage (

=0.951

95%

: 0.939-0.962)

total bilirubin (

=1.003

95%

: 1.002-1.004)

abnormal C-reactive protein (

=1.626

95%

: 1.310-2.017)

international normalized ratio (

=1.346

95%

: 1.091-1.681)

prealbumin (

=0.990

95%

: 0.987-0.993) and model for end stage liver disease (MELD) score (

=1.038

95%

: 1.015-1.063). The AUC of the internal verification of the optimized logistic model was 0.860

with a sensitivity of 0.872 and a specificity of 0.719; while the corresponding values of the external verification were 0.818

0.662 and 0.812

respectively. Delong test showed that there was no statistical difference in AUC between the optimized logistic regression model and the other models with favorable performance.

Conclusion

The risk prediction models established by machine learning algorithm for liver cirrhosis complicated with SBP have high diagnostic value. Among them

the optimized logistic regression model has performed well in both internal and external verification

and is able to provide reference for clinical diagnosis of SBP.

关键词

Keywords

references

BUNCHORNTAVAKUL C, CHAMROONKUL N, CHAVALITDHAMRONG D. Bacterial infections in cirrhosis: a critical review and practical guidance[J]. World J Hepatol, 2016, 8(6): 307-321. DOI: 10.4254/wjh.v8.i6.307.

ALBILLOS A, LARIO M, ÁLVAREZ-MON M. Cirrhosis-associated immune dysfunction: distinctive features and clinical relevance[J]. J Hepatol, 2014, 61(6): 1385-1396. DOI: 10.1016/j.jhep.2014.08.010.

徐小元, 丁惠国, 李文刚, 等. 肝硬化腹水及相关并发症的诊疗指南[J]. 实用肝脏病杂志, 2018, 21(1): 21-31.

XU X Y, DING H G, LI W G, et al . Guidelines on the management of ascites and complications in cirrhosis[J ] . J Pract Hepatol, 2018, 21(1): 21-31.

BONNEL A R, BUNCHORNTAVAKUL C, REDDY K R. Immune dysfunction and infections in patients with cirrhosis[J]. Clin Gastroenterol Hepatol, 2011, 9(9): 727-738. DOI: 10.1016/j.cgh.2011.02.031.

ARVANITI V, D'AMICO G, FEDE G, et al . Infections in patients with cirrhosis increase mortality four-fold and should be used in determining prognosis[J ] . Gastroenterology, 2010, 139(4): 1246-1256, 1256. e1. DOI: 10.1053/j.gastro.2010.06.019.

BAJAJ J S, O'LEARY J G, REDDY K R, et al . Second infections independently increase mortality in hospitalized patients with cirrhosis: the North American consortium for the study of end-stage liver disease (NACSELD) experience[J ] . Hepatology, 2012, 56(6): 2328-2335. DOI: 10.1002/hep.25947.

SINGAL A K, SALAMEH H, KAMATH P S. Prevalence and in-hospital mortality trends of infections among patients with cirrhosis: a nationwide study of hospitalised patients in the United States[J]. Aliment Pharmacol Ther, 2014, 40(1): 105-112. DOI: 10.1111/apt.12797.

李浩, 程璠, 郭东星, 等. 肝硬化患者并发自发性细菌性腹膜炎的高危特征与潜在风险分析[J]. 中国卫生统计, 2020, 37(5): 664-666.

LI H, CHENG F, GUO D X, et al . Latent class analysis of distribution characteristics in cirrhosis complicated by spontaneous bacterial peritonitis[J ] . Chin J Heal Stat, 2020, 37(5): 664-666.

[新华社. 中共中央国务院印发《"健康中国2030"规划纲要》[ EB/OL ] . (2016-10-25)[2021-03-18 ] . http://www.gov.cn/zhengce/2016-10/25/content_5124174.htm http://www.gov.cn/zhengce/2016-10/25/content_5124174.htm .

[Xinhua News Agency. State Council of China issued "Healthy China 2030" Planning Outline[EB/OL ] . (2016-10-25)[2021-03-18 ] . http://www.gov.cn/zhengce/2016-10/25/content_5124174.htm http://www.gov.cn/zhengce/2016-10/25/content_5124174.htm .

GOECKS J, JALILI V, HEISER L M, et al . How machine learning will transform biomedicine[J ] . Cell, 2020, 181(1): 92-101. DOI: 10.1016/j.cell.2020.03.022.

ZHU L C, XU L, HE W H, et al . A quick screening mo del for symptomatic bacterascites in cirrhosis[J ] . Saudi J Gastroenterol, 2016, 22(4): 282-287. DOI: 10.4103/1319-3767.187600.

王苏淮, 李晶洁. 机器学习在心血管疾病中的临床应用进展[J]. 心血管病学进展, 2021, 42(2): 144-147. DOI: 10.16806/j.cnki.issn.1004-3934.2021.02.013.

WANG S H, LI J J. Clinical applications of machine learning in cardiovascular[J]. Adv Cardiovasc Dis, 2021, 42(2): 144-147. DOI: 10.16806/j.cnki.issn.1004-3934.2021.02.013.

BZDOK D, KRZYWINSKI M, ALTMAN N. Machine learning: supervised methods[J]. Nat Methods, 2018, 15(1): 5-6. DOI: 10.1038/nmeth.4551.

FELDMANN J, YOUNGBLOOD N, WRIGHT C D, et al . All-optical spiking neurosynaptic networks with self-learning capabilities[J ] . Nature, 2019, 569(7755): 208-214. DOI: 10.1038/s41586-019-1157-8.

徐小元, 丁惠国, 李文刚, 等. 肝硬化诊治指南[J]. 临床肝胆病杂志, 2019, 35: 2408-2425.

XU X Y, DING H G, LI W G, et al . Chinese guidelines on the management of liver cirrhosis[J ] . J Clin Hepatol, 2019, 35: 2408-2425.

European Association for the Study of the Liver. EASL clinical practice guidelines on the management of ascites, spontaneous bacterial peritonitis, and hepatorenal syndrome in cirrhosis[J]. J Hepatol, 2010, 53(3): 397-417. DOI: 10.1016/j.jhep.2010.05.004.

ZOPLUOGLU C. Detecting examinees with itempreknowledge in large-scale testing using extreme gradient boosting (XGBoost)[J]. Educ Psychol Meas, 2019, 79(5): 931-961. DOI: 10.1177/0013164419839439.

王俊峰, 章仲恒, 周支瑞, 等. 临床预测模型: 模型的验证[J]. 中国循证心血管医学杂志, 2019, 11(2): 141-144.

WANG J F, ZHANG Z H, ZHOU Z R, et al . Clinical prediction models: Model validation[J ] . Chin J Evid Based Cardiovasc Med, 2019, 11(2): 141-144.

STEYERBERG E W, HARRELL F E. Prediction models need appropriate internal, internal-external, and external validation[J]. J Clin Epidemiol, 2016, 69: 245-247. DOI: 10.1016/j.jclinepi.2015.04.005.

ZASTROW S, KRABBE L M, WOLFF I, et al . External validation of a postoperative nomogram for the prediction of disease-specific survival in patients with papillary renal cell carcinoma using a large multicenter database[J ] . Int J Clin Oncol, 2020, 25(1): 145-150. DOI: 10.1007/s10147-019-01530-x.

POCA M, CONCEPCIÓN M, CASAS M, et al . Role of albumin treatment in patients with spontaneous bacterial peritonitis[J ] . Clin Gastroenterol Hepatol, 2012, 10(3): 309-315. DOI: 10.1016/j.cgh.2011.11.012.

SHIZUMA T. Spontaneous bacterial and fungal peritonitis in patients with liver cirrhosis: A literature review[J]. World J Hepatology, 2018, 10(2): 254-266. DOI: 10.4254/wjh.v10.i2.254.

张天洪, 陈婧, 万雪梅. 肝硬化并自发性腹膜炎96例临床诊治探讨[J]. 西南医科大学学报, 2018, 41(5): 436-440.

ZHANG T H, CHEN J, WAN X M. Clinical diagnosis and treatment of liver cirrhosis complicated by spontaneous peritonitis: An analysis of 96 cases[J]. J Xinan Med Univ, 2018, 41(5): 436-440.

李维勤, 王新颖, 朱虹, 等. 严重感染患者血清白蛋白动力学研究[J]. 解放军医学杂志, 2005, 30(11): 978-980. DOI: 10.3321/j.issn:0577-7402.2005.11.013.

LI W Q, WANG X Y, ZHU H, et al . Kinetics of serum albumin in patients with severe Sepsis[J ] . Med J PLA, 2005, 30(11): 978-980. DOI: 10.3321/j.issn:0577-7402.2005.11.013.

王新颖, 李维勤, 李宁, 等. 内毒素抑制肝细胞白蛋白表达的分子机制研究[J]. 中国危重病急救医学, 2004(10): 626-628. DOI: 10.3760/j.issn:1003-0603.2004.10.015.

WANG X Y, LI W Q, LI N, et al . Study on molecular mechanisms of indirect suppression of albumin mRNA expression of hepatocytes by lipopolysaccharide in rat[J ] . Chin Crit Care Med, 2004(10): 626-628. DOI: 10.3760/j.issn:1003-0603.2004.10.015.

LIU F, CAI L Y, ZHONG L, et al . Model for end-stage liver disease combined with serum prealbumin to predict the prognosis of patients with decompensated liver cirrhosis[J ] . J Dig Dis, 2010, 11(6): 352-357. DOI: 10.1111/j.1751-2980.2010.00465.x.

杜小华. 血清前白蛋白检测在肝脏疾病诊断中的应用[J]. 中国继续医学教育, 2018, 10(18): 53-54.

DU X H. The application of prealbumin in the diagnosis of liver disease[J]. China Continu Med Educ, 2018, 10(18): 53-54.

TAN L, MENG Y, ZENG T, et al . Clinical diagnostic significance of prealbumin, cholinesterase and retinol binding protein in liver cirrhosis combined with encephalopathy[J ] . Br J Biomed Sci, 2019, 76(1): 24-28. DOI: 10.1080/09674845.2018.1523673.

申红霞, 娄小平, 苌新伟, 等. 肝硬化患者自发性细菌性腹膜炎危险因素的Meta分析[J]. 世界华人消化杂志, 2016, 24(12): 1903-1909.

SHEN H X, LOU X P, CHANG X W, et al . Risk factors for spontaneous bacterial peritonitis in cirrhotic pati ents: A meta analysis[J ] . World Chin J Dig, 2016, 24(12): 1903-1909.

PAUL K, KAUR J, KAZAL H L. To study the incidence, predictive factors and clinical outcome of spontaneous bacterial peritonitis in patients of cirrhosis with ascites[J]. J Clin Diagn Res, 2015, 9(7): OC09-OC12. DOI: 10.7860/jcdr/2015/14855.6191.

林太顺, 林清标, 孔金峰, 等. 降钙素原联合C反应蛋白检测在肝衰竭合并自发性腹膜炎疾病中的诊断价值[J]. 临床合理用药杂志, 2019, 12(14): 5-6. DOI: 10.15887/j.cnki.13-1389/r.2019.14.003.

LIN T S, LIN Q B, KONG J F, et al . Diagnostic value of procalcitonin combined with C-reactive protein in liver failure complicated with spontaneous peritonitis[J ] . Chin J Clin Ration Drug Use, 2019, 12(14): 5-6. DOI: 10.15887/j.cnki.13-1389/r.2019.14.003.

KAMATH P S, WIESNER R H, MALINCHOC M, et al . A model to predict survival in patients with end-stage liver disease[J ] . Hepatology, 2001, 33(2): 464-470. DOI: 10.1053/jhep.2001.22172.

YANG W B, CHEN E Q, BI H X, et al . Different modelsin predicting the short-term prognosis of patients with hepatitis B virus-related acute-on-chronic liver failure[J ] . Ann Hepatol, 2012, 11(3): 311-319. DOI: 10.1016/S1665-2681(19)30925-1.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Biomarkers for hemorrhagic shock at high-altitude based on metabolomics and machine learning: Identification and validation of D-inositol-4-phosphate, phosalone and methionine

Risk factors for postoperative respiratory failure in patients undergoing cardiovascular surgery and construction of a prediction model

Development of a postoperative recurrence prediction model for stage Ⅰ non-small cell lung cancer patients using multimodal data based on machine learning

Construction of machine learning-based prognostic model of centrosome amplification-related genes for esophageal squamous cell carcinoma

Related Author

GUO Pengpeng

KOU Menglin

HUANG Jingyue

FANG Jingya

LI Mei

XUE Aiguo

LIANG Jingrong

ZHOU Yuanqun

Related Institution

Department of Internal Medicine， Zhuhai Center for Chronic Disease Control and Prevention

Department of Acupuncture and Moxibustion， Dongguan Hospital of Guangzhou University of Chinese Medicine

National Key Laboratory of Trauma and Chemical Poisoning， Department of War Trauma， Shock and Blood Transfusion， Daping Hospital， Army Medical University（Third Military Medical University）

Department of Anesthesiology， First Affiliated Hospital， Army Medical University （Third Military Medical University）

Jinfeng Laboratory

⁰