Risk stratification of spontaneous bacterial peritonitis recurrence: integrating acute kidney injury, biomarkers, composite scores, and machine learning models.

IF 5 3区医学 Q1 GASTROENTEROLOGY & HEPATOLOGY

Gut Pathogens Pub Date : 2025-12-07 DOI:10.1186/s13099-025-00774-5

Nasser Mousa, Alaa Elmetwalli, Mostafa Abdelsalam, Mohamed Wahba, Mohamed Selim, Dina Nour, Eman Abdelkader, Ahmed El-Eraky, Amany Hasson, Ahmed E Taha, Eman Mousa, Adel El-Assmy, Ali El-Assmy, Sherif Shiha, Muhammad Diasty, Mohammed Abdelaziz, Shereen A Mourad, Nader Elmalky, Marwa Mansour

{"title":"Risk stratification of spontaneous bacterial peritonitis recurrence: integrating acute kidney injury, biomarkers, composite scores, and machine learning models.","authors":"Nasser Mousa, Alaa Elmetwalli, Mostafa Abdelsalam, Mohamed Wahba, Mohamed Selim, Dina Nour, Eman Abdelkader, Ahmed El-Eraky, Amany Hasson, Ahmed E Taha, Eman Mousa, Adel El-Assmy, Ali El-Assmy, Sherif Shiha, Muhammad Diasty, Mohammed Abdelaziz, Shereen A Mourad, Nader Elmalky, Marwa Mansour","doi":"10.1186/s13099-025-00774-5","DOIUrl":null,"url":null,"abstract":"Background and aim: Recurrent spontaneous bacterial peritonitis (SBP) is a major concern for cirrhotic patients with ascites. This study seeks to identify predictors of recurrent SBP using clinical factors, inflammatory markers, and machine learning models.Patients and methods: The study involved 347 patients with cirrhotic ascites and SBP. Receiver Operating Characteristic (ROC) curve analysis assessed the predictive ability of biomarkers. A composite score was created to evaluate the risk stratification model. Different machine learning models were compared for predictive accuracy.Results: Eighty-three patients (23.9%) experienced recurrent SBP. Independent predictors of recurrence in multivariable analysis included acute kidney injury (AKI), elevated C-reactive protein (CRP) levels, higher serum bilirubin levels, a higher model for end-stage liver disease (MELD) score, proton-pump inhibitor (PPI) use, and lack of β-blocker use. A composite 10-point score (including AKI, CRP > 50 mg/L, low albumin levels < 2.5 g/dL, ascitic protein < 1.0 g/dL, albumin/ascitic ratio < 2.5 [2 points], MELD ≥ 15, diabetes, multidrug-resistant organism [MDRO] infection, and non-use of β-blockers) stratified the risk of recurrence into low (0-3: 15%), moderate (4-6: 45%), and high (7-10: 80%) categories. Machine learning models outperformed supervised machine logistic regression in predicting recurrence. Logistic regression achieved 70% accuracy, 65% sensitivity, and 68% specificity. The decision tree model improved accuracy to 75%, sensitivity to 72%, and specificity to 71%. The random forest model showed the best performance with 78% accuracy, 77% sensitivity, and 76% specificity.Conclusion: A composite score, combined with machine-learning models like random forest, enhances risk assessment for SBP recurrence. Clinical predictors such as AKI, CRP, bilirubin, MELD, PPI use, and β-blockers non-use help in targeted prevention.","PeriodicalId":12833,"journal":{"name":"Gut Pathogens","volume":" ","pages":"103"},"PeriodicalIF":5.0000,"publicationDate":"2025-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12699928/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Gut Pathogens","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1186/s13099-025-00774-5","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"GASTROENTEROLOGY & HEPATOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Background and aim: Recurrent spontaneous bacterial peritonitis (SBP) is a major concern for cirrhotic patients with ascites. This study seeks to identify predictors of recurrent SBP using clinical factors, inflammatory markers, and machine learning models.

Patients and methods: The study involved 347 patients with cirrhotic ascites and SBP. Receiver Operating Characteristic (ROC) curve analysis assessed the predictive ability of biomarkers. A composite score was created to evaluate the risk stratification model. Different machine learning models were compared for predictive accuracy.

Results: Eighty-three patients (23.9%) experienced recurrent SBP. Independent predictors of recurrence in multivariable analysis included acute kidney injury (AKI), elevated C-reactive protein (CRP) levels, higher serum bilirubin levels, a higher model for end-stage liver disease (MELD) score, proton-pump inhibitor (PPI) use, and lack of β-blocker use. A composite 10-point score (including AKI, CRP > 50 mg/L, low albumin levels < 2.5 g/dL, ascitic protein < 1.0 g/dL, albumin/ascitic ratio < 2.5 [2 points], MELD ≥ 15, diabetes, multidrug-resistant organism [MDRO] infection, and non-use of β-blockers) stratified the risk of recurrence into low (0-3: 15%), moderate (4-6: 45%), and high (7-10: 80%) categories. Machine learning models outperformed supervised machine logistic regression in predicting recurrence. Logistic regression achieved 70% accuracy, 65% sensitivity, and 68% specificity. The decision tree model improved accuracy to 75%, sensitivity to 72%, and specificity to 71%. The random forest model showed the best performance with 78% accuracy, 77% sensitivity, and 76% specificity.

Conclusion: A composite score, combined with machine-learning models like random forest, enhances risk assessment for SBP recurrence. Clinical predictors such as AKI, CRP, bilirubin, MELD, PPI use, and β-blockers non-use help in targeted prevention.

Abstract Image

查看原文本刊更多论文

自发性细菌性腹膜炎复发的风险分层：整合急性肾损伤、生物标志物、综合评分和机器学习模型。

背景和目的：复发性自发性细菌性腹膜炎（SBP）是肝硬化腹水患者的主要问题。本研究旨在通过临床因素、炎症标志物和机器学习模型来确定复发性收缩压的预测因素。患者和方法：该研究纳入了347例肝硬化腹水和收缩压患者。受试者工作特征（ROC）曲线分析评估生物标志物的预测能力。创建一个综合评分来评估风险分层模型。比较了不同的机器学习模型的预测准确性。结果：83例（23.9%）患者复发性收缩压。在多变量分析中，复发的独立预测因子包括急性肾损伤（AKI）、c反应蛋白（CRP）水平升高、血清胆红素水平升高、终末期肝病模型（MELD）评分较高、质子泵抑制剂（PPI）的使用以及β受体阻滞剂的缺乏。综合10分评分（包括AKI、CRP > 50 mg/L、低白蛋白水平）结论：综合评分与随机森林等机器学习模型相结合，增强了收缩压复发的风险评估。临床预测指标如AKI、CRP、胆红素、MELD、PPI使用和β受体阻滞剂不使用有助于有针对性的预防。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Gut Pathogens GASTROENTEROLOGY & HEPATOLOGY-MICROBIOLOGY

CiteScore

7.70

自引率

2.40%

发文量

期刊介绍： Gut Pathogens is a fast publishing, inclusive and prominent international journal which recognizes the need for a publishing platform uniquely tailored to reflect the full breadth of research in the biology and medicine of pathogens, commensals and functional microbiota of the gut. The journal publishes basic, clinical and cutting-edge research on all aspects of the above mentioned organisms including probiotic bacteria and yeasts and their products. The scope also covers the related ecology, molecular genetics, physiology and epidemiology of these microbes. The journal actively invites timely reports on the novel aspects of genomics, metagenomics, microbiota profiling and systems biology. Gut Pathogens will also consider, at the discretion of the editors, descriptive studies identifying a new genome sequence of a gut microbe or a series of related microbes (such as those obtained from new hosts, niches, settings, outbreaks and epidemics) and those obtained from single or multiple hosts at one or different time points (chronological evolution).