Enhancing the accuracy and effectiveness of diagnosis of spontaneous bacterial peritonitis in cirrhotic patients: A machine learning approach utilizing clinical and laboratory data

IF 2.5 4区医学 Q3 MEDICINE, RESEARCH & EXPERIMENTAL

Advances in medical sciences Pub Date : 2024-10-16 DOI:10.1016/j.advms.2024.10.001

Babak Khorsand , Mohsen Rajabnia , Ali Jahanian , Mobin Fathy , Somayye Taghvaei , Hamidreza Houri

{"title":"Enhancing the accuracy and effectiveness of diagnosis of spontaneous bacterial peritonitis in cirrhotic patients: A machine learning approach utilizing clinical and laboratory data","authors":"Babak Khorsand , Mohsen Rajabnia , Ali Jahanian , Mobin Fathy , Somayye Taghvaei , Hamidreza Houri","doi":"10.1016/j.advms.2024.10.001","DOIUrl":null,"url":null,"abstract":"<div><h3>Purpose</h3><div>Spontaneous bacterial peritonitis (SBP) is a bacterial infection of ascitic fluid that develops naturally, without being triggered by any surgical conditions or procedures, and is a common complication of cirrhosis. With a potential mortality rate of 40 %, accurate diagnosis and prompt initiation of appropriate antibiotic therapy are crucial for optimizing patient outcomes and preventing life-threatening complications. This study aimed to expand the use of computational models to improve the diagnostic accuracy of SBP in cirrhotic patients by incorporating a broader range of data, including clinical variables and laboratory values.</div></div><div><h3>Patients and methods</h3><div>We employed 5 machine learning classification methods - Decision Tree, Support Vector Machine, Naive Bayes, K-Nearest Neighbor, and Random Forest, utilizing a variety of demographic, clinical, and laboratory features and biomarkers.</div></div><div><h3>Results</h3><div>Ascitic fluid markers, including white blood cell (WBC) count, lactate dehydrogenase (LDH), total protein, and polymorphonuclear cells (PMN), significantly differentiated between SBP and non-SBP patients. The Random Forest model demonstrated the highest overall accuracy at 86 %, while the Naive Bayes model achieved the highest sensitivity at 72 %. Utilizing 10 key features instead of the full feature set improved model performance, notably enhancing specificity and accuracy.</div></div><div><h3>Conclusion</h3><div>Our analysis highlights the potential of machine learning to enhance the accuracy of SBP diagnosis in cirrhotic patients. Integrating these models into clinical workflows could substantially improve patient outcomes. To achieve this, ongoing multidisciplinary research is crucial. Ensuring model interpretability, continuous monitoring, and rigorous validation will be essential for the successful implementation of real-time clinical decision support systems.</div></div>","PeriodicalId":7347,"journal":{"name":"Advances in medical sciences","volume":"70 1","pages":"Pages 1-7"},"PeriodicalIF":2.5000,"publicationDate":"2024-10-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in medical sciences","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1896112624000579","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MEDICINE, RESEARCH & EXPERIMENTAL","Score":null,"Total":0}

引用次数: 0

Abstract

Purpose

Spontaneous bacterial peritonitis (SBP) is a bacterial infection of ascitic fluid that develops naturally, without being triggered by any surgical conditions or procedures, and is a common complication of cirrhosis. With a potential mortality rate of 40 %, accurate diagnosis and prompt initiation of appropriate antibiotic therapy are crucial for optimizing patient outcomes and preventing life-threatening complications. This study aimed to expand the use of computational models to improve the diagnostic accuracy of SBP in cirrhotic patients by incorporating a broader range of data, including clinical variables and laboratory values.

Patients and methods

We employed 5 machine learning classification methods - Decision Tree, Support Vector Machine, Naive Bayes, K-Nearest Neighbor, and Random Forest, utilizing a variety of demographic, clinical, and laboratory features and biomarkers.

Results

Ascitic fluid markers, including white blood cell (WBC) count, lactate dehydrogenase (LDH), total protein, and polymorphonuclear cells (PMN), significantly differentiated between SBP and non-SBP patients. The Random Forest model demonstrated the highest overall accuracy at 86 %, while the Naive Bayes model achieved the highest sensitivity at 72 %. Utilizing 10 key features instead of the full feature set improved model performance, notably enhancing specificity and accuracy.

Conclusion

Our analysis highlights the potential of machine learning to enhance the accuracy of SBP diagnosis in cirrhotic patients. Integrating these models into clinical workflows could substantially improve patient outcomes. To achieve this, ongoing multidisciplinary research is crucial. Ensuring model interpretability, continuous monitoring, and rigorous validation will be essential for the successful implementation of real-time clinical decision support systems.

查看原文本刊更多论文

提高肝硬化患者自发性细菌性腹膜炎诊断的准确性和有效性：一种利用临床和实验室数据的机器学习方法。

目的：自发性细菌性腹膜炎（SBP）是一种腹腔积液的细菌感染，是肝硬化的常见并发症。腹腔积液的潜在死亡率高达 40%，因此准确诊断和及时启动适当的抗生素治疗对于优化患者预后和预防危及生命的并发症至关重要。本研究旨在扩大计算模型的使用范围，通过纳入更广泛的数据（包括临床变量和实验室值）来提高肝硬化患者SBP的诊断准确性：我们采用了 5 种机器学习分类方法--决策树、支持向量机、Naive Bayes、K-近邻和随机森林，并利用了各种人口统计学、临床和实验室特征及生物标志物：结果：腹水标志物，包括白细胞（WBC）计数、乳酸脱氢酶（LDH）、总蛋白和多形核细胞（PMN），能显著区分SBP和非SBP患者。随机森林模型的总体准确率最高，达 86%，而 Naive Bayes 模型的灵敏度最高，达 72%。利用 10 个关键特征而不是全部特征集提高了模型的性能，尤其是提高了特异性和准确性：我们的分析凸显了机器学习在提高肝硬化患者 SBP 诊断准确性方面的潜力。将这些模型整合到临床工作流程中可以大大改善患者的预后。为此，持续的多学科研究至关重要。确保模型的可解释性、持续监测和严格验证对于实时临床决策支持系统的成功实施至关重要。

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

Advances in medical sciences 医学-医学：研究与实验

CiteScore

5.00

自引率

0.00%

发文量

审稿时长

25 days

期刊介绍： Advances in Medical Sciences is an international, peer-reviewed journal that welcomes original research articles and reviews on current advances in life sciences, preclinical and clinical medicine, and related disciplines. The Journal’s primary aim is to make every effort to contribute to progress in medical sciences. The strive is to bridge laboratory and clinical settings with cutting edge research findings and new developments. Advances in Medical Sciences publishes articles which bring novel insights into diagnostic and molecular imaging, offering essential prior knowledge for diagnosis and treatment indispensable in all areas of medical sciences. It also publishes articles on pathological sciences giving foundation knowledge on the overall study of human diseases. Through its publications Advances in Medical Sciences also stresses the importance of pharmaceutical sciences as a rapidly and ever expanding area of research on drug design, development, action and evaluation contributing significantly to a variety of scientific disciplines. The journal welcomes submissions from the following disciplines: General and internal medicine, Cancer research, Genetics, Endocrinology, Gastroenterology, Cardiology and Cardiovascular Medicine, Immunology and Allergy, Pathology and Forensic Medicine, Cell and molecular Biology, Haematology, Biochemistry, Clinical and Experimental Pathology.