{"title":"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。","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":"{\"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}","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}
Enhancing the accuracy and effectiveness of diagnosis of spontaneous bacterial peritonitis in cirrhotic patients: A machine learning approach utilizing clinical and laboratory data
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.
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.