Assisting the Diagnosis of Cirrhosis in Chronic Hepatitis C Patients Based on Machine Learning Algorithms: A Novel Non-Invasive Approach.

IF 2.6 4区医学 Q2 MEDICAL LABORATORY TECHNOLOGY

Journal of Clinical Laboratory Analysis Pub Date : 2025-05-19 DOI:10.1002/jcla.70054

Emre Dirican, Tayibe Bal, Yusuf Onlen, Figen Sarigul, Ulku User, Nagehan Didem Sari, Behice Kurtaran, Ebubekir Senates, Alper Gunduz, Esra Zerdali, Hasan Karsen, Ayse Batirel, Ridvan Karaali, Hatice Rahmet Guner, Tansu Yamazhan, Sukran Kose, Nurettin Erben, Nevin Koc Ince, Iftihar Koksal, Nefise Oztoprak, Gulsen Yoruk, Suheyla Komur, Sibel Yildiz Kaya, Ilkay Bozkurt, Ozgur Gunal, Ilknur Esen Yildiz, Dilara Inan, Sener Barut, Mustafa Namiduru, Selma Tosun, Kamuran Turker, Alper Sener, Kenan Hizel, Nurcan Baykam, Fazilet Duygu, Hurrem Bodur, Guray Can, Hanefi Cem Gul, Ayse Sagmak Tartar, Guven Celebi, Mahmut Sunnetcioglu, Oguz Karabay, Hayat Kumbasar Karaosmanoglu, Fatma Sirmatel, Omer Fehmi Tabak

{"title":"Assisting the Diagnosis of Cirrhosis in Chronic Hepatitis C Patients Based on Machine Learning Algorithms: A Novel Non-Invasive Approach.","authors":"Emre Dirican, Tayibe Bal, Yusuf Onlen, Figen Sarigul, Ulku User, Nagehan Didem Sari, Behice Kurtaran, Ebubekir Senates, Alper Gunduz, Esra Zerdali, Hasan Karsen, Ayse Batirel, Ridvan Karaali, Hatice Rahmet Guner, Tansu Yamazhan, Sukran Kose, Nurettin Erben, Nevin Koc Ince, Iftihar Koksal, Nefise Oztoprak, Gulsen Yoruk, Suheyla Komur, Sibel Yildiz Kaya, Ilkay Bozkurt, Ozgur Gunal, Ilknur Esen Yildiz, Dilara Inan, Sener Barut, Mustafa Namiduru, Selma Tosun, Kamuran Turker, Alper Sener, Kenan Hizel, Nurcan Baykam, Fazilet Duygu, Hurrem Bodur, Guray Can, Hanefi Cem Gul, Ayse Sagmak Tartar, Guven Celebi, Mahmut Sunnetcioglu, Oguz Karabay, Hayat Kumbasar Karaosmanoglu, Fatma Sirmatel, Omer Fehmi Tabak","doi":"10.1002/jcla.70054","DOIUrl":null,"url":null,"abstract":"Aim: This study aimed to determine the important features and cut-off values after demonstrating the detectability of cirrhosis using routine laboratory test results of chronic hepatitis C (CHC) patients in machine learning (ML) algorithms.Methods: This retrospective multicenter (37 referral centers) study included the data obtained from the Hepatitis C Turkey registry of 1164 patients with biopsy-proven CHC. Three different ML algorithms were used to classify the presence/absence of cirrhosis with the determined features.Results: The highest performance in the prediction of cirrhosis (Accuracy = 0.89, AUC = 0.87) was obtained from the Random Forest (RF) method. The five most important features that contributed to the classification were platelet, αlpha-feto protein (AFP), age, gamma-glutamyl transferase (GGT), and prothrombin time (PT). The cut-off values of these features were obtained as platelet < 182.000/mm3, AFP > 5.49 ng/mL, age > 52 years, GGT > 39.9 U/L, and PT > 12.35 s. Using cut-off values, the risk coefficients were AOR = 4.82 for platelet, AOR = 3.49 for AFP, AOR = 4.32 for age, AOR = 3.04 for GGT, and AOR = 2.20 for PT.Conclusion: These findings indicated that the RF-based ML algorithm could classify cirrhosis with high accuracy. Thus, crucial features and cut-off values for physicians in the detection of cirrhosis were determined. In addition, although AFP is not included in non-invasive indexes, it had a remarkable contribution in predicting cirrhosis.Trial registration: Clinicaltrials.gov identifier: NCT03145844.","PeriodicalId":15509,"journal":{"name":"Journal of Clinical Laboratory Analysis","volume":" ","pages":"e70054"},"PeriodicalIF":2.6000,"publicationDate":"2025-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Clinical Laboratory Analysis","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1002/jcla.70054","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICAL LABORATORY TECHNOLOGY","Score":null,"Total":0}

引用次数: 0

Abstract

Aim: This study aimed to determine the important features and cut-off values after demonstrating the detectability of cirrhosis using routine laboratory test results of chronic hepatitis C (CHC) patients in machine learning (ML) algorithms.

Methods: This retrospective multicenter (37 referral centers) study included the data obtained from the Hepatitis C Turkey registry of 1164 patients with biopsy-proven CHC. Three different ML algorithms were used to classify the presence/absence of cirrhosis with the determined features.

Results: The highest performance in the prediction of cirrhosis (Accuracy = 0.89, AUC = 0.87) was obtained from the Random Forest (RF) method. The five most important features that contributed to the classification were platelet, αlpha-feto protein (AFP), age, gamma-glutamyl transferase (GGT), and prothrombin time (PT). The cut-off values of these features were obtained as platelet < 182.000/mm³, AFP > 5.49 ng/mL, age > 52 years, GGT > 39.9 U/L, and PT > 12.35 s. Using cut-off values, the risk coefficients were AOR = 4.82 for platelet, AOR = 3.49 for AFP, AOR = 4.32 for age, AOR = 3.04 for GGT, and AOR = 2.20 for PT.

Conclusion: These findings indicated that the RF-based ML algorithm could classify cirrhosis with high accuracy. Thus, crucial features and cut-off values for physicians in the detection of cirrhosis were determined. In addition, although AFP is not included in non-invasive indexes, it had a remarkable contribution in predicting cirrhosis.

Trial registration: Clinicaltrials.gov identifier: NCT03145844.

查看原文本刊更多论文

基于机器学习算法的慢性丙型肝炎肝硬化辅助诊断：一种新的无创方法。

目的：本研究旨在利用机器学习（ML）算法对慢性丙型肝炎（CHC）患者的常规实验室检测结果证明肝硬化的可检测性后，确定其重要特征和临界值。方法：这项回顾性多中心（37个转诊中心）研究纳入了1164例活检证实的CHC患者的土耳其丙型肝炎登记处的数据。使用三种不同的ML算法根据确定的特征对肝硬化的存在/不存在进行分类。结果：随机森林（Random Forest， RF）预测肝硬化的准确度最高（准确率0.89,AUC = 0.87）。血小板、α - α -胎蛋白（AFP）、年龄、γ -谷氨酰转移酶（GGT）和凝血酶原时间（PT）是影响分类的五个最重要的特征。这些特征的临界值分别为血小板3、AFP > 5.49 ng/mL、年龄> 52岁、GGT > 39.9 U/L、PT > 12.35 s。采用截断值，血小板AOR = 4.82, AFP AOR = 3.49，年龄AOR = 4.32, GGT AOR = 3.04, pt AOR = 2.20。结论：基于rf的ML算法对肝硬化有较高的分类准确率。因此，确定了医生在肝硬化检测中的关键特征和临界值。此外，AFP虽未被纳入无创指标，但在预测肝硬化方面有显著贡献。试验注册：Clinicaltrials.gov标识符：NCT03145844。

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

Journal of Clinical Laboratory Analysis 医学-医学实验技术

CiteScore

5.60

自引率

7.40%

发文量

584

审稿时长

6-12 weeks

期刊介绍： Journal of Clinical Laboratory Analysis publishes original articles on newly developing modes of technology and laboratory assays, with emphasis on their application in current and future clinical laboratory testing. This includes reports from the following fields: immunochemistry and toxicology, hematology and hematopathology, immunopathology, molecular diagnostics, microbiology, genetic testing, immunohematology, and clinical chemistry.