Exploratory study of extracellular matrix biomarkers for non-invasive liver fibrosis staging: A machine learning approach with XGBoost and explainable AI

IF 2.5 3区 医学 Q2 MEDICAL LABORATORY TECHNOLOGY Clinical biochemistry Pub Date : 2025-01-01 DOI:10.1016/j.clinbiochem.2024.110861
Valeria Carnazzo , Stefano Pignalosa , Marzia Tagliaferro , Laura Gragnani , Anna Linda Zignego , Cosimo Racco , Luigi Di Biase , Valerio Basile , Gian Ludovico Rapaccini , Riccardo Di Santo , Benedetta Niccolini , Mariapaola Marino , Marco De Spirito , Guido Gigante , Gabriele Ciasca , Umberto Basile
{"title":"Exploratory study of extracellular matrix biomarkers for non-invasive liver fibrosis staging: A machine learning approach with XGBoost and explainable AI","authors":"Valeria Carnazzo ,&nbsp;Stefano Pignalosa ,&nbsp;Marzia Tagliaferro ,&nbsp;Laura Gragnani ,&nbsp;Anna Linda Zignego ,&nbsp;Cosimo Racco ,&nbsp;Luigi Di Biase ,&nbsp;Valerio Basile ,&nbsp;Gian Ludovico Rapaccini ,&nbsp;Riccardo Di Santo ,&nbsp;Benedetta Niccolini ,&nbsp;Mariapaola Marino ,&nbsp;Marco De Spirito ,&nbsp;Guido Gigante ,&nbsp;Gabriele Ciasca ,&nbsp;Umberto Basile","doi":"10.1016/j.clinbiochem.2024.110861","DOIUrl":null,"url":null,"abstract":"<div><h3>Background</h3><div>Novel circulating markers for the non-invasive staging of chronic liver disease (CLD) are in high demand. Although underutilized, extracellular matrix (ECM) components offer significant diagnostic potential. This study evaluates ECM-related markers in hepatitis C virus (HCV)-positive patients across varying fibrosis stages.</div></div><div><h3>Methods</h3><div>Sixty-eight patients with mild-to-moderate fibrosis (F1-F2), sixty-six with advanced fibrosis (F3-F4), and thirty healthy donors were recruited. Inclusion criteria were detectable HCV-RNA and no other liver diseases or co-infections. Levels of ECM markers—hyaluronic acid (HA), laminin (LN), collagen-III N-peptide (PIIIP N-P), collagen-IV (C-IV)—along with cholylglycine (CG) and Golgi protein-73 (GP73), were measured in serum using the MAGLUMI 800 CLIA platform.</div></div><div><h3>Results</h3><div>Levels of LN, HA, C-IV, PIIIP N-P (p &lt; 0.001), and GP73 (p &lt; 0.01) increased from controls to F1-F2 and F3-F4. CG levels were higher in pathological subjects compared to controls (p &lt; 0.001), but no significant differences emerged between fibrosis stages. These trends persisted after adjusting for age and sex. A multivariate ordinal regression identified LN, PIIIP N-P, and C-IV as promising markers, with an accuracy of 0.77. An XGBoost model improved accuracy to 0.87 and enhanced other metrics. SHAP analysis confirmed these variables as key contributors to the model’s predictions.</div></div><div><h3>Conclusion</h3><div>This study underscores the potential of ECM biomarkers, particularly LN, PIIIP N-P, and C-IV, in non-invasively staging CLD. Furthermore, our preliminary data suggest that a machine learning approach, combined with explainable AI, could further enhance diagnostic accuracy, potentially reducing the need for invasive biopsies.</div></div>","PeriodicalId":10172,"journal":{"name":"Clinical biochemistry","volume":"135 ","pages":"Article 110861"},"PeriodicalIF":2.5000,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Clinical biochemistry","FirstCategoryId":"3","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0009912024001553","RegionNum":3,"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

Background

Novel circulating markers for the non-invasive staging of chronic liver disease (CLD) are in high demand. Although underutilized, extracellular matrix (ECM) components offer significant diagnostic potential. This study evaluates ECM-related markers in hepatitis C virus (HCV)-positive patients across varying fibrosis stages.

Methods

Sixty-eight patients with mild-to-moderate fibrosis (F1-F2), sixty-six with advanced fibrosis (F3-F4), and thirty healthy donors were recruited. Inclusion criteria were detectable HCV-RNA and no other liver diseases or co-infections. Levels of ECM markers—hyaluronic acid (HA), laminin (LN), collagen-III N-peptide (PIIIP N-P), collagen-IV (C-IV)—along with cholylglycine (CG) and Golgi protein-73 (GP73), were measured in serum using the MAGLUMI 800 CLIA platform.

Results

Levels of LN, HA, C-IV, PIIIP N-P (p < 0.001), and GP73 (p < 0.01) increased from controls to F1-F2 and F3-F4. CG levels were higher in pathological subjects compared to controls (p < 0.001), but no significant differences emerged between fibrosis stages. These trends persisted after adjusting for age and sex. A multivariate ordinal regression identified LN, PIIIP N-P, and C-IV as promising markers, with an accuracy of 0.77. An XGBoost model improved accuracy to 0.87 and enhanced other metrics. SHAP analysis confirmed these variables as key contributors to the model’s predictions.

Conclusion

This study underscores the potential of ECM biomarkers, particularly LN, PIIIP N-P, and C-IV, in non-invasively staging CLD. Furthermore, our preliminary data suggest that a machine learning approach, combined with explainable AI, could further enhance diagnostic accuracy, potentially reducing the need for invasive biopsies.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
用于无创肝纤维化分期的细胞外基质生物标志物的探索性研究:采用XGBoost和可解释人工智能的机器学习方法。
背景:用于慢性肝病(CLD)无创分期的新型循环标记物需求量很大。细胞外基质(ECM)成分虽然未得到充分利用,但却具有巨大的诊断潜力。本研究评估了丙型肝炎病毒(HCV)阳性患者不同纤维化阶段的 ECM 相关标记物:招募了 68 名轻度至中度纤维化患者(F1-F2)、66 名晚期纤维化患者(F3-F4)和 30 名健康供体。纳入标准为可检测到 HCV-RNA,且无其他肝病或合并感染。使用 MAGLUMI 800 CLIA 平台测量了血清中 ECM 标记物--透明质酸 (HA)、层粘连蛋白 (LN)、胶原蛋白-III N-肽 (PIIIP N-P)、胶原蛋白-IV (C-IV)--以及胆酰甘氨酸 (CG) 和高尔基体蛋白-73 (GP73) 的水平:结果:LN、HA、C-IV、PIIIP N-P(p)的水平均有所下降:本研究强调了 ECM 生物标志物,尤其是 LN、PIIIP N-P 和 C-IV 在对 CLD 进行无创分期方面的潜力。此外,我们的初步数据表明,机器学习方法与可解释的人工智能相结合,可进一步提高诊断准确性,从而减少有创活检的需要。
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 去求助
来源期刊
Clinical biochemistry
Clinical biochemistry 医学-医学实验技术
CiteScore
5.10
自引率
0.00%
发文量
151
审稿时长
25 days
期刊介绍: Clinical Biochemistry publishes articles relating to clinical chemistry, molecular biology and genetics, therapeutic drug monitoring and toxicology, laboratory immunology and laboratory medicine in general, with the focus on analytical and clinical investigation of laboratory tests in humans used for diagnosis, prognosis, treatment and therapy, and monitoring of disease.
期刊最新文献
Assessment of accuracy, clinical validity, and analytical linearity in point-of-care glucose monitoring devices for diabetes mellitus: A systematic review and meta-analysis Rising illicit drug Adulterants: Xylazine and levamisole. Phosphatidylethanol clearance after packed red blood cell transfusion Editorial Board Cardiac troponin I is associated with ICU admission in pediatric patients with RSV
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1