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

• Published in: Clinical biochemistry 2024-12, Vol.135, p.110861, Article 110861
• Main Authors: Carnazzo, Valeria, Pignalosa, Stefano, Tagliaferro, Marzia, Gragnani, Laura, Linda Zignego, Anna, Racco, Cosimo, Biase, Luigi Di, Basile, Valerio, Ludovico Rapaccini, Gian, Santo, Riccardo Di, Niccolini, Benedetta, Marino, Mariapaola, Spirito, Marco De, Gigante, Guido, Ciasca, Gabriele, Basile, Umberto
• Format: Article
• Language: English
• Subjects: Biomarkers; Collagen-III N-peptide; Collagen-IV; ECM; Explainable AI; HCV; Liver fibrosis; Machine learning; XGBoost
• ISSN: 0009-9120; 1873-2933; 1873-2933
• DOI: 10.1016/j.clinbiochem.2024.110861

•This study highlights ECM biomarkers’ potential for non-invasive CLD staging.•The combination of PIIIP N-P, C-IV, and LN is the most promising biomarker panel.•Machine learning (XGBoost) outperformed traditional models in classification accuracy.•Explainable AI (SHAP) confirms PIIIP N-P, C-IV, and LN as key classification markers. 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. 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. Levels of LN, HA, C-IV, PIIIP N-P (p