Exploratory study of extracellular matrix biomarkers for non-invasive liver fibrosis staging: A machine learning approach with XGBoost and explainable AI
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.
Authors
- Umberto Basile (ORCID: https://orcid.org/0000-0002-8328-2570)
- Gabriele Ciasca (ORCID: https://orcid.org/0000-0002-3694-8229)
- Guido Gigante
- Anna Linda Zignego (ORCID: https://orcid.org/0000-0002-8552-4166)
- Luigi Di Biase
- Gian Ludovico Rapaccini (ORCID: https://orcid.org/0000-0002-3580-8929)
- Marzia Tagliaferro
- Stefano Pignalosa
- Marco De Spirito (ORCID: https://orcid.org/0000-0003-4260-5107)
- Cosimo Racco
- Benedetta Niccolini (ORCID: https://orcid.org/0000-0002-3233-1897)
- Valeria Carnazzo
- Riccardo Di Santo (ORCID: https://orcid.org/0000-0002-0400-4661)
- Mariapaola Marino (ORCID: https://orcid.org/0000-0001-9155-6378)
- Laura Gragnani (ORCID: https://orcid.org/0000-0001-6800-9149)
- Valerio Basile (ORCID: https://orcid.org/0000-0002-9716-070X)
Institutions
- Università Cattolica del Sacro Cuore (IT)
- University of Pisa (IT)
- Istituto Superiore di Sanità (IT)
- Agostino Gemelli University Polyclinic (IT)
- Ospedale Santa Maria Goretti (IT)
- University of Florence (IT)
Publication Details
- Journal
- Clinical Biochemistry
- Published
- 2024-12-13
- DOI
- https://doi.org/10.1016/j.clinbiochem.2024.110861
- Citations
- 7
- Primary Topic
- Liver Disease Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 2.71
Funders
- Fondazione Umberto Veronesi
- Università Cattolica del Sacro Cuore