Copyright
©The Author(s) 2025. Published by Baishideng Publishing Group Inc. All rights reserved.
Extracellular vesicles as biomarkers for metabolic dysfunction-associated steatotic liver disease staging using explainable artificial intelligence
Eleni Myrto Trifylli, Athanasios Angelakis, Anastasios G Kriebardis, Nikolaos Papadopoulos, Sotirios P Fortis, Vasiliki Pantazatou, John Koskinas, Hariklia Kranidioti, Evangelos Koustas, Panagiotis Sarantis, Spilios Manolakopoulos, Melanie Deutsch
Eleni Myrto Trifylli, John Koskinas, Hariklia Kranidioti, Spilios Manolakopoulos, Melanie Deutsch, Gastrointestinal-Liver Unit, The 2nd Department of Internal Medicine, National and Kapodistrian University of Athens, General Hospital of Athens “Hippocratio,” Athens 11521, Greece
Eleni Myrto Trifylli, Anastasios G Kriebardis, Sotirios P Fortis, Vasiliki Pantazatou, Laboratory of Reliability and Quality Control in Laboratory Hematology, Department of Biomedical Sciences, Section of Medical Laboratories, School of Health & Caring Sciences, University of West Attica, Egaleo 12243, Attikí, Greece
Athanasios Angelakis, Department of Epidemiology and Data Science, Amsterdam University Medical Center, Amsterdam 1105, Netherlands
Athanasios Angelakis, Department of Methodology, Digital Health, Amsterdam Public Health Research Institute, Amsterdam 1105, Netherlands
Athanasios Angelakis, Data Science Center, University of Amsterdam, Amsterdam 1098, Netherlands
Nikolaos Papadopoulos, The Second Department of Internal Medicine, 401 General Army Hospital of Athens, Athens 11525, Greece
Evangelos Koustas, Department of Oncology, General Hospital Evangelismos, Athens 10676, Greece
Panagiotis Sarantis, Department of Biological Chemistry, Medical School, National and Kapodistrian University of Athens, Athens 11527, Greece
Co-first authors: Eleni Myrto Trifylli and Athanasios Angelakis.
Author contributions: Trifylli EM and Angelakis A are co-first authors and both contributed to the conception of the study; Trifylli EM, Angelakis A, Kriebardis AG, Papadopoulos N, Fortis SP, Manolakopoulos S, and Deutsch M contributed to the design of the study; Trifylli EM contributed to data acquisition and interpretation and drafting, reviewing, and editing the manuscript; Angelakis A contributed to data processing, analysis, and interpretation and drafting, reviewing, editing, and supervising the manuscript; Kriebardis AG contributed to the supervision, data acquisition, sample processing, analysis, and reviewing and editing the manuscript; Papadopoulos N contributed to the data acquisition, transient elastography operation, data interpretation, and reviewing and editing the manuscript; Fortis SP contributed to sample processing and analysis, data acquisition, data interpretation, and manuscript review; Pantazatou V contributed to sample processing; Koskinas J and Kranidioti H contributed to data acquisition and review of the manuscript; Koustas E and Sarantis P contributed to the review of the manuscript; Angelakis A, Kriebardis AG, Papadopoulos N, Manolakopoulos S, and Deutsch M critically revised the manuscript for important intellectual content; All authors approved the final version of the manuscript to be published and ensured that questions related to the accuracy or integrity of the work were appropriately investigated.
Institutional review board statement: This study was reviewed and approved by the Ethics Committee of the General Hospital of Athens “Hippocratio” in 1st Health Authority of Greece, Attica (No. 24, dated 15 November 2022).
Informed consent statement: Informed consent was obtained from all subjects involved in the study.
Conflict-of-interest statement: All the authors report no relevant conflicts of interest for this article.
STROBE statement: The authors have read the STROBE Statement—checklist of items, and the manuscript was prepared and revised according to the STROBE Statement—checklist of items.
Data sharing statement: Our methodological pipeline is transparently documented for reproducibility; however, the dataset is not publicly accessible due to ethical and privacy restrictions but is available upon reasonable request following institutional approval. The datasets generated and/or analyzed during the current study are available from the corresponding author upon reasonable request at
nipapmed@gmail.com.
Open Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See:
https://creativecommons.org/Licenses/by-nc/4.0/ Corresponding author: Nikolaos Papadopoulos, MD, PhD, Chief, Director, The Second Department of Internal Medicine, 401 General Army Hospital of Athens, 138 Mesogeion Ave, Athens 11525, Greece.
nipapmed@gmail.com
Received: March 11, 2025
Revised: April 18, 2025
Accepted: May 22, 2025
Published online: June 14, 2025
Processing time: 93 Days and 10.9 Hours
BACKGROUND
Metabolic dysfunction-associated steatotic liver disease (MASLD) is a leading cause of chronic liver disease globally. Current diagnostic methods, such as liver biopsies, are invasive and have limitations, highlighting the need for non-invasive alternatives.
AIM
To investigate extracellular vesicles (EVs) as potential biomarkers for diagnosing and staging steatosis in patients with MASLD using machine learning (ML) and explainable artificial intelligence (XAI).
METHODS
In this single-center observational study, 798 patients with metabolic dysfunction were enrolled. Of these, 194 met the eligibility criteria, and 76 successfully completed all study procedures. Transient elastography was used for steatosis and fibrosis staging, and circulating plasma EV characteristics were analyzed through nanoparticle tracking. Twenty ML models were developed: Six to differentiate non-steatosis (S0) from steatosis (S1-S3); and fourteen to identify severe steatosis (S3). Models utilized EV features (size and concentration), clinical (advanced fibrosis and presence of type 2 diabetes mellitus), and anthropomorphic (sex, age, height, weight, body mass index) data. Their performance was assessed using receiver operating characteristic (ROC)-area under the curve (AUC), specificity, and sensitivity, while correlation and XAI analysis were also conducted.
RESULTS
The CatBoost C1a model achieved an ROC-AUC of 0.71/0.86 (train/test) on average across ten random five-fold cross-validations, using EV features alone to distinguish S0 from S1-S3. The CatBoost C2h-21 model achieved an ROC-AUC of 0.81/1.00 (train/test) on average across ten random three-fold cross-validations, using engineered features including EVs, clinical features like diabetes and advanced fibrosis, and anthropomorphic data like body mass index and weight for identifying severe steatosis (S3). Key predictors included EV mean size and concentration. Correlation, XAI, and SHapley Additive exPlanations analysis revealed non-linear feature relationships with steatosis stages.
CONCLUSION
The EV-based ML models demonstrated that the mean size and concentration of circulating plasma EVs constituted key predictors for distinguishing the absence of significant steatosis (S0) in patients with metabolic dysfunction, while the combination of EV, clinical, and anthropomorphic features improved the diagnostic accuracy for the identification of severe steatosis. The algorithmic approach using ML and XAI captured non-linear patterns between disease features and provided interpretable MASLD staging insights. However, further large multicenter studies, comparisons, and validation with histopathology and advanced imaging methods are needed.
Core Tip: This study evaluated circulating plasma extracellular vesicles (EVs) as metabolic dysfunction-associated steatotic liver disease biomarkers for steatosis identification and staging using machine learning and explainable artificial intelligence. EV-based machine learning models demonstrated that mean size and concentration of EVs are key predictors that effectively distinguish the absence of significant steatosis in patients with metabolic dysfunction and the presence of severe steatosis (S3) when they are combined with clinical and anthropomorphic data. Further, large multicenter studies, comparison with advanced imaging methods, and histopathology validation are required to confirm the clinical utility of EVs.
