Artificial Intelligence for Fibrosis Diagnosis in Metabolic-Dysfunction-Associated Steatotic Liver Disease: A Systematic Review
Künstliche Intelligenz zur Fibrose-Diagnose bei Metabolic-Dysfunction-Associated Steatotic Liver Disease: systematische Übersicht
Diagnostics · 14.01.2026 · 16 (2) · 261
DOI: 10.3390/diagnostics16020261 ↗Auf einen Blick
21 Studien zeigen: KI-Modelle schnitten bei der nichtinvasiven Diagnose von Leberfibrose bei MASLD besser ab als konventionelle Scores. Die Aussagekraft ist durch fehlende externe Validierung begrenzt.
Fragestellung
Wie gut diagnostizieren KI-Modelle eine Leberfibrose bei Erwachsenen mit MASLD im Vergleich zu konventionellen Verfahren?
Methode
Systematische Übersicht; Suche in PubMed, Scopus, Web of Science, ScienceDirect, Embase, LILACS, IEEE Series und ACM; Bewertung mit QUADAS-2 und MINIMAR.
Ergebnisse
21 Studien mit 19.221 Patient:innen und 5237 Bildern. KI-Modelle übertrafen durchgehend FIB-4 und NFS. Geringes Verzerrungsrisiko insgesamt, aber geringe methodische Transparenz und externe Validierung.
Einschränkungen
Externe Validierung war begrenzt; hohe Heterogenität zwischen den Studien.
Schlussfolgerung der Autor:innen
KI ist für die nichtinvasive Diagnose von Leberfibrose bei MASLD machbar und zeigte eine höhere Genauigkeit als Standard-Scores. Für die Routine ist weitere prospektive Validierung nötig.
Kernaussagen
- 21 Studien mit 19.221 Patient:innen und 5237 Bildern
- KI besser als FIB-4 und NFS
- Externe Validierung und Transparenz begrenzt
Deutsche Zusammenfassung: KI-gestützt aus dem Original-Abstract erstellt; alle Zahlen wurden automatisch mit dem Original abgeglichen. Maßgeblich ist der Original-Abstract.
Kurz gefasst
Übersichtsarbeit in der Zeitschrift Diagnostics, online erschienen am 14.01.2026. Verfasst von Neilson Silveira de Souza und 4 weiteren Autor:innen. Beteiligte Einrichtung: Faculty of Medicine of Bahia, Federal University of Bahia, Salvador 40026-010, Bahia, Brazil. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Council for Scientific and Technological Development, Improvement of Higher Education Personnel—Brazil.
Abstract (Originalsprache)
Background/Objectives: Artificial intelligence (AI) is an emerging technology for diagnosing liver fibrosis in Metabolic-Dysfunction-Associated Steatotic Liver Disease (MASLD), but a comprehensive synthesis of its performance is lacking. This systematic review (SR) aimed to evaluate the current evidence of AI models for diagnosing or staging liver fibrosis in patients with MASLD compared to conventional diagnostic tools.
Methods
A comprehensive search was conducted in PubMed, Scopus, Web of Science, ScienceDirect, Embase, LILACS, IEEE Series, and Association for Computing Machinery (ACM). Primary studies applying AI to diagnose fibrosis in adults with MASLD were included. Risk of bias was assessed using the QUADAS-2 tool, and methodological reporting was evaluated according to the MINimum Information for Medical AI Reporting (MINIMAR) guideline. A narrative synthesis was performed, grouping studies by data type (clinical/laboratory vs. imaging) and summarizing diagnostic performance and clinical application. A frequency-based analysis was applied to identify the most recurrent predictive features, and an analysis of the AI architecture and application was reported. The review was registered in PROSPERO (CRD420251035919).
Results
Twenty-one studies were included, encompassing 19,221 patients and 5237 images. Across studies, AI models consistently outperformed non-invasive scores such as Fibrosis-4 Index (FIB-4) and NAFLD Fibrosis Score (NFS). The most frequent predictive variables were identified. Despite an overall low risk of bias, methodological transparency and external validation were limited.
Conclusions
AI is feasible for the non-invasive diagnosis of liver fibrosis in MASLD, demonstrating superior accuracy to standard clinical scores. Broader clinical application is limited by the lack of external validation and high heterogeneity among the studies. Prospective validation in diverse, multicenter cohorts is essential before AI can be integrated into routine clinical practice.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Faculty of Medicine of Bahia, Federal University of Bahia, Salvador 40026-010, Bahia, Brazil.
- Postgraduate Program in Medicine and Health, Faculty of Medicine of Bahia, Federal University of Bahia, Salvador 40110-060, Bahia, Brazil.
- Radtec Serviços de Física Médica LTDA, Salvador 40295-010, Bahia, Brazil.
- Department of Radiology, Professor Edgard Santos University Hospital, Federal University of Bahia, Salvador 40110-060, Bahia, Brazil.
ORCID-Profile: Neilson Silveira de Souza, Théo Cordeiro Veiga Vitório, Raphael Augusto de Souza, Marcos Antônio Dórea Machado, Helma Pinchemel Cotrim
Förderung
- National Council for Scientific and Technological Development
- Improvement of Higher Education Personnel—Brazil
Zitieren
APA
Souza, N. S., Vitório, T. C. V., Souza, R. A., Machado, M. A. D., & Cotrim, H. P. (2026). Artificial Intelligence for Fibrosis Diagnosis in Metabolic-Dysfunction-Associated Steatotic Liver Disease: A Systematic Review. Diagnostics, 16(2), 261. https://doi.org/10.3390/diagnostics16020261
Vancouver
Souza NS, Vitório TCV, Souza RA, Machado MAD, Cotrim HP. Artificial Intelligence for Fibrosis Diagnosis in Metabolic-Dysfunction-Associated Steatotic Liver Disease: A Systematic Review. Diagnostics. 2026;16(2):261. doi:10.3390/diagnostics16020261
BibTeX
@article{Souza2026,
author = {Souza, Neilson Silveira de and Vitório, Théo Cordeiro Veiga and Souza, Raphael Augusto de and Machado, Marcos Antônio Dórea and Cotrim, Helma Pinchemel},
title = {Artificial Intelligence for Fibrosis Diagnosis in Metabolic-Dysfunction-Associated Steatotic Liver Disease: A Systematic Review},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {2},
pages = {261},
doi = {10.3390/diagnostics16020261}
}
EUVIMED