EUVIMEDEUVIMED entdecken
ÜbersichtsarbeitOpen Access · CC BY 4.0

Federated learning in inflammatory bowel disease: The future of privacy-preserving Artificial Intelligence

Pierluigi Puca, Loris Riccardo Lopetuso, Lucrezia Laterza, Alfredo Papa, Silvio Danese, Alfredo Cesario, Andrea Damiani, Antonio Gasbarrini, Giovanni Arcuri, Franco Scaldaferri

Best Practice & Research Clinical Gastroenterology · 2025-09 · 78 · 102050

DOI: 10.1016/j.bpg.2025.102050 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Best Practice & Research Clinical Gastroenterology, 2025-09. Verfasst von Pierluigi Puca und 9 weiteren Autor:innen. Beteiligte Einrichtung: IBD Unit, CEMAD, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy; Dipartimento di Medicina e Chirurgia Traslazionale, Univer…. Hauptthemen laut MEDLINE: Inflammatory Bowel Diseases, Artificial Intelligence, Privacy, Confidentiality. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 80 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning is an emerging paradigm in artificial intelligence that enables the training of robust models across decentralized datasets without requiring the physical transfer of sensitive data. This privacy-preserving approach has gained increasing traction in medical research, where data fragmentation and legal barriers often hinder the development of multicentric trials and AI applications. In this review, we first provide an explanation of federated learning's process and functioning. We then provide a structured overview of its implementation in clinical research, highlighting key multicentric studies in several fields of medicine. These studies consistently demonstrate that FL achieves comparable, and in some cases superior, diagnostic and prognostic performance in comparison to centralized learning approaches, with area under the curve values often exceeding 0.80. We then consider the potential of federated learning in the context of inflammatory bowel diseases, where data heterogeneity, geographic dispersion, and patient privacy concerns currently limit the development of large-scale predictive models. In doing so, we will provide specific focus on its application in multicentric trials and basic research. Finally, aspects like semantic interoperability in federated learning and privacy issues will also be discussed. We believe that federated learning could transform the way inflammatory bowel diseases datasets are utilized across institutions, facilitating collaborative algorithm development in areas such as treatment response prediction, endoscopic image analysis, and disease phenotyping-without compromising patient confidentiality.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Inflammatory Bowel DiseasesArtificial IntelligencePrivacyConfidentialityHumansFederated Learning

Stichwörter der Autor:innen

Artificial intelligenceFederated learningInflammatory bowel disease

Autor:innen und Institutionen

  • IBD Unit, CEMAD, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy; Dipartimento di Medicina e Chirurgia Traslazionale, Università Cattolica del Sacro Cuore, Rome, Italy. Electronic address: pierl…
  • IBD Unit, CEMAD, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy; Department of Life Science, Health, and Health Professions, Link Campus University, Rome, Italy.
  • IBD Unit, CEMAD, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
  • IBD Unit, CEMAD, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy; Dipartimento di Medicina e Chirurgia Traslazionale, Università Cattolica del Sacro Cuore, Rome, Italy.
  • Department of Gastroenterology and Digestive Endoscopy, IRCCS San Raffaele Hospital and Vita-Salute San Raffaele University, Milan, Italy.
  • Real World Data Facility, Gemelli Generator, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.

Zitieren

APA

Puca, P., Lopetuso, L. R., Laterza, L., Papa, A., Danese, S., Cesario, A., Damiani, A., Gasbarrini, A., Arcuri, G., & Scaldaferri, F. (2025). Federated learning in inflammatory bowel disease: The future of privacy-preserving Artificial Intelligence. Best Practice & Research Clinical Gastroenterology, 78, 102050. https://doi.org/10.1016/j.bpg.2025.102050

Vancouver

Puca P, Lopetuso LR, Laterza L, Papa A, Danese S, Cesario A, et al. Federated learning in inflammatory bowel disease: The future of privacy-preserving Artificial Intelligence. Best Practice & Research Clinical Gastroenterology. 2025;78:102050. doi:10.1016/j.bpg.2025.102050

BibTeX
@article{Puca2025,
  author = {Puca, Pierluigi and Lopetuso, Loris Riccardo and Laterza, Lucrezia and Papa, Alfredo and Danese, Silvio and Cesario, Alfredo and Damiani, Andrea and Gasbarrini, Antonio and Arcuri, Giovanni and Scaldaferri, Franco},
  title = {Federated learning in inflammatory bowel disease: The future of privacy-preserving Artificial Intelligence},
  journal = {Best Practice & Research Clinical Gastroenterology},
  year = {2025},
  volume = {78},
  pages = {102050},
  doi = {10.1016/j.bpg.2025.102050}
}
Kostenlos starten →