As healthcare data becomes increasingly distributed across institutions, unlocking its full potential for AI-driven medicine remains a major challenge. Strict privacy regulations, data governance constraints, and institutional boundaries often prevent data sharing, limiting the development of robust and generalizable models. Federated Learning and related privacy-preserving approaches offer a promising solution by enabling collaborative learning without exchanging sensitive patient data.

MULTIPLi Health aims to bring together researchers and practitioners working on multicentric and privacy-aware AI in healthcare. We invite submissions on methods, systems, and real-world applications that address the challenges of learning from heterogeneous, distributed data, with a focus on privacy, robustness, trustworthiness, and clinical impact.

Submission Guidelines

We accept submissions of the following formats:

• Full papers: up to 10 pages
• Short papers: 4-6 pages

Submitted papers should be formatted according to Springer's LNCS Format.

Submissions are processed via EasyChair.
All submissions will be peer-reviewed by at least two members of the Program Committee.

Organizing Committee

• Christoph Düsing, Bielefeld University
• Bruno Casella, University of Torino
• Mirko Polato, University of Torino
• Ioanna Miliou, Stockholm University
• Björn Eskofier, LMU Munich

Contact

Further details and contact information is provided on the workshop website: https://multipli26.di.unito.it/