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.

We welcome contributions including but not limited to:
• Federated and distributed learning for healthcare
• Privacy-preserving machine learning
• Learning under data heterogeneity and imbalance
• Multicentric, multi-modal, and longitudinal data analysis
• Evaluation, benchmarking, and reproducibility
• Systems and infrastructures for collaborative AI
• Clinical applications and real-world deployments
• Trust, robustness, fairness, and explainability