aiqbench analysis
This research addresses the critical challenge of domain generalization in clinical settings by leveraging medical ontologies to discover hierarchy-grounded patient domains without relying on explicit labels. The proposed UdonCare method demonstrates superior performance over existing baselines on major public datasets, effectively bridging distribution gaps between different patient groups using structured medical knowledge. By integrating domain-specific insights into the model training process, this approach offers a robust pathway for deploying predictive AI systems across diverse healthcare environments.
Discovering Hierarchy-Grounded Domains with Adaptive Granularity for Clinical Domain Generalization
arXiv:2506.06977v4 Announce Type: replace-cross Abstract: Domain generalization has become a critical challenge in predictive healthcare, where different patient groups exhibit shifting data distributions that degrade model performance. Still, regular domain generalization approaches often struggle in clinical settings due to (1) the absence of domain labels and (2) the lack of clinical insight integration. To address these challenges in healthcare, we aim to explore how medical ontologies can be used to discover dynamic yet hierarchy-grounded patient domains, a partitioning strategy that remains under-explored in prior work. Hence, we introduce UdonCare, a hierarchy-pruning method that iteratively divides patients into latent domains and retrieves domain-invariant (label) information from patient data. On public datasets (MIMIC-III, MIMIC-IV, and eICU), UdonCare shows superiority over eight generalization baselines across four representative clinical prediction tasks with substantial domain gaps, highlighting the potential of medical knowledge for enhancing model generalization.
Abstract:Domain generalization has become a critical challenge in predictive healthcare, where different patient groups exhibit shifting data distributions that degrade model performance. Still, regular domain generalization approaches often struggle in clinical settings due to (1) the absence of domain labels and (2) the lack of clinical insight integration. To address these challenges in healthcare, we aim to explore how medical ontologies can be used to discover dynamic yet hierarchy-grounded patient domains, a partitioning strategy that remains under-explored in prior work. Hence, we introduce UdonCare, a hierarchy-pruning method that iteratively divides patients into latent domains and retrieves domain-invariant (label) information from patient data. On public datasets (MIMIC-III, MIMIC-IV, and eICU), UdonCare shows superiority over eight generalization baselines across four representative clinical prediction tasks with substantial domain gaps, highlighting the potential of medical knowledge for enhancing model generalization.
Machine Learning (cs.LG); Artificial Intelligence (cs.AI)
arXiv:2506.06977 [cs.LG]
(or arXiv:2506.06977v4 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2506.06977 Focus to learn more arXiv-issued DOI via DataCite
https://doi.org/10.1145/3799682.3840625 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 241 words
Related coverage
News
Quantum Computing Report · Jul 25, 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026
How to build a cancer vaccine, and whether they will work this time
LessWrong · Jun 8, 2026
MedPlex: Deep Vision-Language Co-Adaptation for Clinically Grounded Medical Segmentation
arXiv · Aug 17, 2026