Clinical data goes MEDS—let’s OWL make sense of it
Why it matters
Machine learning on health records often stalls because hospitals store events in many formats. That hurts reproducibility and sharing.
What’s new
- MEDS-OWL: a small, clear vocabulary (ontology) that gives common meanings to MEDS event data, so computers agree on who did what, when.
- meds2rdf: a Python tool that turns MEDS files into RDF graphs that follow the ontology.
The authors show it on a synthetic dataset of care pathways for ruptured brain aneurysms and check the results with SHACL rules.
Why you should care
- Make clinical datasets FAIR (findable, accessible, interoperable, reusable).
- Add provenance to every event.
- Enable graph-style analytics across studies and systems.
From scattered files to a shared, machine-readable map of patient care.
Paper: https://arxiv.org/abs/2601.04164v1
Paper: https://arxiv.org/abs/2601.04164v1
Register: https://www.AiFeta.com
#healthcare #machinelearning #SemanticWeb #RDF #OWL #FAIRdata #interoperability #ClinicalAI #datastandards
