The abstract is read at the publisher; the summary is JClub's.
Ontology-based integration of 9,147 vaccine trials into SEA-CDM linked to Vaccine Ontology and OAE enables semantic retrieval and improved adverse-event ranking, including recall@10 rising from 0.317 to 0.383.
- Why it matters: ClinicalTrials.gov data are fragmented and vaccine naming is inconsistent, limiting systematic cross-trial analysis and making it hard to retrieve semantically related trials or rank adverse events in context.
- What they did: The team mapped AACT vaccine records into SEA-CDM, linked vaccine products to VO and adverse events to OAE, then evaluated three uses: VO query expansion, context-aware AE ranking, and trial similarity/design recommendation.
- The result: VO-based expansion retrieved 41 RNA vaccine trials versus 16 with exact VO identifier matching; AE ranking improved recall@10 to 0.383, and embedding models reached Hits@10 of 0.950 (TransE) and 0.946 (CompGCN).
The findingWhy it mattersWhat they didThe result
AI summary of the abstract · may contain errors · not medical advice · read the paper.