Researchers Add Imaging To Cardio Knowledge Graph
Researchers at the MRC Laboratory of Medical Sciences led by Dr Khaled Rjoob and Professor Declan O'Regan report in 2025 that they added cardiac imaging to a multimodal knowledge graph, CardioKG, integrating >200,000 image-based traits from 9,584 UK Biobank participants with data from 18 biological databases. The AI model improved prediction of gene-disease associations and identified candidate repurposed drugs, including methotrexate and gliptins.
Key Points
- 1Integrated imaging and multi-source data into CardioKG using >200,000 image-based traits
- 2Improved prediction accuracy for gene-disease links and drug repurposing across cardiovascular conditions
- 3Enables practitioners to prioritize gene targets and candidate drugs for validation and clinical trials
Scoring Rationale
Strong novelty and real-world applicability across biomedical discovery, supported by peer-reviewed publication; broader clinical validation remains needed.
Sources
Public references used for this report.
Practice interview problems based on real data
1,625 SQL & Python problems across 15 industry datasets — the exact type of data you work with.
Try 250 free problems
