Researchers have developed a new framework called Bridge-MedDevKG to link FDA-approved cardiovascular devices with their corresponding patents. This task is challenging due to significant semantic differences between clinical outcome-focused FDA documents and technical patent descriptions. The proposed solution integrates a domain-specific ontology (MedDevOnto) with UMLS normalization, multi-signal candidate generation, and heterogeneous reranking using XGBoost to achieve high recall and noise reduction. The resulting MedDevKG provides millions of high-confidence links, enabling better integration of regulatory and intellectual property information for medical devices. AI
IMPACT This research could improve the integration of regulatory and intellectual property data for medical devices, potentially aiding in recalls and M&A activities.
RANK_REASON The item is a research paper detailing a new framework and benchmark for a specific domain. [lever_c_demoted from research: ic=1 ai=0.4]
- arXiv
- Bridge-MedDevKG
- MedDevKG
- MedDevOnto
- UMLS
- United States Food and Drug Administration
- United States Patent and Trademark Office
- XGBoost
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
