A challenge to uncover how entity linking models can improve healthcare delivery
The SNOMED CT Entity Linking Challenge posed an opportunity to advance the development of efficient and reliable tools for automating the coding of patient data, facilitating interoperability, decision support, and improving healthcare delivery.
Much of the world’s healthcare data is stored in free-text documents, usually clinical notes taken by clinicians. Extracting useful information from these notes would unlock incredible opportunities for analytics and research, in turn stimulating the development of new medicines, treatment pathways, and better patient outcomes.
Challenge Partners
Sponsored by:
_edited.jpg){kind=logo}
Collaborator
Clinical notes provider
Hosted by
The objective?
The objective of this competition was to train machine learning models to link clinical notes with specific topics. Participants were challenged to train models based on real-world doctor’s notes, which have been deidentified and annotated with SNOMED CT concepts by medically trained professionals. This is the largest publicly available dataset of labeled clinical notes, and you can be one of the first to use it!
The algorithms that perform best on additional real-world data have been publicly recognized on the challenge leaderboard, and awarded a share of $25,000 in cash prizes.
