Unbabel

Unbabel

Annotating biomedical terms in electronic health records using crowd-sourcing

This collaboration is developing a crowd-sourcing method to improve the precision of extraction and normalization of biomedical terms. Although crowd-sourcing has been applied in other fields, it has not been applied yet to the annotation of health records. We expect this method to improve the precision of supervised machine learning classifiers, by letting the users fix the boundaries of the terms, as well as the respective ontology concept. We intend to apply this method to the recognition and normalization of disorder, drug, gene and protein names, in electronic health records.

Principal Investigator: