Dr. Alex Turchin’s joined us on Monday, May 10, 2021 to share and demo his Canary: A free natural language processing platform for clinicians and researchers.
Natural Language Processing (NLP) technology can make it possible to discover and analyze critical knowledge buried in unstructured clinical data. Nevertheless, widespread adoption of NLP has yet to materialize; the technical skills required for the development or use of such software can present a major barrier for medical researchers. In particular, no free NLP software geared towards biomedical researchers with limited computer science backgrounds has been made available. To address this issue we have developed CANARY, a free and open-source solution designed for users without NLP, software development, or engineering experience. The software allows users to build NLP tools, ranging from simple to complex, using a graphic user interface. Canary comes with an extensive user manual and a number of starter NLP examples as well as a Library containing production-grade NLP tools developed by Canary users. Canary can be used to analyze a wide range of narrative electronic documents, including progress notes, discharge summaries, radiology reports, etc. It supports both RPDR and EDW narrative data formats.