Recent frameworks such as OHDSI have advanced the development of computable phenotypes, which enable standardized shareable definitions using structured data. Unfortunately, these advances have not extended to definitions utilizing unstructured data such as provider notes, radiology reports, and other free text sources. Here we introduce NLPQL, a human readable, expert-friendly syntax for creating computable NLP-based phenotype definitions.

Describe the new knowledge and additional skills the participant will gain after attending your presentation.: Attendees will become familiar with NLPQL, and understand the need, basic syntax, and uses for NLPQL, and how it relates to the ClarityNLP, open-source clinical NLP library. In addition, we will provide a series of examples which combine structured and unstructured data.


Charity Hilton (Presenter)
Georgia Tech Research Institute

Jon Duke, Georgia Tech Research Institute
Richard Boyd, Georgia Tech Research Institute

Presentation Materials: