Reliance upon structured data elements and standard clinical terminologies remains a limitation to the development and implementation of clinical quality measures (CQMs) used in quality reporting and payment programs. This is particularly problematic in domains such as diagnosis which require data not typically involved in payment. The use of data extracted from unstructured fields such as clinical notes, pathology, radiology, and laboratory reports is a potential solution, but the natural language processing (NLP) technologies and tools used to extract the data are not widely adopted nor refined to the degree necessary for health care system-wide implementation.
This session will present the work of a community of practice supported by the Gordon and Betty Moore foundation to promote the use of NLP “at-scale” in CQM used in accountability programs.
Watch the Recording
Presenter