RULE-BASED EXTRACTION OF SOCIAL DETERMINANTS OF HEALTH FROM ELECTRONIC HEALTH RECORDS OF PATIENTS WITH TYPE 2 DIABETES
PublisherThe University of Arizona.
RightsCopyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.
AbstractSocial determinants of health (SDOH) are an important, yet often overlooked part of a patient’s medical history. Successful identification of SDOH would lead to better information from which to make diagnoses. One source of such information is data from electronic health records (EHRs). In this paper, potential approaches to extract SDOH from unstructured text are explored and a rule-based parser is implemented. This parser was tested on a dataset containing 812 sentences and was found to have a precision of 0.774 and a recall of 0.774. Further analysis showed that the most common SDOH documented in the EHR were those relating to family.
Degree ProgramManagement Information Systems