Abstract
Background Electronic medical records (EMRs) are revolutionizing health-related research. One key issue for study quality is the accurate identification of patients with the condition of interest. Information in EMRs can be entered as structured codes or unstructured free text. The majority of research studies have used only coded parts of EMRs for case-detection, which may bias findings, miss cases, and reduce study quality. This review examines whether incorporating information from text into case-detection algorithms can improve research quality. Methods A systematic search returned 9659 papers, 67 of which reported on the extraction of information from free text of EMRs with the stated purpose of detecting cases of a named clinical condition. Methods for extracting information from text and the technical accuracy of case-detection algorithms were reviewed. Results Studies mainly used US hospital-based EMRs, and extracted information from text for 41 conditions using keyword searches, rule-based algorithms, and machine learning methods. There was no clear difference in case-detection algorithm accuracy between rule-based and machine learning methods of extraction. Inclusion of information from text resulted in a significant improvement in algorithm sensitivity and area under the receiver operating characteristic in comparison to codes alone (median sensitivity 78% (codes + text) vs 62% (codes), P = .03; median area under the receiver operating characteristic 95% (codes + text) vs 88% (codes), P = .025). Conclusions Text in EMRs is accessible, especially with open source information extraction algorithms, and significantly improves case detection when combined with codes. More harmonization of reporting within EMR studies is needed, particularly standardized reporting of algorithm accuracy metrics like positive predictive value (precision) and sensitivity (recall).
Highlights
Information recorded in electronic medical records (EMRs), clinical reports, and summaries has the possibility of revolutionizing healthrelated research
Information recording in Electronic medical records (EMRs) In most EMRs there is the possibility for the clinician both to code their findings in a structured format and to enter information in narrative free text
Systematic search Searches were conducted between July 2014 and July 2015 on PubMed and Web of Science (WoS), using search terms derived from Medical Subject Headings vocabulary (US National Library of Medicine): 1) “electronic health records” or “electronic medical records” or “electronic patient records” or “hospital records” or “personal health records” or “computerized patient records” or “computerized medical records” or “automated medical records” combined with 2) “free text” or “narrative” or “text mining” or “natural language processing.”
Summary
Information recorded in electronic medical records (EMRs), clinical reports, and summaries has the possibility of revolutionizing healthrelated research. Information recording in EMRs In most EMRs there is the possibility for the clinician both to code their findings in a structured format and to enter information in narrative free text. There are various nomenclatures for structuring or coding information; the most widely used are International Classification of Diseases version 10,1 Systematized Nomenclature of Medicine – Clinical Terms,[2] and the International Classification of Primary Care.[3] Within multi-modal EMRs there are laboratory, pathology, and radiology reports, admission and discharge summaries, and chief complaints fields, which are in unstructured or semi-structured text. This review examines whether incorporating information from text into case-detection algorithms can improve research quality. Methods A systematic search returned 9659 papers, 67 of which reported on the extraction of information from free text of EMRs with the stated purpose of detecting cases of a named clinical condition. Methods for extracting information from text and the technical accuracy of case-detection algorithms were reviewed
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
