A simple algorithm for identifying negated findings and diseases in discharge summaries.

@article{citeulike:239652, abstract = {Narrative reports in medical records contain a wealth of information that may augment structured data for managing patient information and predicting trends in diseases. Pertinent negatives are evident in text but are not usually indexed in structured databases. The objective of the study reported here was to test a simple algorithm for determining whether a finding or disease mentioned within narrative medical reports is present or absent. We developed a simple regular expression algorithm called NegEx that implements several phrases indicating negation, filters out sentences containing phrases that falsely appear to be negation phrases, and limits the scope of the negation phrases. We compared NegEx against a baseline algorithm that has a limited set of negation phrases and a simpler notion of scope. In a test of 1235 findings and diseases in 1000 sentences taken from discharge summaries indexed by physicians, NegEx had a specificity of 94.5\% (versus 85.3\% for the baseline), a positive predictive value of 84.5\% (versus 68.4\% for the baseline) while maintaining a reasonable sensitivity of 77.8\% (versus 88.3\% for the baseline). We conclude that with little implementation effort a simple regular expression algorithm for determining whether a finding or disease is absent can identify a large portion of the pertinent negatives from discharge summaries.}, address = {Center for Biomedical Informatics, 8084 Forbes Tower, University of Pittsburgh, Pittsburgh, PA 15213, USA. chapman@cbmi.upmc.edu}, author = {Chapman, W. W. and Bridewell, W. and Hanbury, P. and Cooper, G. F. and Buchanan, B. G. }, citeulike-article-id = {239652}, doi = {http://dx.doi.org/10.1006/jbin.2001.1029}, issn = {1532-0464}, journal = {J Biomed Inform}, keywords = {clinical, natural\_language\_processing, negation\_detection, negex, nlp}, month = {October}, number = {5}, pages = {301--310}, posted-at = {2007-11-15 12:08:20}, priority = {2}, title = {A simple algorithm for identifying negated findings and diseases in discharge summaries.}, url = {http://dx.doi.org/10.1006/jbin.2001.1029}, volume = {34}, year = {2001} }

TY - JOUR ID - citeulike:239652 L3 - citeulike-article-id:239652 TI - A simple algorithm for identifying negated findings and diseases in discharge summaries. JF - J Biomed Inform VL - 34 IS - 5 SP - 301 EP - 310 AD - Center for Biomedical Informatics, 8084 Forbes Tower, University of Pittsburgh, Pittsburgh, PA 15213, USA. chapman@cbmi.upmc.edu SN - 1532-0464 N2 - Narrative reports in medical records contain a wealth of information that may augment structured data for managing patient information and predicting trends in diseases. Pertinent negatives are evident in text but are not usually indexed in structured databases. The objective of the study reported here was to test a simple algorithm for determining whether a finding or disease mentioned within narrative medical reports is present or absent. We developed a simple regular expression algorithm called NegEx that implements several phrases indicating negation, filters out sentences containing phrases that falsely appear to be negation phrases, and limits the scope of the negation phrases. We compared NegEx against a baseline algorithm that has a limited set of negation phrases and a simpler notion of scope. In a test of 1235 findings and diseases in 1000 sentences taken from discharge summaries indexed by physicians, NegEx had a specificity of 94.5% (versus 85.3% for the baseline), a positive predictive value of 84.5% (versus 68.4% for the baseline) while maintaining a reasonable sensitivity of 77.8% (versus 88.3% for the baseline). We conclude that with little implementation effort a simple regular expression algorithm for determining whether a finding or disease is absent can identify a large portion of the pertinent negatives from discharge summaries. KW - clinical KW - natural_language_processing KW - negation_detection KW - negex KW - nlp AU - Chapman, WW AU - Bridewell, W AU - Hanbury, P AU - Cooper, GF AU - Buchanan, BG PY - 2001/10// UR - http://dx.doi.org/10.1006/jbin.2001.1029 ER -