Automated knowledge extraction from MEDLINE citations

@article{11079949:HAP, abstract = {As part of preliminary studies for the development of a digital library, we have studied the possibility of using the co-occurrence of MeSH terms in MEDLINE citations associated with the search strategies optimal for evidence-based medicine to automate construction of a knowledge base. We use the UMLS semantic types in order to analyze search results to determine which semantic types are most relevant for different types of questions (etiology, diagnosis, therapy, and prognosis). The automated process generated a large amount of information. Seven to eight percent of the semantic pairs generated in each clinical task group co-occur significantly more often than can be accounted for by chance. A pilot study showed good specificity and sensitivity for the intended purposes of this project in all groups.}, author = {Mendonca, E. A. and Cimino, J. J. }, citeulike-article-id = {518684}, journal = {Proc AMIA Symp}, keywords = {all, ir, mesh, nlp}, pages = {575--9}, posted-at = {2006-02-23 18:37:42}, priority = {3}, title = {Automated knowledge extraction from MEDLINE citations}, year = {2000} }

TY - JOUR ID - 11079949:HAP L3 - citeulike-article-id:518684 TI - Automated knowledge extraction from MEDLINE citations JF - Proc AMIA Symp SP - 575 EP - 9 N2 - As part of preliminary studies for the development of a digital library, we have studied the possibility of using the co-occurrence of MeSH terms in MEDLINE citations associated with the search strategies optimal for evidence-based medicine to automate construction of a knowledge base. We use the UMLS semantic types in order to analyze search results to determine which semantic types are most relevant for different types of questions (etiology, diagnosis, therapy, and prognosis). The automated process generated a large amount of information. Seven to eight percent of the semantic pairs generated in each clinical task group co-occur significantly more often than can be accounted for by chance. A pilot study showed good specificity and sensitivity for the intended purposes of this project in all groups. KW - all KW - ir KW - mesh KW - nlp AU - Mendonca, EA AU - Cimino, JJ PY - 2000/// ER -