Knowledge discovery and data mining to assist natural language understanding.

Item request has been placed! ×
Item request cannot be made. ×
loading   Processing Request
Read More Add to Saved list
  • Author(s): Wilcox A;Wilcox A; Hripcsak G
  • Source:
    Proceedings. AMIA Symposium [Proc AMIA Symp] 1998, pp. 835-9.
  • Publication Type:
    Journal Article; Research Support, U.S. Gov't, P.H.S.
  • Language:
    English
  • Additional Information
    • Source:
      Publisher: Hanley & Belfus Country of Publication: United States NLM ID: 100883449 Publication Model: Print Cited Medium: Print ISSN: 1531-605X (Print) Linking ISSN: 1531605X NLM ISO Abbreviation: Proc AMIA Symp Subsets: MEDLINE
    • Publication Information:
      Original Publication: Philadelphia : Hanley & Belfus, c1998-
    • Subject Terms:
      Artificial Intelligence* ; Information Storage and Retrieval* ; Natural Language Processing* ; Radiography, Thoracic*; Decision Trees ; Heart Diseases/diagnostic imaging ; Humans ; Lung Diseases/diagnostic imaging ; Sensitivity and Specificity
    • Abstract:
      As natural language processing systems become more frequent in clinical use, methods for interpreting the output of these programs become increasingly important. These methods require the effort of a domain expert, who must build specific queries and rules for interpreting the processor output. Knowledge discovery and data mining tools can be used instead of a domain expert to automatically generate these queries and rules. C5.0, a decision tree generator, was used to create a rule base for a natural language understanding system. A general-purpose natural language processor using this rule base was tested on a set of 200 chest radiograph reports. When a small set of reports, classified by physicians, was used as the training set, the generated rule base performed as well as lay persons, but worse than physicians. When a larger set of reports, using ICD9 coding to classify the set, was used for training the system, the rule base performed worse than the physicians and lay persons. It appears that a larger, more accurate training set is needed to increase performance of the method.
    • References:
      J Gerontol A Biol Sci Med Sci. 1995 Nov;50(6):M298-302. (PMID: 7583800)
      Ann Intern Med. 1995 May 1;122(9):681-8. (PMID: 7702231)
      J Am Med Inform Assoc. 1994 Mar-Apr;1(2):161-74. (PMID: 7719797)
      Comput Methods Programs Biomed. 1994 Oct;45(1-2):117-20. (PMID: 7889741)
      Ann Intern Med. 1993 Oct 15;119(8):844-50. (PMID: 8018127)
      Proc Annu Symp Comput Appl Med Care. 1993;:274-8. (PMID: 8130477)
      Proc Annu Symp Comput Appl Med Care. 1993;:639-43. (PMID: 8130552)
      Comput Biomed Res. 1993 Feb;26(1):74-97. (PMID: 8444029)
      Comput Biomed Res. 1996 Jun;29(3):153-61. (PMID: 8812067)
      J Am Med Inform Assoc. 1996 Jul-Aug;3(4):288-99. (PMID: 8816352)
      Comput Biomed Res. 1996 Oct;29(5):351-72. (PMID: 8902364)
      Artif Intell Med. 1996 Feb;8(1):23-36. (PMID: 8963379)
      Methods Inf Med. 1996 Dec;35(4-5):285-301. (PMID: 9019092)
    • Grant Information:
      5T15 LM07079 United States LM NLM NIH HHS; R29 LM05627 United States LM NLM NIH HHS
    • Publication Date:
      Date Created: 19990203 Date Completed: 19990316 Latest Revision: 20181113
    • Publication Date:
      20240829
    • Accession Number:
      PMC2232072
    • Accession Number:
      9929336