Automatic identification of negated concepts in narrative clinical reports

Lior Rokach, Roni Romano, Oded Maimon

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Substantial medical data such as discharge summaries and operative reports are stored in textual form. Databases containing free-text clinical narratives reports often need to be retrieved to find relevant information for clinical and research purposes. Terms that appear in these documents tend to appear in different contexts. The context of negation, a negative finding, is of special importance, since many of the most frequently described findings are those denied by the patient or subsequently "ruled out." Hence, when searching free-text narratives for patients with a certain medical condition, if negation is not taken into account, many of the documents retrieved will be irrelevant. In this paper we examine the applicability of machine learning methods for automatic identification of negative context patterns in clinical narratives reports. We suggest two new simple algorithms and compare their performance with standard machine learning techniques such as neural networks and decision trees. The proposed algorithms significantly improve the performance of information retrieval done on medical narratives.

Original languageEnglish
Title of host publicationICEIS 2006 - 8th International Conference on Enterprise Information Systems, Proceedings
Pages257-262
Number of pages6
StatePublished - 2006
Event8th International Conference on Enterprise Information Systems, ICEIS 2006 - Paphos, Cyprus
Duration: 23 May 200627 May 2006

Publication series

NameICEIS 2006 - 8th International Conference on Enterprise Information Systems, Proceedings
VolumeAIDSS

Conference

Conference8th International Conference on Enterprise Information Systems, ICEIS 2006
Country/TerritoryCyprus
CityPaphos
Period23/05/0627/05/06

Keywords

  • Information retrieval
  • Machine learning
  • Medical informatics
  • Text classification

Fingerprint

Dive into the research topics of 'Automatic identification of negated concepts in narrative clinical reports'. Together they form a unique fingerprint.

Cite this