A Survey of Text Extraction Tools for Intelligent Healthcare Decision Support Systems

  • Ryan Ramirez
  • Jordan Iversen
  • John Ouimet
  • Ziad Kobti
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 4)


Due to abundance of textual corpora present in the medical field, it is difficult for humans to process text and infer knowledge efficiently. Traditionally, gathered information would be analyzed by domain experts who would infer knowledge and provide decisions or solutions based on a problem. The medical field would greatly benefit from an automated decision support system to make intelligent and justified decisions about a certain topic. The approach taken in this study is to survey existing text extraction tools to analyze human-generated comments from newspaper articles relating to H1N1 hype. The goal is to evaluate existing tools to later implement into an automated healthcare decision support system. From our results, Alchemy seems to be the most promising term extraction tool for use within a larger decision support framework.


Decision Support System Natural Language Processing Input Text Name Entity Recognition Candidate Term 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Kao, A., Poteet, S.: Text Mining And Natural Language Processing - Introduction for the Special Issue. SIGKDD Explorations 7(1), 1–2 (2006)CrossRefGoogle Scholar
  2. 2.
    Tsoi, L.C., Patel, R., Zhao, W., Zheng, W.J.: Text-mining Approach To Evaluate Terms For Ontology Development. N. Engl. J. Biomedical Informatics 42, 824–830 (2009)CrossRefGoogle Scholar
  3. 3.
    Feldman, R., Hirsh, H.: Exploiting background information in knowledge discovery from text. N. Engl. J. Intelligent Information Systems 9, 83–97 (1997)CrossRefGoogle Scholar
  4. 4.
    Feldman, R., et al.: Maximal association rules: a new tool for mining for keyword co-occurrences in document collections. Presented at the 3rd International Conference on Knowledge Discovery, Newport Beach, CA., USA (1997)Google Scholar
  5. 5.
    Frawley, W.J., et al.: Knowledge discovery in databases: an overview. In: Piatetsky-Shapiro, G., Frawley, W.J. (eds.) Knowledge Discovery in Databases, pp. 1–27. MIT Press, Cambridge (1991)Google Scholar
  6. 6.
    Hayes, P.: Intelligent high-volume processing using shallow, domain-specific techniques. In: Text-Based Intelligent Systems: Current Research and Practice in Information Extraction and Retrieval, pp. 227–242. Lawrence Erlbaum, Hillside (1992)Google Scholar
  7. 7.
    Joachims, T.: Text categorization with support vector machines: learning with many relevant features. In: Nédellec, C., Rouveirol, C. (eds.) ECML 1998. LNCS, vol. 1398. Springer, Heidelberg (1998)CrossRefGoogle Scholar
  8. 8.
    Sebastiani, F.: Machine learning in automated text categorization. ACM Computing Surveys 34, 1–47 (2002)CrossRefMathSciNetGoogle Scholar
  9. 9.
    Frantzi, T.K.: Incorporating context information for the extraction of terms. Presented at the conference of ACL-EACL, Madrid, Spain (1997)Google Scholar
  10. 10.
    Cardie, C.: Empirical methods in information extraction. AI Magazine 18, 65–80 (1997)Google Scholar
  11. 11.
    Cowie, J., Lehnert, W.: Information extraction. Comm. Assoc. Comput. Mach. 39, 80–91 (1996)Google Scholar
  12. 12.
    Chapman, W.W., Cohen, K.B.: Current Issues in Biomedical Text Mining and Natural Language Processing. N. Engl. J. Biomedical Informatics 42, 757–759 (2009)CrossRefGoogle Scholar
  13. 13.
    Bichindaritz, I., Akkineni, S.: Concept Mining For Indexing Medical Literature. J. Engineering Applications of Artificial Intelligence 19, 411–417 (2006)CrossRefGoogle Scholar
  14. 14.
    Chang, C., Hsu, C.: Enabling Concept-Based Relevance Feedback For Information Retrieval on the WWW. IEEE Knowledge and Data Engineering 11(4), 595–609 (1999)CrossRefGoogle Scholar
  15. 15.
    Fuller, S., et al.: A Knowledge-based System To Enhance Scientific Discovery: Telemakus. Biomedical Digital Library 1(1), 2 (2004)CrossRefGoogle Scholar
  16. 16.
    Brunzel, M., Spiliopoulou, M.: Domain Relevance on Term Weighting. In: Kedad, Z., Lammari, N., Métais, E., Meziane, F., Rezgui, Y. (eds.) NLDB 2007. LNCS, vol. 4592, pp. 427–432. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  17. 17.
    Triantaphyllou, E., et al.: Computers & Industrial Engineering 43, 657–659 (2002)Google Scholar
  18. 18.
    Liu, B., et al.: Opinion Mining & Summarization – Sentiment Analysis. In: WWW 2008 (2008)Google Scholar
  19. 19.
    Grimes, S.: Text Analytics For Dummies, Text Analytics Summit (2008)Google Scholar
  20. 20.
    OpenCalais: FAQ – General Question (2009), (Cited April 4, 2010)
  21. 21.
    NaCTeM: National Centre for Text Mining (2010), (Cited April 1, 2010)
  22. 22.
    Evri: Evri Developer Center, (Cited April 2, 2010)
  23. 23.
    Alchemy: Alchemy API Overview (2010), (Cited April 2, 2010)
  24. 24.
    Frantzi, K., Ananiadou, S., Mima, H.: Automatic recognition of multi-word terms. International Journal of Digital Libraries 3(2), 117–132 (2000)CrossRefGoogle Scholar
  25. 25.
    The Canadian Press: WHO dismisses claims H1N1 pandemic was a fake (2010), (Cited April 1, 2010)
  26. 26.
    Pearson, C. (The Windsor Star): H1N1’s severity didn’t come close to some predictions, says Dr. Allen Heiman (2010), (Cited April 1, 2010)
  27. 27.
    Kirkey, S. (Canwest News Service): Experts call for end of vaccination program (2009), (Cited April 1, 2010)
  28. 28.
    Kirkey, S. (Canwest News Service): H1N1 flu: The fear, the facts, the future (2009), (Cited April 1, 2010)
  29. 29.
    Jones, A., The Canadian Press: Latest poll backs government handling of H1N1 vaccinations (2009), (Cited April 1, 2010)
  30. 30.
    There a Boyle, Health Reporter: Health bosses accused of flu-mongering (2009), (Cited 1 April 2010)
  31. 31.
    Hall, J.(Health Reporter): H1N1 reaction product of hype or prudence? (2009), (Cited April 1, 2010)

Copyright information

© Springer Berlin Heidelberg 2010

Authors and Affiliations

  • Ryan Ramirez
    • 1
  • Jordan Iversen
    • 1
  • John Ouimet
    • 1
  • Ziad Kobti
    • 1
  1. 1.School of Computer ScienceUniversity of Windsor 

Personalised recommendations