A framework of a logic-based question-answering system for the medical domain (LOQAS-Med)

ABSTRACT

Question-answering systems that provide precise answers to questions, by combining techniques for information retrieval, information extraction, and natural language processing, are seen as the next-generation search engines. Due to the growth and real-world impact of biomedical information, the need for question-answering systems that can aid medical researchers and health care professionals in their information search is acutely felt. In order to provide users with accurate answers, such systems need to go beyond lexico-syntactic analysis to semantic analysis and processing of texts and knowledge resources. Moreover, question-answering systems equipped with reasoning capabilities can derive more adequate answers by using inference. Research on question answering in the medical and health care domain is still in its inception stage. While several recent approaches to medical question answering have explored use of semantic knowledge, few approaches have exploited the utility of logic formalisms and of inference mechanisms. In this paper, we present a framework for a logic-based question-answering system for the medical domain, which uses Description Logic as the formalism for knowledge representation and reasoning. As a first step toward building the proposed system, we present semantic analysis and classification of medical questions.

REFERENCES

• 1: Armstrong, E. C. The well-built clinical question: the key to finding the best evidence efficiently. WMJ, 98 (1999), 25--28.
• 2: Athenikos, S. J., Han, H., and Brooks, A. D. Semantic analysis and classification of medical questions for a logic-based medical question-answering system. In Proceedings of the International Workshop on Biomedical and Health Informatics (BHI 2008) in conjunction with 2008 IEEE Conference on Bioinformatics and Biomedicine (IEEE BIBM 2008) (Philadelphia, PA, Nov. 3--5, 2008), 111--112.
• 3: Franz Baader , Diego Calvanese , Deborah L. McGuinness , Daniele Nardi , Peter F. Patel-Schneider, The description logic handbook: theory, implementation, and applications, Cambridge University Press, New York, NY, 2003
• 4: Bergus, G. R., Randall, C. S., Sinift, S. D., and Rosenthal, D. M. Does the structure of clinical questions affect the outcome of curbside consultations with specialty colleagues? Arch Fam Med, 9 (2000), 541--547.
• 5: Delbecque, T., Jacquemart, P., and Zweigenbaum, P. Indexing UMLS semantic types for medical question-answering. In Connecting Medical Informatics and Bio-Informatics. ENMI, 2005, 805--810.
• 6: Demner-Fushman, D., Few, B., Hauser, S. E., and Thoma, G. Automatically identifying health outcome information in MEDLINE records. J Am Med Inform Assoc, 13 (2006), 52--60.
• 7: Dina Demner-Fushman , Jimmy Lin, Answering Clinical Questions with Knowledge-Based and Statistical Techniques, Computational Linguistics, v.33 n.1, p.63-103, March 2007 [doi>10.1162/coli.2007.33.1.63]
• 8: Ely, J. W., Osheroff, J. A., Ebell, M. H., Bergus, G. R., Levy, B. T., Chamliss, M. L., and Evans, E. R. Analysis of questions asked by family doctors regarding patient care. BMJ, 319 (1999), 358--361.
• 9: Ely, J. W., Osheroff, J. A., Gorman, P. N., Ebell, M. H., Chambliss, M. L., Pifer, E. A., and Stavri, P. Z. A taxonomy of generic clinical questions: classification study. BMJ, 321 (2000), 429--432.
• 10: Ely, J. W., Osheroff, J. A., Ebell, M. H., Chambliss, M. L., Vinson, D. C., Stevermer, J. J., amd Pifer, E. A. Obstacles to answering doctors' questions about patient care with evidence: qualitative study. BMJ, 324 (2002), 710--716.
• 11: Ely, J. W., Osheroff, J. A., Chambliss, M. L., Ebell, M. H., and Rosenbaum, M. E. Answering physicians' clinical questions: obstacles and potential solutions. J Am Med Inform Assoc, 12 (2005), 217--224.
• 12: Fiszman, M., Rindflesch, T. C., and Kilicoglu, H. Integrating a hypernymic proposition interpreter into a semantic processor for biomedical texts. In Proceedings of the 2003 AMIA Annual Symposium (AMIA 2003) (Washington, D.C., Nov. 8--12, 2003). AMIA, 2003, 239--243.
• 13: GeneOntology. http://www.geneontology.org/.
• 14: Hersh, W. R., Crabtree, M. K., Hickman, D. H., Sacherek, L., Friedman, C. P., Tidmarsh, P., Mosbaek, C., and Kraemer, D. Factors associated with success in searching MEDLINE and applying evidence to answer clinical questions. J Am Med Inform Assoc, 9 (2002), 283--293.
• 15: Huang, X., Lin, J., and Demner-Fushman, D. Evaluation of PICO as a knowledge representation for clinical questions. In Proceedings of the 2006 AMIA Annual Symposium (AMIA 2006) (Washington, D.C., Nov. 11--16, 2006). AMIA, 2006, 359--363.
• 16: Jacquemart, P., and Zweigenbaum, P. Towards a medical question-answering system: a feasibility study. Stud Health Technol Inform, 95 (2003), 463--468.
• 17: Diego Mollá , José Luis Vicedo, Question Answering in Restricted Domains: An Overview, Computational Linguistics, v.33 n.1, p.41-61, March 2007 [doi>10.1162/coli.2007.33.1.41]
• 18: NCI (National Cancer Institute) Thesaurus. www.nci.nih.gov/cancerinfo/terminologyresources/.
• 19: Niu, Y., and Hirst, G. Analysis of semantic classes in medical text for question answering. In Proceedings of the ACL 2004 Workshop on Question Answering in Restricted Domains (Barcelona, Spain, Jul 25, 2004). ACL, 2004.
• 20: Niu, Y., Zhu, X., and Hirst, G. Using outcome polarity in sentence extraction for medical question-answering. In Proceedings of the 2006 AMIA Annual Symposium (AMIA 2006) (Washington, D.C., Nov. 11--16, 2006). AMIA, 2006, 599--603.
• 21: NLM Clinical Questions Collection. http://clinques.nlm.nih.gov/.
• 22: OWL Web Ontology Language Guide. http://www.w3.org/TR/owl-guide/.
• 23: Richardson, W. S., Wilson, M. C., Nishikawa, J., and Hayward, R. S. The well-built clinical question: a key to evidence-based decisions. ACP J Club, 123 (1995), A12--13.
• 24: Sackett, D. L., Strauss, S., Richardson, W., Rosenberg, W., and Haynes, R. Evidence-Based Medicine: How to Practice and Teach EBM (2^nd ed.). Churchill Livingstone, Edinburgh, UK, 2000.
• 25: Terol, R. M., Martínez -Barco, P., and Palomar, M. Applying NLP Techniques and Biomedical Resources to Medical Questions in QA Performance. In Proceedings of the Fifth Mexican International Conference on Artificial Intelligence (MICAI 2006) (Apizaco, Mexico, Nov. 13--17, 2006). Springer-Verlag, Berlin; Heidelberg, 2006, 996--1006.
• 26: Rafael M. Terol , Patricio Martínez-Barco , Manuel Palomar, A knowledge based method for the medical question answering problem, Computers in Biology and Medicine, v.37 n.10, p.1511-1521, October, 2007 [doi>10.1016/j.compbiomed.2007.01.013]
• 27: UMLS (Unified Medical Language System). www.nlm.nih.gov/research/umls/.
• 28: Ellen M. Voorhees, The TREC question answering track, Natural Language Engineering, v.7 n.4, p.361-378, December 2001 [doi>10.1017/S1351324901002789]

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.3 Information Search and Retrieval

Additional Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.1 Applications and Expert Systems
          Subjects: Medicine and science
      I.2.3 Deduction and Theorem Proving
          Subjects: Deduction (e.g., natural, rule-based); Logic programming; Inference engines; Answer/reason extraction
      I.2.4 Knowledge Representation Formalisms and Methods
          Subjects: Predicate logic; Semantic networks; Representation languages
      I.2.7 Natural Language Processing
          Subjects: Language parsing and understanding; Text analysis

  J. Computer Applications
  J.3 LIFE AND MEDICAL SCIENCES
      Subjects: Medical information systems

General Terms:
Algorithms, Design, Languages, Theory

Keywords:
biomedical informatics, description logics, natural language processing, question answering, semantic text mining