Advertisement

Knowledge and Information Systems

, Volume 50, Issue 1, pp 117–143 | Cite as

Clinical evidence framework for Bayesian networks

  • Barbaros Yet
  • Zane B. Perkins
  • Nigel R. M. Tai
  • D. William R. Marsh
Regular Paper

Abstract

There is poor uptake of prognostic decision support models by clinicians regardless of their accuracy. There is evidence that this results from doubts about the basis of the model as the evidence behind clinical models is often not clear to anyone other than their developers. In this paper, we propose a framework for representing the evidence-base of a Bayesian network (BN) decision support model. The aim of this evidence framework is to be able to present all the clinical evidence alongside the BN itself. The evidence framework is capable of presenting supporting and conflicting evidence, and evidence associated with relevant but excluded factors. It also allows the completeness of the evidence to be queried. We illustrate this framework using a BN that has been previously developed to predict acute traumatic coagulopathy, a potentially fatal disorder of blood clotting, at early stages of trauma care.

Keywords

Bayesian networks Evidence-based medicine Prognostic models Clinical decision support Knowledge engineering 

Notes

Acknowledgments

This research has been partly funded by the Academic Department of Military Surgery and Trauma, UK Defence Medical Services, and a Principal’s Studentship, Queen Mary University of London.

References

  1. 1.
    Allemang D, Hendler J (2011) Semantic web for the working ontologist: effective modeling in RDFS and OWL. Morgan Kaufmann, Los AltosGoogle Scholar
  2. 2.
    Altman DG, Vergouwe Y, Royston P, Moons KG (2009) Prognosis and prognostic research: validating a prognostic model. BMJ 338:1432–1435CrossRefGoogle Scholar
  3. 3.
    Antal P, Fannes G, Timmerman D, Moreau Y, De Moor B (2004) Using literature and data to learn Bayesian networks as clinical models of ovarian tumors. Artif Intell Med 30:257–281CrossRefGoogle Scholar
  4. 4.
    Antal P, Mészáros T, De Moor B, Dobrowiecki T (2001) Annotated Bayesian networks: a tool to integrate textual and probabilistic medical knowledge. In: Proceedings of 14th IEEE symposium on computer-based medical systems, 2001. CBMS 2001, pp 177–182Google Scholar
  5. 5.
    Arias M, Diez FJ, Palacios-Alonso M, Bermejo I (2012) ProbModelXML: a format for encoding probabilistic graphical models. In: Proceedings of the sixth European workshop on probabilistic graphical models, Granada, Spain, pp 11–18Google Scholar
  6. 6.
    ATCBN (2015) Acute traumatic coagulopathy Bayesian network evidence browser [Online]. http://www.traumamodels.com/atcbn/ATC_EBase. Accessed 15 Jan 2016
  7. 7.
    Berners-Lee T, Hendler J, Lassila O (2001) The semantic web. Sci Am 284:28–37CrossRefGoogle Scholar
  8. 8.
    Bodenreider O (2004) The unified medical language system (UMLS): integrating biomedical terminology. Nucl Acids Res 32:D267–D270CrossRefGoogle Scholar
  9. 9.
    Bucci G, Sandrucci V, Vicario E (2011) Ontologies and Bayesian networks in medical diagnosis. In: 2011 44th Hawaii international conference on system sciences (HICSS), Hawaii, USA, pp 1–8Google Scholar
  10. 10.
    Cozman FG (1998) The interchange format for Bayesian networks [Online]. http://www.cs.cmu.edu/~fgcozman/Research/InterchangeFormat/x. Accessed 15 Jan 2016
  11. 11.
    Da Costa PCG, Laskey KB, Laskey KJ (2008) PR-OWL: a Bayesian ontology language for the semantic web. In: Uncertainty reasoning for the semantic web I. Springer, pp 88–107Google Scholar
  12. 12.
    Daly R, Shen Q, Aitken S (2011) Learning Bayesian networks: approaches and issues. Knowl Eng Rev 26(02):99–157CrossRefGoogle Scholar
  13. 13.
    Devitt A, Danev B, Matusikova K (2006) Ontology-driven automatic construction of Bayesian networks for telecommunication network management. In: 2nd international workshop: formal ontologies meet industry (FOMI 2006), Trento, ItalyGoogle Scholar
  14. 14.
    Ding Z, Peng Y (2004) A probabilistic extension to ontology language OWL. In: Proceedings of the 37th annual Hawaii international conference on system sciences, 2004, Hawaii, USA, pp 1–10Google Scholar
  15. 15.
    Fenton NE, Neil M, Caballero JG (2007) Using ranked nodes to model qualitative judgments in Bayesian networks. IEEE Trans Knowl Data Eng 19:1420–1432CrossRefGoogle Scholar
  16. 16.
    Fenton NE, Neil MD (2012) Risk assessment and decision analysis with Bayesian networks. CRC Press, Boca RatonzbMATHGoogle Scholar
  17. 17.
    Fenz S (2012) An ontology-based approach for constructing Bayesian networks. Data Knowl Eng 73:73–88. doi: 10.1016/j.datak.2011.12.001 CrossRefGoogle Scholar
  18. 18.
    Guazzelli A, Zeller M, Lin W-C, Williams G (2009) PMML: an open standard for sharing models. R J 1(1):60–65Google Scholar
  19. 19.
    Harbour R, Miller J (2001) A new system for grading recommendations in evidence based guidelines. BMJ 323:334–336CrossRefGoogle Scholar
  20. 20.
    Helsper EM, van der Gaag LC (2002) Building Bayesian networks through ontologies. In: ECAI proceedings of 15th, Lyon, France, pp 680–684Google Scholar
  21. 21.
    Helsper EM, van Der Gaag LC (2007) Ontologies for probabilistic networks: a case study in the oesophageal-cancer domain. Knowl Eng Rev 22:67–86CrossRefGoogle Scholar
  22. 22.
    Ishak MB, Leray P, Amor NB (2011) Ontology-based generation of object oriented Bayesian networks. In: Proceedings of the 8th Bayesian modelling applications workshop, pp 9–17Google Scholar
  23. 23.
    Jaspers MW, Smeulers M, Vermeulen H, Peute LW (2011) Effects of clinical decision-support systems on practitioner performance and patient outcomes: a synthesis of high-quality systematic review findings. J Am Med Inform Assoc 18:327–334CrossRefGoogle Scholar
  24. 24.
    Kawamoto K, Houlihan CA, Balas EA, Lobach DF (2005) Improving clinical practice using clinical decision support systems: a systematic review of trials to identify features critical to success. BMJ 330:765CrossRefGoogle Scholar
  25. 25.
    Knublauch H, Fergerson R, Noy N, Musen M (2004) The Protégé OWL plugin: an open development environment for semantic web applications. In: Semantic web—ISWC 2004, Hiroshima, Japan, pp 229–243Google Scholar
  26. 26.
    Koller D, Pfeffer A (1997) Object-oriented Bayesian networks. In: Proceedings of the thirteenth conference on uncertainty in artificial intelligence. Morgan Kaufmann Publishers Inc., Providence, RI, pp 302–313Google Scholar
  27. 27.
    Kuo C-L, Buchman D, Katiyar A, Poole D (2013) Probabilistic reasoning with undefined properties in ontologically-based belief networks. In: Proceedings of the twenty-third international joint conference on artificial intelligence. AAAI Press, Beijing, China, pp 2532–2539Google Scholar
  28. 28.
    Laskey KB, Costa PC (2005) Of klingons and starships: Bayesian logic for the 23rd century. In: Proceedings of the twenty-first conference on uncertainty in artificial intelligence, Edinburgh, UK, pp 346–353Google Scholar
  29. 29.
    Laskey KB, Mahoney S (1997) Network fragments: representing knowledge for constructing probabilistic models. In: Proceedings of the thirteenth annual conference on uncertainty in artificial intelligence (UAI-97). Morgan Kaufmann Publishers, Providence, RI, pp 334–341Google Scholar
  30. 30.
    Li J, Wang ZJ (2009) Controlling the false discovery rate of the association/causality structure learned with the PC algorithm. J Mach Learn Res 10:475–514Google Scholar
  31. 31.
    Lucas PJ, van der Gaag LC, Abu-Hanna A (2004) Bayesian networks in biomedicine and health-care. Artif Intell Med 30:201–214CrossRefGoogle Scholar
  32. 32.
    Moons KGM, Altman DG, Vergouwe Y, Royston P (2009a) Prognosis and prognostic research: application and impact of prognostic models in clinical practice. BMJ 338:1487–1490Google Scholar
  33. 33.
    Moons KGM, Royston P, Vergouwe Y, Grobbee DE, Altman DG (2009b) Prognosis and prognostic research: What, why, and how? BMJ 338:1317–1320. doi: 10.1136/bmj.b375 CrossRefGoogle Scholar
  34. 34.
    Neil M, Fenton NE, Nielsen L (2000) Building large-scale Bayesian networks. Knowl Eng Rev 15:257–284CrossRefzbMATHGoogle Scholar
  35. 35.
    Pearl J (2000) Causality: models, reasoning and inference. Cambridge University Press, CambridgezbMATHGoogle Scholar
  36. 36.
    Richardson M, Domingos P (2006) Markov logic networks. Mach Learn 62:107–136CrossRefGoogle Scholar
  37. 37.
    Richardson T, Spirtes P (2002) Ancestral graph Markov models. Ann Stat 30(4):962–1030MathSciNetCrossRefzbMATHGoogle Scholar
  38. 38.
    Rieger C, Grinberg M (1977) The declarative representation and procedural simulation of causality in physical mechanisms. In: Proceedings of the 5th international joint conference on artificial intelligence, vol 1, pp 250–256Google Scholar
  39. 39.
    Sadeghi S, Barzi A, Smith JW (2005) Ontology driven construction of a knowledgebase for Bayesian decision models based on UMLS. Stud Health Technol Inform 116:223–228Google Scholar
  40. 40.
    Segaran T, Evans C, Taylor J (2009) Programming the semantic web. O’Reilly Media, Sebastopol, CAGoogle Scholar
  41. 41.
    Spirtes P, Glymour CN, Scheines R (2000) Causation, prediction, and search. MIT press, CambridgezbMATHGoogle Scholar
  42. 42.
    Tsamardinos I, Brown LE (2008) Bounding the false discovery rate in local Bayesian network learning. In: AAAI, pp 1100–1105Google Scholar
  43. 43.
    Van der Gaag LC, Tabachneck-Schijf HJM (2010) Library-style ontologies to support varying model views. Int J Approx Reason 51:196–208CrossRefGoogle Scholar
  44. 44.
    World Wide Web Consortium (W3C) (2004) Web Ontology Language (OWL), W3C Recommendation [Online]. http://www.w3.org/TR/owlref/. Accessed 18 Mar 2016
  45. 45.
    Wyatt JC, Altman DG (1995) Commentary: Prognostic models: Clinically useful or quickly forgotten? BMJ 311:1539–1541. doi: 10.1136/bmj.311.7019.1539 CrossRefGoogle Scholar
  46. 46.
    Yang Y, Calmet J (2005) OntoBayes: an ontology-driven uncertainty model. In: International conference on computational intelligence for modelling, control and automation, 2005 and international conference on intelligent agents, web technologies and internet commerce, Vienna, Austria, pp 457–463. doi: 10.1109/CIMCA.2005.1631307
  47. 47.
    Yet B, Marsh W (2015) BNEvidenceBase: evidence framework for BN models [Online]. https://github.com/byet/BNEvidenceBase/. Accessed 15 Jan 2016
  48. 48.
    Yet B, Perkins Z, Fenton N, Tai N, Marsh W (2014a) Not just data: a method for improving prediction with knowledge. J Biomed Inform 48:28–37. doi: 10.1016/j.jbi.2013.10.012 CrossRefGoogle Scholar
  49. 49.
    Yet B, Perkins Z, Tai N, Marsh W (2014b) Explicit evidence for prognostic Bayesian network models. Stud Health Technol Inform 205:53–57. doi: 10.3233/978-1-61499-432-9-53 Google Scholar
  50. 50.
    Zheng H-T, Kang B-Y, Kim H-G (2008) An ontology-based Bayesian network approach for representing uncertainty in clinical practice guidelines. In: Uncertainty reasoning for the semantic web I: ISWC international workshops, URSW 2005–2007, revised selected and invited papers. Springer, pp 161–173Google Scholar

Copyright information

© Springer-Verlag London 2016

Authors and Affiliations

  1. 1.School of Electronic Engineering and Computer ScienceQueen Mary University of LondonLondonUK
  2. 2.Centre for Trauma ScienceQueen Mary University of LondonLondonUK
  3. 3.The Royal London HospitalLondonUK
  4. 4.Department of Industrial EngineeringHacettepe UniversityAnkaraTurkey

Personalised recommendations