Abstract
While Bayesian network models may contain a handful of numerical parameters that are important for their quality, several empirical studies have confirmed that overall precision of their probabilities is not crucial. In this paper, we study the impact of the structure of a Bayesian network on the precision of medical diagnostic systems. We show that also the structure is not that important – diagnostic accuracy of several medical diagnostic models changes minimally when we subject their structures to such transformations as arc removal and arc reversal.
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
Similar content being viewed by others
References
Henrion, M., Breese, J.S., Horvitz, E.J.: Decision Analysis and Expert Systems. AI Magazine 12(4), 64–91 (1991)
Pearl, J.: Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Kaufmann Publishers, Inc, San Mateo (1988)
Druzdzel, M.J., Oniśko, A.: The impact of overconfidence bias on practical accuracy of Bayesian network models: An empirical study. In: Renooij, S., Tabachneck-Schijf, H.J., Mahoney, S.M. (eds.) Working Notes of the 2008 Bayesian Modelling Applications Workshop, Special Theme: How Biased Are Our Numbers? Annual Conference on Uncertainty in Artificial Intelligence (UAI–2008), July 9 (2008)
Oniśko, A., Druzdzel, M.J.: Effect of imprecision in probabilities on Bayesian network models: An empirical study. In: Working Notes of the European Conference on Artificial Intelligence in Medicine (AIME 2003), Workshop on Qualitative and Model-based Reasoning in Biomedicine, pp. 45–49 (October 19, 2003)
Oniśko, A., Druzdzel, M.J.: Impact of precision of Bayesian network parameters on accuracy of medical diagnostic systems. Artificial Intelligence in Medicine 57(3), 197–206 (2013)
Pradhan, M., Henrion, M., Provan, G., del Favero, B., Huang, K.: The sensitivity of belief networks to imprecise probabilities: An experimental investigation. Artificial Intelligence 85(1-2), 363–397 (1996)
Bache, K., Lichman, M.: UCI Machine Learning Repository, University of California, Irvine, School of Information and Computer Sciences, USA (2013), http://archive.ics.uci.edu/ml
Oniśko, A., Druzdzel, M.J., Wasyluk, H.: Extension of the Hepar II model to multiple-disorder diagnosis. In: Kłopotek, M., Michalewicz, S.W. (eds.) Intelligent Information Systems. Advances in Soft Computing, pp. 303–313. Physica-Verlag (A Springer-Verlag Company), Heidelberg (2000)
Czerniak, J., Zarzycki, H.: Application of rough sets in the presumptive diagnosis of urinary system diseases. In: Soldek, J., Drobiazgiewicz, L. (eds.) 9th International Conference on Artifical Inteligence and Security in Computing Systems, ACS 2002, pp. 41–51. Kluwer Academic Publishers, Norwell (2003)
Kononenko, I.: Inductive and Bayesian learning in medical diagnosis. Applied Artificial Intelligence 7, 317–337 (1993)
Cooper, G.F., Herskovits, E.: A Bayesian method for the induction of probabilistic networks from data. Machine Learning 9(4), 309–347 (1992)
Oniśko, A., Druzdzel, M.J., Wasyluk, H.: An experimental comparison of methods for handling incomplete data in learning parameters of Bayesian networks. In: Kłopotek, M., Michalewicz, M., Wierzchoń, S.T. (eds.) Intelligent Information Systems. Advances in Soft Computing, pp. 351–360. Physica-Verlag (A Springer-Verlag Company), Heidelberg (2002)
Moore, A.W., Lee, M.S.: Efficient algorithms for minimizing cross validation error. In: Proceedings of the 11th International Conference on Machine Learning. Morgan Kaufmann, San Francisco (1994)
Boerlage, B.: Link strengths in Bayesian networks. Master’s thesis, Dept. of Computer Science, The University of British Columbia, Vancuver, Canada (1992)
Nicholson, A.E., Jitnah, N.: Using mutual information to determine relevance in Bayesian networks. In: Lee, H.-Y. (ed.) PRICAI 1998. LNCS, vol. 1531, pp. 399–410. Springer, Heidelberg (1998)
Ebert-Uphoff, I.: Measuring connection strengths and link strengths in discrete Bayesian networks. Technical Report GT-IIC-07-01, Georgia Institute of Technology (2007)
Ebert-Uphoff, I.: Tutorial on how to measure link strengths in discrete Bayesian networks. Technical Report GT-ME-2009-001, Georgia Institute of Technology (2009)
Lacave, C., Díez, F.J.: A review of explanation methods for heuristic expert systems. The Knowledge Engineering Review 19(2), 133–146 (2004)
Koiter, J.R.: Visualizing inference in Bayesian networks. Master’s thesis, Delft University of Technology, Delft, The Netherlands (2006)
Kanazawa, Y.: Hellinger distance and Akaike’s information criterion for the histogram. Statistics and Probability Letters 17(4), 293–298 (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Oniśko, A., Druzdzel, M.J. (2014). Impact of Bayesian Network Model Structure on the Accuracy of Medical Diagnostic Systems. In: Rutkowski, L., Korytkowski, M., Scherer, R., Tadeusiewicz, R., Zadeh, L.A., Zurada, J.M. (eds) Artificial Intelligence and Soft Computing. ICAISC 2014. Lecture Notes in Computer Science(), vol 8468. Springer, Cham. https://doi.org/10.1007/978-3-319-07176-3_15
Download citation
DOI: https://doi.org/10.1007/978-3-319-07176-3_15
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07175-6
Online ISBN: 978-3-319-07176-3
eBook Packages: Computer ScienceComputer Science (R0)