Abstract
Alzheimer’s Disease (AD) is a degenerative disease with high prevalence in the elderly population. Its symptoms are often related to difficulty in remembering new information and include impaired judgment, disorientation, confusion, behavioral changes and difficulty in speaking and walking. Clinical Decision Support Systems can be designed to improve clinical decision-making by making the physician aware of the most probable diagnosis given the patient health records, and then reducing AD diagnostic error rates. This work extends a previous discrete Bayesian decision model for supporting diagnosis of AD and related disorders and proposes improvements in this model following two approaches: mixing continuous and discrete nodes by implementing a Hybrid Logistic Regression-Naïve Bayes model and relaxing independence assumptions by adopting the AnDE (Averaged n-Dependence Estimators) model. Our proposal presents better performance results. The 4-fold cross-validation results on CAD (Center for Alzheimer’s Disease and Related Disorders) patient dataset showed that the A2DE classifier (AnDE with n = 2) outperforms the previous discrete Bayesian network for AD considering all proposed measures: Area Under Receiver Operating Curve (AUC), F1-score, Mean Square Error (MSE) and Mean Cross-Entropy (MXE). Also, the Hybrid Logistic Regression-Naïve Bayes model outperforms the previous discrete Bayesian network for dementia considering MSE and, for AD, considering AUC and MSE.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Sosa-Ortiz, A., Acosta-Castillo, I., Prince, M.: Epidemiology of dementias and Alzheimer’s disease. Arch. Med. Res. 43(8), 600–608 (2012)
Newman-Toker, D., Pronovost, P.: Diagnostic errors: the next frontier for patient safety. J. Am. Med. Assoc. (JAMA) 301(10), 1060–1062 (2009)
Berner, E.S.: Clinical Decision Support Systems: Theory and Practice. Springer, New York (2007)
Haynes, R.B., Wilczynski, N.L.: Effects of computerized clinical decision support systems on practitioner performance and patient outcomes: methods of a decision-maker-researcher partnership systematic review. Implement Sci. 5(1), 12 (2010)
Kong, G., Xu, D., Yang, J.: Clinical decision support systems: a review on knowledge representation and inference under uncertainties. Int. J. Comput. Intell. Syst. 1(2), 159–167 (2008)
Jensen, F.V., Nielsen, T.D.: Bayesian Networks and Decision Graphs. Springer, New York (2007)
Pradhan, M., Provan, G., Middleton, B., Henrion, M.: Knowledge engineering for large belief networks. In: Tenth Conference of Uncertainty in Artificial Intelligence, pp. 484–490. Morgan Kaufmann Publishers Inc., San Francisco (1994)
Seixas, F.L., Zadrozny, B., Laks, J., Conci, A., Muchaluat-Saade, D.C.: A Bayesian network decision model for supporting the diagnosis of dementia, Alzheimer’s disease and mild cognitive impairment. Comput. Biol. Med. 51, 140–158 (2014)
Langseth, H., Nielsen, T.D., Rumí, R., Salmerón, A.: Inference in hybrid Bayesian networks. Reliab. Eng. Syst. Saf. 94(10), 1499–1509 (2009)
McGeachie, M.J., Chang, H., Weiss, S.T.: CGBayesNets: conditional Gaussian Bayesian network learning and inference with mixed discrete and continuous data. PLoS Comput. Biol. 10, 6 (2014)
Webb, G.I., Boughton, J.R., Wang, Z.: Not so Naïve Bayes: aggregating one-dependence estimators. Mach. Learn. 58(1), 5–24 (2005)
Pinheiro, P.R., Castro, A., Pinheiro, M.: A multicriteria model applied in the diagnosis of Alzheimer’s disease: a Bayesian network. In: Proceedings of the 11th IEEE International Conference on Computational Science and Engineering, CSE 2008, São Paulo (2008)
Fillenbaum, G., van Belle, G., Morris, J., Mohs, R., Mirra, S., Davis, P., Tariot, P., Silverman, J., Clark, C., Welsh-Bohmer, K.: Consortium to establish a registry for Alzheimer’s disease (CERAD): the first twenty years. Alzheimer’s Dement. J. Alzheimer’s Assoc. 4(2), 96–109 (2008)
Moreira, L.B., Namen, A.A.: System predictive for Alzheimer’s disease in clinical trial. J. Health Inform. 8, 3 (2016)
Dempster, A., Laird, N., Rubin, D.: Maximum likelihood from incomplete data via the EM algorithm. J. R. Stat. Soc. Ser. B Methodol. 39(1), 1–38 (1977)
Cooper, G.F., Herskovits, E.: A Bayesian method for the induction of probabilistic networks from data. Mach. Learn. 9(4), 309–347 (1992)
Murphy, K.: The Bayes net toolbox for Matlab. Comput. Sci. Stat. 33(2), 1024–1034 (2001)
Chawla, N., Bowyer, K., Hall, L., Kegelmeyer, W.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321–357 (2002)
Kononenko I.: On biases in estimating multi-valued attributes. In: International Joint Conference on Artificial Intelligence, vol. 14, pp. 1034–1040. Lawrence Erlbaum Associates, Montreal (1995)
Lucas, P.J.F., Hommersom, A.: Modeling the interactions between discrete and continuous causal factors in Bayesian networks. Int. J. Intell. Syst. 30(3), 209–235 (2015)
Shenoy, P.P.: Inference in hybrid Bayesian networks using mixtures of Gaussians. arXiv preprint arXiv:1206.6877 (2012)
Tan, Y., Moses, P.P., Chan, W., Romberg, P.M.: On construction of hybrid logistic regression-Naïve Bayes model for classification. In: Proceedings of the Eighth International Conference on Probabilistic Graphical Models, Lugano, 6–9 September 2016
Dash, D., Druzdzel, M.J.: Robust independence testing for constraint-based learning of causal structure. In: Proceedings of the Nineteenth Conference on Uncertainty in Artificial Intelligence, pp. 167–174. Morgan Kaufmann Publishers Inc., San Francisco (2002)
Zhang, H., Jiang, L., Su J.: Hidden Naïve Bayes. In: Proceedings of the Twentieth National Conference on Artificial Intelligence, Pennsylvania, 9–13 July 2005
Webb, G.I., Boughton, J.R., Zheng, F., Ting, K.M., Salem, H.: Learning by extrapolation from marginal to full-multivariate probability distributions: decreasingly Naïve Bayesian classification. Mach. Learn. 86(2), 233–272 (2012)
Han, J., Kamber, M., Pei, J.: Data Mining: Concepts and Techniques, 3rd edn. Elsevier, Amsterdam (2011)
Gaag, L.C., Renooij, S., Feelders, A., Groote, A., Eijkemans, M.J.C., Broekmans, F.J., Fauser, B.C.J .M.: Aligning Bayesian network classifiers with medical contexts. In: Perner, P. (ed.) MLDM 2009. LNCS (LNAI), vol. 5632, pp. 787–801. Springer, Heidelberg (2009). doi:10.1007/978-3-642-03070-3_59
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Appendix
Appendix
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Carvalho, C.M., Seixas, F.L., Conci, A., Muchaluat-Saade, D.C., Laks, J. (2017). Improving a Bayesian Decision Model for Supporting Diagnosis of Alzheimer’s Disease and Related Disorders. In: Perner, P. (eds) Machine Learning and Data Mining in Pattern Recognition. MLDM 2017. Lecture Notes in Computer Science(), vol 10358. Springer, Cham. https://doi.org/10.1007/978-3-319-62416-7_13
Download citation
DOI: https://doi.org/10.1007/978-3-319-62416-7_13
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-62415-0
Online ISBN: 978-3-319-62416-7
eBook Packages: Computer ScienceComputer Science (R0)