Abstract
The relative performances of different classifiers applied to the same data are typically analyzed using the Receiver Operator Characteristic framework (ROC). This paper proposes a further analysis by explaining the operation of classifiers using low-order Boolean rules to fit the predicted response surfaces using the Orthogonal Search Based Rule Extraction algorithm (OSRE). Four classifiers of malignant or benign ovarian tumours are considered. The models analyzed are two Logistic Regression models and two Multi-Layer Perceptrons with Automatic Relevance Determination (MLP-ARD) each applied to a specific alternative covariate subset. While all models have comparable classification rates by Area Under ROC (AUC) the classification varies for individual cases and so do the resulting explanatory rules. Two sets of clinically plausible rules are obtained which account for over one half of the malignancy cases, with near-perfect specificity. These rules are simple, explicit and can be prospectively validated in future studies.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Ameye, L.: Predictive Models for Classification in Gynecology. PhD thesis, Faculty of Engineering, Katholieke Universiteit Leuven, Leuven, Belgium (2005)
Aung, M.S.H., Lisboa, P.J.G., Taktak, A.F.G., Damato, B.E.: Modelling Survival of Intraocular Melanoma using a Partial Logistic Artificial Neural Network with Automatic Relevance Determination and Orthogonal Search Based Rule Extraction. In: Proc. Computational Intelligence in Medicine (CIMED), Lisbon, Portugal, pp. 114–121 (2005)
Van Calster, B., Timmerman, D., Nabney, I.T., Valentin, L., Van Holsbeke, C., Van Huffel, S.: Classifying Ovarian Tumors using Bayesian Multi-Layer Perceptrons and Automatic Relevance Determination: A Multi-Center Study. In: Proc. of the 28th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC2006), New York City, USA, pp. 5342–5345 (2006)
Etchells, T.A., Harrison, M.J.: Orthogonal Search-Based Rule Extraction for Modelling the Decision to Transfuse. Anesthesia 61(4), 335–338 (2006)
Etchells, T.A., Lisboa, P.J.G.: Orthogonal Search-Based Rule Extraction (OSRE) for Trained Neural Networks: A Practical and Efficient Approach. IEEE Trans Neur. Net. 17(2), 374–384 (2006)
Timmerman, D., Testa, A.C., Bourne, T., Ferrazzi, E., Ameye, L., Konstantinovic, M.L., Van Calster, B., Collins, W.P., Vergote, I., Van Huffel, S., Valentin, L.: Logistic Regression Model to Distinguish Between the Benign and Malignant Adnexal Mass Before Surgery: A Multicenter Study by the International Ovarian Tumor Analysis Group. J Clin. Oncol., 8794–8801 (2005)
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 2007 Springer Berlin Heidelberg
About this paper
Cite this paper
Aung, M.S.H. et al. (2007). Comparing Analytical Decision Support Models Through Boolean Rule Extraction: A Case Study of Ovarian Tumour Malignancy. In: Liu, D., Fei, S., Hou, Z., Zhang, H., Sun, C. (eds) Advances in Neural Networks – ISNN 2007. ISNN 2007. Lecture Notes in Computer Science, vol 4492. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-72393-6_139
Download citation
DOI: https://doi.org/10.1007/978-3-540-72393-6_139
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-72392-9
Online ISBN: 978-3-540-72393-6
eBook Packages: Computer ScienceComputer Science (R0)