Abstract
The abdominal pain is considered a very common disease during the childhood. One of the main diseases which are considered nowadays as the cause of childhood abdominal pain is the appendicitis which is very hard to be diagnosed in children. Moreover, even when it is diagnosed the doctors should decide about the type of appendicitis and take a crucial decision about the treatment (surgeon or medication). For these reasons, researchers in the last decade have focused on developing machine learning models to predict appendicitis from childhood abdominal pain clinical cases. However, most of these methods are limited to low performance and to using diagnostic factors which are not generally available. Moreover, none of them is available as a tool which could be used in practice. For all these reasons, we developed and applied a new ensemble methodology which combines the results of three machine learning models: Artificial Neural Networks, Support Vector Machines and Random Forests. The implementation is available as a standalone tool named AppendicitisScan Tool.
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
Sim, K.T., Picone, S., Crade, M., Sweeney, J.P.: Ultrasound with graded compression in the evaluation of acute appendicitis. J. Natl. Med. Assoc. 81(9), 954–957 (1989)
Mantzaris, D., Anastassopoulos, G., Adamopoulos, A., Stephanakis, I., Kambouri, K., Gardikis, S.: Selective Clinical Estimation of Childhood Abdominal Pain based on Pruned Artificial Neural Networks. In: Proceedings of the 2007 WSEAS Int. Conference on Cellular and Molecular Biology-Biophysics and Bioengineering, Athens, Greece, August 26-28, pp. 50–55 (2007)
Kentsis, A., Lin, Y.Y., Kurek, K., Calicchio, M., Wang, Y.Y., Monigatti, F., Campagne, F., Lee, R., Horwitz, B., Steen, H., Bachur, R.: Discovery and Validation of Urine Markers of Acute Pediatric Appendicitis Using High-Accuracy Mass Spectrometry. Ann. Emerg. Med. 55(1), 62–70 (2010)
Sakai, S., Kobayashi, K., Nakamura, J., Toyabe, S., Akazawa, K.: Accuracy in the Diagnostic Prediction of Acute Appendicitis Based on the Bayesian Network Model. Methods Inf. Med. 46(6), 723–726 (2007)
Ting, H.W., Wu, J.T., Chan, C.L., Lin, S.L., Chen, M.H.: Decision Model for Acute Appendicitis Treatment With Decision Tree Technology—A Modification of the Alvarado Scoring System. Journal of Chinese Medical Assiciation 73(8), 401–406 (2010)
Adamopoulos, A., Ntasi, M., Mavroudi, S., Likothanassis, S., Iliadis, L., Anastassopoulos, G.: Revealing the Structure of Childhood Abdominal Pain Data and Supporting Diagnostic Decesion Making. In: Palmer-Brown, D., Draganova, C., Pimenidis, E., Mouratidis, H. (eds.) EANN 2009. CCIS, vol. 43, pp. 165–177. Springer, Heidelberg (2009)
Anastasopoulos, G., Iliadis, L.: Intelligent hybrid modeling towards the prognosis of abdominal pain. International Journal of Hybrid Intelligent Systems 6(4), 245–255 (2009)
Haykin, S.: Neural Networks: A Comprehensive Foundation. Prentice Hall (1998)
More, J.: The Levenberg-Marquardt algorithm: Implementation and theory. In: Numerical Analysis Lecture Notes in Mathematics, vol. 630, pp. 105–116 (1978)
Vapnik, V.: The Nature of Statistical Learning Theory. Springer (2000)
Keerthi, S., Lin, C.J.: Asymptotic behaviours of support vector machines with Gaussian kernel. Neural Computation 15, 1667–1689 (2003)
Breiman, L.: Random Forests. Machine Learning 45(1), 5–32 (2001)
Batista, G., Monard, M.C.: K-Nearest Neighbour as Imputation Method: Experimental Results. Technical Report 186, ICMC-USP (2002)
Meir, R., Ratsch, G.: An Introduction to Boosting and Leveraging. In: Mendelson, S., Smola, A.J. (eds.) Advanced Lectures on Machine Learning. LNCS (LNAI), vol. 2600, pp. 118–183. Springer, Heidelberg (2003)
Papadimitriou, S., Terzidis, K.: Efficient and Interpretable Fuzzy Classifiers from Data with Support Vector Learning. Intelligent Data Analysis 9(6), 527–550 (2005)
Papadimitriou, S., Terzidis, K., Mavroudi, S., Skarlas, L., Likothanassis, S.: Fuzzy rule based classifiers from support vector learning. WSEAS Transactions on Computers 4(7), 661–670 (2005)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mitroulias, A., Konstantinos, T., Likothanassis, S., Seferina, M. (2013). AppendicitisScan Tool: A New Tool for the Efficient Classification of Childhood Abdominal Pain Clinical Cases Using Machine Learning Tools. In: Iliadis, L., Papadopoulos, H., Jayne, C. (eds) Engineering Applications of Neural Networks. EANN 2013. Communications in Computer and Information Science, vol 384. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-41016-1_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-41016-1_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-41015-4
Online ISBN: 978-3-642-41016-1
eBook Packages: Computer ScienceComputer Science (R0)