Identification of School-Aged Children with High Probability of Risk Behavior on the Basis of Easily Measurable Variables
- 1.9k Downloads
The use of the methods of Knowledge Discovery in Databases (KDD) in the domain of public health is still topical. One of the major reasons for its increasing use is the need for an efficient processing of the increasing volumes of data. The aim of our contribution is to analyze the possibilities of the usage of these methods to identify the groups of school-aged children with a high probability of risky behavior. The obtained results are useful for the formation of models applicable for more efficient identification of target groups of prevention programs. In this work we use Slovak national dataset from the international study Health Behaviour in School-Aged Children. The used machine learning methods were Support Vector Machine, Naïve Bayes Classifier and the J48 machine learning algorithm. The results suggest promising possibilities for the use of the machine learning methods to develop classification models useful for public health.
KeywordsKnowledge discovery in databases machine learning public health risky behavior
Unable to display preview. Download preview PDF.
- 3.Expert Health Data Programming, http://www.ehdp.com/links/index.htm
- 4.Holmes, J.H., Durbin, D.R., Winston, F.K.: Discovery of predictive models in an injury surveillance database: an application of data mining in clinical research. In: Proc. AMIA Symp., pp. 359–363 (2000)Google Scholar
- 5.Orlygsdottir, B.: Using knowledge discovery to identify potentially useful patterns of health promotion behavior of 10–12 year old Icelandic children. The University of Iowa (2008)Google Scholar
- 13.Health Behaviour in School-Aged Children, http://www.hbsc.org/index.html
- 14.Vapnik, V.: The nature of statistical learning theory. Springer-Verlag New York, Inc. (1995)Google Scholar
- 15.Abe, S.: Support Vector Machines for Pattern Classification (Advances in Pattern Recognition). Springer-Verlag New York, Inc. (2005)Google Scholar
- 17.Paralic, J., Furdik, K., Tutoky, G., Bednar, P., Sarnovsky, M., Butka, P., Babic, F.: Dolovanie znalostí z textov. Equilibria, s.r.o. (2010)Google Scholar
- 18.Quinlan, J.R.: C4.5: programs for machine learning. Morgan Kaufmann Publishers Inc. (1993)Google Scholar