2011 | OriginalPaper | Chapter
Identification of School-Aged Children with High Probability of Risk Behavior on the Basis of Easily Measurable Variables
Authors : Peter Koncz, Jan Paralic
Published in: Information Quality in e-Health
Publisher: Springer Berlin Heidelberg
Activate our intelligent search to find suitable subject content or patents.
Select sections of text to find matching patents with Artificial Intelligence. powered by
Select sections of text to find additional relevant content using AI-assisted search. powered by
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.