In the application of microarray data, how to select a small number of informative genes from thousands of genes that may contribute to the occurrence of cancers is an important issue. Many researchers use various computational intelligence methods to analyzed gene expression data.

Decision tree (DT) analysis was applied in this cross-sectional study to investigate caries experience in children by using clinical and microbiological data obtained from parent–child pairs. Thirty pairs of parents and children were recruited from periodontal and pediatric dental clinics. All participants were clinically examined for caries and periodontitis by a calibrated examiner. Cariogenic and periodontopathic bacteria examinations were conducted. The Kendall rank correlation coefficient was used to measure the association between data variables obtained through clinical and microbiological examinations. A classificatory inductive decision tree was generated using the C4.5 algorithm with the top-down approach. The C4.5 DT analysis was applied to classify major influential factors for children dental caries experience. The DT identified parents’ periodontal health classification, decayed, missing, filled permanent teeth (DMFT) index, periodontopathic test (PerioCheck) result, and periodontal pocket depth as the classification factors for children caries experience. 13.3% of children were identified with a low decayed, missing, filled primary teeth (dmft) index (dmft < 3) whose parents had a periodontal pocket depth ≤3.7, PerioCheck score >1, DMFT index 2. The DT model for this study sample had an accuracy of 93.33%. Here, parental periodontal status and parents’ DMFT were the factors forming the DT for children’s caries experience.