ABSTRACT
OBJECTIVE: To study the application of decision tree in the research of anemia among rural children. METHODS: In the Enterprise Miner module of software SAS 8.2, 3000 observations were sampled from database and the decision tree model was built. The model using decision tree of CART bases on Gini impurity index. RESULTS: The misclassification rate of decision tree model was, training set 21.2%, validation set 21.9%. The Root ASE of decision tree model was, training set 0.399, validation set 0.404. The area under the ROC curve was larger than the reference line. The diagnostic chart showed that the corresponding percentage was higher than the other. The decision tree model selected 9 important factors and ranked them by their power, among which mother of anemia (1.00) was the most important factor. Others were children's age (0.75), time of ablactation (0.53), mother's age (0.32), the time of egg supplementation (0.26), category of the project county (0.26), the time of milk supplementation (0.16), number of people in the family (0.13), the education status of the mother (0.12). Decision tree produced simple and easy rules that might be used to classify and predict in the same research. CONCLUSION: Decision tree could screen out the important factors of anemia and identify the cutting-points for factors. With the wide application of decision tree, it would exhibit important application values in the research of the rural children health care.
Subject(s)
Anemia/prevention & control , Decision Trees , Child, Preschool , Evaluation Studies as Topic , Humans , Rural Population , Sampling StudiesABSTRACT
OBJECTIVE: The study was to describe the breastfeeding status of children under the age of three in counties of western China and to provide evidence to the government for decision-making on intervention. METHODS: A cross-sectional study with probability-proportional-to-size (PPS) sampling method was used. The information on breastfeeding was obtained through memory of the mothers. Fourteen thousand and seventy-seven children were studied. Data on breastfed status in counties of western China was compared with those of the children from the survey of the counties of western China in 2001. RESULTS: The breastfeeding rate of children under 3 years old in western China was 96.5%. However, the overall breastfed rate of children under 6 months were only 33.4%, with rates of 11.4% and 22.0% on exclusively and predominantly breastfed groups respectively. Timely first-suckling rate was 43.5% with the continued breastfeeding rate (1 year) as 64.9%, but the continued breastfeeding rate (2 year) was only 9.7%. Reasons causing mothers to wean would include according to her own intention and to be able to attend the physical labor while exclusive breastfeeding under 6 months was for the growth and development of children, which might reduce the two-week prevalence of diarrhea. Major risks of exclusive breastfeeding of children under 6 months were seen as: level of education of the mothers, economic depression of the counties and mother's nationality (if as minority). CONCLUSION: Most of the children were ever or being breastfed at the time of interview with timely first-suckling took place earlier than in 2001. However continued breastfeeding did not last long. During these five years, the exclusive breastfeeding rate had been at low level, especially at the economic depression and the minority area.