Premium
Application of classification tree and logistic regression for the management and health intervention plans in a community‐based study
Author(s) -
Teng JuHsi,
Lin KuanChia,
Ho BinShenq
Publication year - 2007
Publication title -
journal of evaluation in clinical practice
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.737
H-Index - 73
eISSN - 1365-2753
pISSN - 1356-1294
DOI - 10.1111/j.1365-2753.2006.00747.x
Subject(s) - logistic regression , body mass index , medicine , demography , population , regression analysis , index (typography) , gerontology , statistics , environmental health , mathematics , computer science , sociology , world wide web
Background A community‐based aboriginal study was conducted and analysed to explore the application of classification tree and logistic regression. Methods A total of 1066 aboriginal residents in Yilan County were screened during 2003–2004. The independent variables include demographic characteristics, physical examinations, geographic location, health behaviours, dietary habits and family hereditary diseases history. Risk factors of cardiovascular diseases were selected as the dependent variables in further analysis. Results The completion rate for heath interview is 88.9%. The classification tree results find that if body mass index is higher than 25.72 kg m −2 and the age is above 51 years, the predicted probability for number of cardiovascular risk factors ≥3 is 73.6% and the population is 322. If body mass index is higher than 26.35 kg m −2 and geographical latitude of the village is lower than 24°22.8′, the predicted probability for number of cardiovascular risk factors ≥4 is 60.8% and the population is 74. As the logistic regression results indicate that body mass index, drinking habit and menopause are the top three significant independent variables. Conclusions The classification tree model specifically shows the discrimination paths and interactions between the risk groups. The logistic regression model presents and analyses the statistical independent factors of cardiovascular risks. Applying both models to specific situations will provide a different angle for the design and management of future health intervention plans after community‐based study.