A Predictive Model of Depression in Rural Elders-Decision Tree Analysis

ABSTRACT

PURPOSE: This descriptive study was done to develop a predictive model of depression in rural elders that will guide prevention and reduction of depression in elders. METHODS: A cross-sectional descriptive survey was done using face-to-face private interviews. Participants included in the final analysis were 461 elders (aged> or = 65 years). The questions were on depression, personal and environmental factors, body functions and structures, activity and participation. Decision tree analysis using the SPSS Modeler 14.1 program was applied to build an optimum and significant predictive model to predict depression in rural elders. RESULTS: From the data analysis, the predictive model for factors related to depression in rural elders presented with 4 path-ways. Predictive factors included exercise capacity, self-esteem, farming, social activity, cognitive function, and gender. The accuracy of the model was 83.7%, error rate 16.3%, sensitivity 63.3%, and specificity 93.6%. CONCLUSION: The results of this study can be used as a theoretical basis for developing a systematic knowledge system for nursing and for developing a protocol that prevents depression in elders living in rural areas, thereby contributing to advanced depression prevention for elders.