The aim of the present study was to analyze the factors that affects the Endocrine Disorders in Korean elderly. Data were from the A Study on the Seoul Welfare Panel Study 2010. Subjects were 2111 persons (879 male, 1,232 female) aged 60 and older living in the community. Dependent variable was defined as prevalence of endocrine disorders. Explanatory variables were included as gender, level of education, household income, employment status, marital status, drinking, smoking, subjective reported body type, subjective health status, physical activity, experience of Stress, and depression. In the neural network algorithm analysis, level of education and subjective health status were significantly associated with endocrine disorders in Korean elderly. Based on this result, systematic programs are required in order to prevention of endocrine disorders.