-
Identification of Dietary Factors Related to Hypertension, Diabetes, Hyperlipidemia, and Obesity using Neural Network.
-
Sim Yeol Lee, Hee Young Paik, Song Min Yoo, Hong Kyu Lee
-
Korean J Epidemiol. 1998;20(2):226-233.
-
-
-
Abstract
PDF
-
Abstract
This study was performed to find out nutritional factors associated with identification of chronic disease using neural network model. A dietary survey with 24-hour recall method was conducted together with a health survey including health qustionnaire, physical examination and glucose tolerance test to 2037 adults over 30 years of age in rural area of Korea. Subjects have been classified into groups with and without disease depending on each disease criteria(groups with desease include those who are newly diagnosed to have diabetes, hypertension, hyperlipidemia and obesity, respictively). Neural network method has been applied to predict disease using selected 3 nutrients out of 12 nutrient elements as input information and resulting outputs which designate either disease or without disease group. Backpropagation learning algorithm has been applied to train neural network structure assigning weight factors connecting each node. 20 subjects from both disease and without disease group have been collected to train neural network structure and remaining subjects were later used in order to test the validity of the trained structure. In order to quantify contrivution ratio of each nutrients for predictiong disease status, number of appearance frequency of each nutrients in the top 20 prediction rate has been compared. When a nutrient used 10 times for prediction, its appearance rate was calculated to be 50%. vitamin C, vitamin A and iron showed appearance rate of 70%, 40% and 30%, respectively for predicting diavetes. vitain C, Fat and beta-carotene showed appearance rate of 60%, 60% and 40% for predicting hypertension. For predicting hyperlipidemia, appearance rate of vitamin C, iron and energy was 65%, 55% and 30%, respectively. From the study, vitamin C was shown to be prominent in predicting chronic disease groups from subjects.
-
Summary
|