@article{ART003159960},
author={kim kwang-Hwan},
title={A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis},
journal={The Journal of Transdisciplinary Studies},
issn={2586-5439},
year={2024},
volume={8},
number={3},
pages={369-384}
TY - JOUR
AU - kim kwang-Hwan
TI - A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis
JO - The Journal of Transdisciplinary Studies
PY - 2024
VL - 8
IS - 3
PB - The Society for Transdisciplinary Studies
SP - 369
EP - 384
SN - 2586-5439
AB - The purpose of this study is to examine the impact of subjects’ lifestyle habits on the risk of metabolic syndrome. The primary data used are the statistics from the 2022 Korea National Health & Nutrition Examination Survey (KNHANES), as published by the Korea Disease Control and Prevention Agency, with the survey period remaining consistent. The sampling method of KNHANES involves a two-stage stratified cluster sampling, where survey districts and households serve as the primary and secondary sampling units, respectively. In order to predict the ex planatory variables with health characteristics as the dependent variable, the study conducted a median correlation analysis or canonical correlation analysis using the Quantification Method II. Looking at general character istics, the age distribution was highest in the 34 years and younger group at 29.6%, followed by those 65 years and older at 26.6%, 50~64 years old at 24.0%, and the 35~49 years old group at 19.8%, the lowest distribution. As a result of canonical correlation analysis of the health characteristics, general characteristics, lifestyle characteristics, and meta bolic syndrome indicator characteristics of the men among the study subjects, 13 canonical functions were derived. Among them, four canon ical functions were found to be statistically significant (p<0.05, p<0.001).
As a result of canonical correlation analysis of women’s health character istics, general characteristics, lifestyle characteristics, and metabolic syn drome indicator characteristics, 13 canonical functions were derived.
Among them, four canonical functions were found to be statistically significant (p<0.05, p<0.001). The study results show that metabolic syndrome can be prevented and managed through a comprehensive ap proach that includes a balanced diet, regular exercise, strengthening public policies, and personal health management.
KW - Big data;Disease risk;Lifestyle;Metabolic syndrome;Prediction study
DO -
UR -
ER -
kim kwang-Hwan. (2024). A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis. The Journal of Transdisciplinary Studies, 8(3), 369-384.
kim kwang-Hwan. 2024, "A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis", The Journal of Transdisciplinary Studies, vol.8, no.3 pp.369-384.
kim kwang-Hwan "A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis" The Journal of Transdisciplinary Studies 8.3 pp.369-384 (2024) : 369.
kim kwang-Hwan. A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis. 2024; 8(3), 369-384.
kim kwang-Hwan. "A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis" The Journal of Transdisciplinary Studies 8, no.3 (2024) : 369-384.
kim kwang-Hwan. A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis. The Journal of Transdisciplinary Studies, 8(3), 369-384.
kim kwang-Hwan. A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis. The Journal of Transdisciplinary Studies. 2024; 8(3) 369-384.
kim kwang-Hwan. A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis. 2024; 8(3), 369-384.
kim kwang-Hwan. "A Study on Predicting the Risk of Metabolic Syndrome according to Lifestyle through Big Data Analysis" The Journal of Transdisciplinary Studies 8, no.3 (2024) : 369-384.
