The cross-sectional study of depressive symptoms and associated factors among adolescents by backpropagation neural network

• Published in: Public health (London) Vol. 208; pp. 52 - 58
• Main Authors: Lv, J., Guo, X., Meng, C., Fei, J., Ren, H., Zhang, Y., Qin, Z., Hu, Y., Yuan, T., Liang, L., Li, C., Yue, J., Gao, R., Song, Q., Zhao, X., Mei, S.
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier Ltd 01.07.2022
• Subjects: Adolescents; BP neural Network; Depressive symptoms; Diet behavior; Lifestyle behavior; BP neural Network; Depressive symptoms; Adolescents; Diet behavior; Lifestyle behavior
• ISSN: 0033-3506; 1476-5616
• DOI: 10.1016/j.puhe.2022.04.017

This study aimed to investigate the association between depressive symptoms and diet- and lifestyle-related behaviors among adolescents. Cross-sectional study. Our study used stratified random cluster sampling method to recruit 6,251 adolescents aged 11–19 years as samples for research and analysis. The Center for Epidemiological Studies Depression Scale was used to assess depressive symptoms. Chi-squared test, t test, and logistic regression were used to explore the diet and lifestyle factors of depressive symptoms. Backpropagation (BP) neural network model was used to investigate the ranking of diet and lifestyle behaviors factors of depressive symptoms. The prevalence of depressive symptoms among adolescents was 32.1%. Multivariable logistic regression was used to determine 10 important variables of depressive symptoms. After ranking the importance by BP neural network, the top three important variables were found, which were sleep duration (100%), screen time (49.1%), and breakfast (23.6%). Sleep duration, screen time, and breakfast were associated factors with the most significant impacts on depressive symptoms.