Scholarlink

<p>Adolescent Self-Injurious Behavior (SIB) is a significant global public health issue, with a lifetime prevalence rate of approximately 13.7%. As awareness of SIB rises, there is an urgent need for effective prediction mechanisms to enable early identification and intervention, reducing the risk of suicide and self-harm attempts. This study, grounded in Psychopathological Network Theory, uses machine learning and network analysis to explore the multidimensional structure of risk factors for adolescent SIB. A survey of 2047 adolescents aged 11 to 17 years in China analyzed 19 variables across physiological, psychological, and social domains. The Entropy Weight Method (EWM) was applied to combine network analysis and machine learning outcomes for a comprehensive risk evaluation. The study identified key risk factors for SIB, including loneliness, ADHD symptoms, Internet addiction, anxiety, depression, affinity for solitude, autistic traits, being bullied. These factors interact within a complex network structure, influencing the occurrence of SIB both directly and indirectly. The integration of EWM, network analysis, and machine learning provides a more precise risk assessment approach for adolescent SIB. The findings offer valuable insights into the causal mechanisms of SIB and emphasize the importance of targeted prevention and intervention strategies.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Entropy-based risk network identification in adolescent self-injurious behavior using machine learning and network analysis

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2025年8月20日

查看全文
  • Zheng Zhang,
  • Honghui Chen,
  • Yanyue Ye,
  • Hui Chen,
  • Huijuan Guo,
  • Jiansong Zhou

摘要

Adolescent Self-Injurious Behavior (SIB) is a significant global public health issue, with a lifetime prevalence rate of approximately 13.7%. As awareness of SIB rises, there is an urgent need for effective prediction mechanisms to enable early identification and intervention, reducing the risk of suicide and self-harm attempts. This study, grounded in Psychopathological Network Theory, uses machine learning and network analysis to explore the multidimensional structure of risk factors for adolescent SIB. A survey of 2047 adolescents aged 11 to 17 years in China analyzed 19 variables across physiological, psychological, and social domains. The Entropy Weight Method (EWM) was applied to combine network analysis and machine learning outcomes for a comprehensive risk evaluation. The study identified key risk factors for SIB, including loneliness, ADHD symptoms, Internet addiction, anxiety, depression, affinity for solitude, autistic traits, being bullied. These factors interact within a complex network structure, influencing the occurrence of SIB both directly and indirectly. The integration of EWM, network analysis, and machine learning provides a more precise risk assessment approach for adolescent SIB. The findings offer valuable insights into the causal mechanisms of SIB and emphasize the importance of targeted prevention and intervention strategies.