Psychosocial Factors Predict the Level of Substance Craving of People with Drug Addiction: A Machine Learning Approach

被引:4
|
作者
Gong, Hua [1 ]
Xie, Chuyin [1 ]
Yu, Chengfu [1 ,2 ]
Sun, Nan [1 ]
Lu, Hong [1 ,3 ]
Xie, Ying [1 ,4 ]
机构
[1] Guangzhou Univ, Sch Educ, Dept Psychol, Guangzhou 510006, Peoples R China
[2] Guangzhou Univ, Res Ctr Adolescent Psychol & Behav, Guangzhou 510006, Peoples R China
[3] Guangzhou Univ, Ctr Brain & Cognit Sci, Guangzhou 510006, Peoples R China
[4] Guangzhou Univ, Sch Publ Adm, Dept Sociol, Guangzhou 510006, Peoples R China
关键词
substance craving; life events; aggression behavior; impulsivity; gradient boosting method; ATTENTIONAL BIAS; FOREST-FIRE; ALCOHOL; STRESS; MODEL; ALEXITHYMIA; SYMPTOMS; MINDFULNESS; PERSONALITY; RESPONSES;
D O I
10.3390/ijerph182212175
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
This study aimed to explore which factors had a greater impact on substance craving in people with substance use and the direction of the impact. A total of 895 male substance users completed questionnaires regarding substance craving, psychological security, positive psychological capital, interpersonal trust, alexithymia, impulsivity, parental conflict, aggression behavior, life events, family intimacy, and deviant peers. Calculating the factor importance by gradient boosting method (GBM), found that the psychosocial factors that had a greater impact on substance craving were, in order, life events, aggression behavior, positive psychological capital, interpersonal trust, psychological security, impulsivity, alexithymia, family intimacy, parental conflict, and deviant peers. Correlation analysis showed that life events, positive psychological capital, interpersonal trust, psychological security, and family intimacy negatively predicted substance craving, while aggression behavior, impulsivity, alexithymia, parental conflict, and deviant peers positively predicted substance cravings. These findings have important implications for the prevention and intervention of substance craving behavior among substance users.
引用
收藏
页数:12
相关论文
共 50 条
  • [1] Psychosocial Factors Predict the Level of Aggression of People with Drug Addiction: A Machine Learning Approach
    Lu, Hong
    Xie, Chuyin
    Lian, Peican
    Yu, Chengfu
    Xie, Ying
    [J]. PSYCHOLOGY HEALTH & MEDICINE, 2022, 27 (05) : 1168 - 1175
  • [2] A Machine Learning Approach to Predict Volatile Substance Abuse for Drug Risk Analysis
    Nath, Priyanka
    Kilam, Sumran
    Swetapadma, Aleena
    [J]. 2017 THIRD IEEE INTERNATIONAL CONFERENCE ON RESEARCH IN COMPUTATIONAL INTELLIGENCE AND COMMUNICATION NETWORKS (ICRCICN), 2017, : 255 - 258
  • [3] A Comparative Machine Learning Study to Predict Drug Addiction in Bangladesh
    Alam, K. M. Rashedul
    Ahammed, Khair
    Rony, Mohammad Abu Tareq
    Ferdousi, Zannatul
    [J]. 2021 IEEE 15TH INTERNATIONAL CONFERENCE ON APPLICATION OF INFORMATION AND COMMUNICATION TECHNOLOGIES (AICT2021), 2021,
  • [4] An Intelligent Approach Using Machine Learning Techniques to Predict Flow in People
    Pegalajar, M. C.
    Ruiz, L. G. B.
    Perez-Moreiras, E.
    Boada-Grau, J.
    Serrano-Fernandez, M. J.
    [J]. BIG DATA AND COGNITIVE COMPUTING, 2023, 7 (02)
  • [5] Machine learning technology to help predict smartphone addiction
    Choi, Inyoung
    [J]. JOURNAL OF BEHAVIORAL ADDICTIONS, 2018, 7 : 54 - 55
  • [6] Proposing a Machine Learning Approach to Analyze and Predict Employment and its Factors
    Garcia-Penalvo, Francisco J.
    Cruz-Benito, Juan
    Martin-Gonzalez, Martin
    Vazquez-Ingelmo, Andrea
    Carlos Sanchez-Prieto, Jose
    Theron, Roberto
    [J]. INTERNATIONAL JOURNAL OF INTERACTIVE MULTIMEDIA AND ARTIFICIAL INTELLIGENCE, 2018, 5 (02): : 39 - 45
  • [7] Pattern of Intake and Drug Craving Predict the Development of Cocaine Addiction-like Behavior in Rats
    Belin, David
    Balado, Eric
    Piazza, Pier Vincenzo
    Deroche-Gamonet, Veronique
    [J]. BIOLOGICAL PSYCHIATRY, 2009, 65 (10) : 863 - 868
  • [8] Can machine learning predict drug nanocrystals?
    He, Yuan
    Ye, Zhuyifan
    Liu, Xinyang
    Wei, Zhengjie
    Qiu, Fen
    Li, Hai-Feng
    Zheng, Ying
    Ouyang, Defang
    [J]. JOURNAL OF CONTROLLED RELEASE, 2020, 322 : 274 - 285
  • [9] Using contextual factors to predict information security overconfidence: A machine learning approach
    Frank, Muriel
    Jaeger, Lennart
    Ranft, Lukas Manuel
    [J]. COMPUTERS & SECURITY, 2023, 125
  • [10] A machine learning approach to predict surgical learning curves
    Gao, Yuanyuan
    Kruger, Uwe
    Intes, Xavier
    Schwaitzberg, Steven
    De, Suvranu
    [J]. SURGERY, 2020, 167 (02) : 321 - 327