Abstract
Machine learning provides a method of identifying factors that discriminate between substance users and non-users potentially improving our ability to match need with available prevention services within context with limited resources. Our aim was to utilize machine learning to identify high impact factors that best discriminate between substance users and non-users among a national sample (N = 52,171) of Mexican children (i.e., 5th, 6th grade; Mage = 10.40, SDage = 0.82). Participants reported information on individual factors (e.g., gender, grade, religiosity, sensation seeking, self-esteem, perceived risk of substance use), socioecological factors (e.g., neighborhood quality, community type, peer influences, parenting), and lifetime substance use (i.e., alcohol, tobacco, marijuana, inhalant). Findings suggest that best friend and father illicit substance use (i.e., drugs other than tobacco or alcohol) and respondent sex (i.e., boys) were consistent and important discriminators between children who tried substances and those that did not. Friend cigarette use was a strong predictor of lifetime use of alcohol, tobacco, and marijuana. Friend alcohol use was specifically predictive of lifetime alcohol and tobacco use. Perceived danger of engaging in frequent alcohol and inhalant use predicted lifetime alcohol and inhalant use. Overall, findings suggest that best friend and father illicit substance use and respondent’s sex appear to be high impact screening questions associated with substance initiation during childhood for Mexican youths. These data help practitioners narrow prevention efforts by helping identify youth at highest risk.
Similar content being viewed by others
References
Baca-Garcia, E., Perez-Rodriguez, M. M., Saiz-Gonzalez, D., Basurte-Villamor, I., Saiz-Ruiz, J., Leiva-Murillo, J. M., et al. (2007). Variables associated with familial suicide attempts in a sample of suicide attempters. Progress in Neuro-Psychopharmacology and Biological Psychiatry, 31, 1312–1316. https://doi.org/10.1016/j.pnpbp.2007.05.019.
Barrett, T. S., & Lockhart, G. (2018). Efficient exploration of many variables and interactions using regularized regression. Prevention Science, 20, 575–584. https://doi.org/10.1007/s11121-018-0963-9.
Borges, G., Medina-Mora, M. E., Orozco, R., Fleiz, C., Villatoro, J., Rojas, E., & Zemore, S. (2009). Unmet needs for treatment of alcohol and drug use in four cities in Mexico. Salud Mental, 32, 327–333.
Breiman, L. (2001). Statistical modeling: The two cultures (with comments and a rejoinder by the author). Statistical Science, 16, 199–231. https://doi.org/10.1214/ss/1009213726.
Bronfenbrenner, U. (1977). Toward an experimental ecology of human development. American Psychologist, 32, 513–531. https://doi.org/10.1037/0003-066X.32.7.513.
Burdzovic Andreas, J., & Watson, M. W. (2016). Person-environment interactions and adolescent substance use: The role of sensation seeking and perceived neighborhood risk. Journal of Child & Adolescent Substance Abuse, 25, 438–447. https://doi.org/10.1080/1067828X.2015.1066722.
Chollet, F., & Allaire, J. J. (2018). Deep learning with R (1st ed.). Shelter Island: Manning Publications. https://doi.org/10.1109/18.796380.
Drinovac, M., Wagner, H., Agrawal, N., Cock, H. R., Mitchell, A. J., & von Oertzen, T. J. (2015). Screening for depression in epilepsy: A model of an enhanced screening tool. Epilepsy and Behavior, 44, 67–72. https://doi.org/10.1016/j.yebeh.2014.12.014.
Enders, C. K. (2010). Applied missing data analysis. New York: Guilford Press.
Friese, B., & Grube, J. (2008). Differences in drinking behavior and access to alcohol between native American and white adolescents. Journal of Drug Education, 38, 273–284.
Gilliard-Matthews, S., Stevens, R., Nilsen, M., & Dunaev, J. (2015). “You see it everywhere. It’s just natural.”: Contextualizing the role of peers, family, and neighborhood in initial substance use. Deviant Behavior, 36, 492–509. https://doi.org/10.1080/01639625.2014.944068.
Hastie, T., Tibshirani, R., & Friedman, J. (2009). The elements of statistical learning. The mathematical intelligencer. New York: Guilford Press.
Hosmer, D. W., & Lemeshow, S. (2000). Applied logistic regression. New York: Wiley.
Hussong, A. (2002). Differing peer contexts and risk for adolescent substance use. Journal of Youth and Adolescence, 31, 207–220.
James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An introduction to statistical learning. New York: Springer. https://doi.org/10.1007/978-1-4614-7138-7.
Johnston, L. D., Miech, R. A., O’malley, P. M., Bachman, J. G., Schulenberg, J. E., & Patrick, M. E. (2018). Monitoring the Future national survey results on drug use: 1975-2017: Overview, key findings on adolescent drug use. Ann Arbor. Institute for Social Research Retrieved from: https://eric.ed.gov/?id=ED589762.
Kliewer, W., & Murrelle, L. (2007). Risk and protective factors for adolescent substance use: Findings from a study in selected Central American countries. Journal of Adolescent Health, 40, 448–455. https://doi.org/10.1016/j.jadohealth.2006.11.148.
Kuhn, M., & Johnson, K. (2013). Applied predictive modeling. New York: Springer.
Lehmann, E. L., & Romano, J. P. (2012). Generalizations of the familywise error rate. In In Selected Works of EL Lehmann (33rd ed., pp. 719–735). Boston: Springer. https://doi.org/10.1007/978-1-4614-1412-4.
Li, Y., & Lerner, R. M. (2011). Trajectories of school engagement during adolescence: Implications for grades, depression, delinquency, and substance use. Developmental Psychology, 47, 233–247. https://doi.org/10.1037/a0021307.
Li, C., Pentz, M. A., & Chou, C. P. (2002). Parental substance use as a modifier of adolescent substance use risk. Addiction, 97, 1537–1550.
Luthar, S. S., Small, P. J., & Ciciolla, L. (2018). Adolescents from upper middle class communities: Substance misuse and addiction across early adulthood. Development and Psychopathology, 30, 315–335.
Marinić, I., Supek, F., Kovačić, Z., Rukavina, L., Jendričko, T., & Kozarić-kovačić, D. (2007). Clinical science posttraumatic stress disorder : Diagnostic data analysis by data mining methodology. Croatian Medical Journal, 48, 185–197. https://doi.org/10.1007/s10238-014-0316-3.
Marsiglia, F. F., Booth, J. M., Ayers, S. L., Nuño-Gutierrez, B. L., Kulis, S., & Hoffman, S. (2014). Short-term effects on substance use of the keepin’ it REAL pilot prevention program: Linguistically adapted for youth in Jalisco, Mexico. Prevention Science, 15, 694–704. https://doi.org/10.1007/s11121-013-0421-7.
Messler, E. C., Quevillon, R. P., & Simons, J. S. (2014). The effect of perceived parental approval of drinking on alcohol use and problems. Journal of Alcohol and Drug Education, 58, 44–59.
Mohr, D. C., Burns, M. N., Schueller, S. M., Clarke, G., & Klinkman, M. (2013). Behavioral intervention technologies: Evidence review and recommendations for future research in mental health. General Hospital Psychiatry, 35, 332–338.
Olds, R. S., & Thombs, D. L. (2001). The relationship of adolescent perceptions of peer norms and parent involvement to cigarette and alcohol use. Journal of School Health, 71, 223–228.
Patterson, G. R. (2005). The next generation of PMTO models. The Behavior Therapist, 28, 27–33.
Paulson, M. J., Coombs, R. H., & Richardson, M. A. (1990). School performance, academic aspirations, and drug use among children and adolescents. Journal of Drug Education, 20, 289–303.
Rahman, M. M., & Davis, D. N. (2013). Machine learning-based missing value imputation method for clinical datasets. In G.-C. Yang, S.-L. Ao, & L. Gelman (Eds.), IAENG transactions on engineering technologies (pp. 245–257). Dordrecht: Springer. https://doi.org/10.1007/978-94-007-6818-5.
Riley, A. W. (2004). Evidence that school-age children can self-report on their health. Ambulatory Pediatrics, 4, 371–376. https://doi.org/10.1367/A03-178R.1.
Rosenberg, M. (1965). Society and the adolescent self-image. Princeton: Princeton University Press.
Rossi, A., Amaddeo, F., Sandri, M., & Tansella, M. (2005). Determinants of once-only contact in a community-based psychiatric service. Social Psychiatry and Psychiatric Epidemiology, 40, 50–56. https://doi.org/10.1007/s00127-005-0845-x.
Sargent, J. D., Tanski, S., Stoolmiller, M., & Hanewinkel, R. (2010). Using sensation seeking to target adolescents for substance use interventions. Addiction, 105, 506–514. https://doi.org/10.1111/j.1360-0443.2009.02782.x.
Secretariado Ejecutivo del Sistema Nacional de Seguridad Pública ([SESNSP] 2018). Incidencia delictiva del Fuero Común, nueva metodología. Retrived from: https://www.gob.mx/sesnsp/acciones-y-programas/incidencia-delictiva-del-fuero-comun-nueva-metodologia
Shelton, K. K., Frick, P. J., & Wootton, J. (1996). Assessment of parenting practices in families of elementary school-age children. Journal of Clinical Child Psychology, 25, 317–329. https://doi.org/10.1207/s15374424jccp2503_8.
Shillington, A. M., & Clapp, J. D. (2000). Self-report stability of adolescent substance use: Are there differences for gender, ethnicity and age? Drug & Alcohol Dependence, 60, 19–27. https://doi.org/10.1016/s0376-8716(99)00137-4.
Substance Abuse and Mental Health Services Administration. (2017). Key substance use and mental health indicators in the United States: Results from the 2016 National Survey on Drug Use and Health (HHS Publication No. SMA 17-5044, NSDUH Series H-52). Rockville, MD: Center for Behavioral Health Statistics and Quality, Substance Abuse and Mental Health Services Administration. Retrieved from https://www.samhsa.gov/data/.
United Nations Office on Drugs and Crime. (2018). World Drug Report 2018. Retrieved from https://www.unodc.org/wdr2018
Varni, J. W., Limbers, C. A., & Burwinkle, T. M. (2007). How young can children reliably and validly self-report their health-related quality of life?: An analysis of 8,591 children across age subgroups with the PedsQL™ 4.0 Generic Core Scales. Health and Quality of Life Outcomes, 5, 1–13. https://doi.org/10.1186/1477-7525-5-1.
Vázquez, A. L., Domenech Rodríguez, M. M., Schwartz, S. E., Amador Buenabad, N. G., Bustos, M., Gutierrez, M., & Villatoro Velazquez J. A. (2019a). Early adolescent substance use in a national sample of Mexican youths: Demographic characteristics that predict use of alcohol, tobacco, and other drugs. Journal of Latinx Psychology. 7, 273–283
Vázquez, A. L., Domenech Rodríguez, M. M., Amador Buenabad, N. G., Bustos, M., Gutierrez, M., & Villatoro Velazquez J. A. (2019b). Addictive Behaviors, 97, 97–103.
Villatorro Velázquez, J. A., Medina-Mora Icaza, M. E., Sánchez, R., Fregoso Ito, D. A., Bustons Gamiño, M. N., Escobar, E., … Martínez, V. (2016). El consumo de drogas en estudiantes de México: Tendencias y magnitud del problema. Salud Mental, 39, 193–203. https://doi.org/10.17711/SM.0185-3325.2016.023
Villatorro Velázquez, J. A., Bustos Gamiño, M. N., Fregoso Ito, D. A., Fleiz Bautista, C., de Lourdes Guitierrez López, M., Amador Buenabad, N. G., & Medina-Mora Icaza, M. E. (2017). Contextual factors associated with marijuana use in school population. Salud Mental, 40, 93–101. https://doi.org/10.17711/SM.0185-3325.2017.012.
Wadolowski, M., Hutchinson, D., Bruno, R., Aiken, A., Najman, J. M., Kypri, K., et al. (2016). Parents who supply sips of alcohol in early adolescence: A prospective study of risk factors. Pediatrics, 137, 1–8. https://doi.org/10.1542/peds.2015-2611.
World Bank (2019). Poverty and Equity Data Portal: Mexico. Retrieved from: http://povertydata.worldbank.org/poverty/country/MEX
Wymbs, B. T., McCarty, C. A., Mason, W. A., King, K. M., Baer, J. S., Vander Stoep, A., & McCauley, E. (2014). Early adolescent substance use as a risk factor for developing conduct disorder and depression symptoms. Journal of Studies on Alcohol and Drugs, 75, 279–289.
Zamboanga, B. L., Schwartz, S. J., Jarvis, L. H., & Van Tyne, K. (2009). Acculturation and substance use among hispanic early adolescents: Investigating the mediating roles of acculturative stress and self-esteem. Journal of Primary Prevention, 30, 315–333. https://doi.org/10.1007/s10935-009-0182-z.
Funding
This research was supported by funding from Comisión Nacional contra las Adicciones (2013–2015) to the National Institute of Psychiatry Ramón de la Fuente Muñíz (Villatoro Velázquez, PI).
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interest
The authors have declare that they have conflict of interest.
Ethical Approval
Approval to perform analyses on the archived, deidentified data was obtained from the Institutional Review Board at [masked for peer review]. Approval for the parent project was obtained from [masked for peer review]. All research activities were performed in accordance with the ethical standards articulated in the 1964 Declaration of Helsinki, its later amendments, and the 1979 Belmont Report.
Informed Consent
The Secretary of Public Education in Mexico provided the ENCODE team consent to survey students. Active parental consent was not obtained as the Secretary of Public Education provided the consent to survey students. Student accented to participation prior to the administration of the survey and those that did not want to participate could chose to do so.
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Vázquez, A.L., Domenech Rodríguez, M.M., Barrett, T.S. et al. Innovative Identification of Substance Use Predictors: Machine Learning in a National Sample of Mexican Children. Prev Sci 21, 171–181 (2020). https://doi.org/10.1007/s11121-020-01089-4
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11121-020-01089-4