Predicting Adolescent Mental Health Outcomes Across Cultures: A Machine Learning Approach.

Abstract

Adolescent mental health problems are rising rapidly around the world. To combat this rise, clinicians and policymakers need to know which risk factors matter most in predicting poor adolescent mental health. Theory-driven research has identified numerous risk factors that predict adolescent mental health problems but has difficulty distilling and replicating these findings. Data-driven machine learning methods can distill risk factors and replicate findings but have difficulty interpreting findings because these methods are atheoretical. This study demonstrates how data- and theory-driven methods can be integrated to identify the most important preadolescent risk factors in predicting adolescent mental health. Machine learning models examined which of 79 variables assessed at age 10 were the most important predictors of adolescent mental health at ages 13 and 17. These models were examined in a sample of 1176 families with adolescents from nine nations. Machine learning models accurately classified 78% of adolescents who were above-median in age 13 internalizing behavior, 77.3% who were above-median in age 13 externalizing behavior, 73.2% who were above-median in age 17 externalizing behavior, and 60.6% who were above-median in age 17 internalizing behavior. Age 10 measures of youth externalizing and internalizing behavior were the most important predictors of age 13 and 17 externalizing/internalizing behavior, followed by family context variables, parenting behaviors, individual child characteristics, and finally neighborhood and cultural variables. The combination of theoretical and machine-learning models strengthens both approaches and accurately predicts which adolescents demonstrate above average mental health difficulties in approximately 7 of 10 adolescents 3-7 years after the data used in machine learning models were collected.

Department

Description

Provenance

Citation

Published Version (Please cite this version)

10.1007/s10964-023-01767-w

Publication Info

Rothenberg, W Andrew, Andrea Bizzego, Gianluca Esposito, Jennifer E Lansford, Suha M Al-Hassan, Dario Bacchini, Marc H Bornstein, Lei Chang, et al. (2023). Predicting Adolescent Mental Health Outcomes Across Cultures: A Machine Learning Approach. Journal of youth and adolescence. pp. 1–25. 10.1007/s10964-023-01767-w Retrieved from https://hdl.handle.net/10161/27271.

This is constructed from limited available data and may be imprecise. To cite this article, please review & use the official citation provided by the journal.

Scholars@Duke

Rothenberg

W. Andrew Rothenberg

Research Scientist

Drew Rothenberg joined the Center for Child and Family Policy as a postdoctoral associate in September 2018 and now works as a Research Scientist at the Center. His research is focused on the development of adaptive and maladaptive parenting practices and family processes across ontogeny, culture and generations. Utilizing a developmental psychopathology framework, he examines how parenting practices, family dynamics, and evidence-based mental health interventions affect normal and abnormal child development. His program of research has three aims. First, he explores how maladaptive family processes can be passed from one generation to the next. Second, he identifies strategies to prevent the intergenerational transmission of these processes in different culture contexts. Third, he implements these preventative interventions in medically underserved communities that need them the most.

He currently works on the Childhood Risk Factors and Young Adult Competence project, funded by the Eunice Kennedy Shriver National Institute of Child Health and Human Development, as part of the Parenting Across Cultures research team.

Lansford

Jennifer Lansford

S. Malcolm Gillis Distinguished Research Professor of Public Policy

Jennifer Lansford is the director of the Center for Child and Family Policy and S. Malcolm Gillis Distinguished Research Professor of Public Policy in the Sanford School of Public Policy.

Dr. Lansford's research focuses on the development of aggression and other behavior problems in youth, with an emphasis on how family and peer contexts contribute to or protect against these outcomes. She examines how experiences with parents (e.g., physical abuse, discipline, divorce) and peers (e.g., rejection, friendships) affect the development of children's behavior problems, how influence operates in adolescent peer groups, and how cultural contexts moderate links between parenting and children's adjustment.

Dodge

Kenneth A. Dodge

William McDougall Distinguished Professor of Public Policy Studies

Kenneth A. Dodge is the William McDougall Distinguished Professor of Public Policy and Professor of Psychology and Neuroscience at Duke University. He is also the founding and past director of the Center for Child and Family Policy, as well as the founder of Family Connects International

Dodge is a leading scholar in the development and prevention of aggressive and violent behaviors. His work provides a model for understanding how some young children grow up to engage in aggression and violence and provides a framework for intervening early to prevent the costly consequences of violence for children and their communities.

Dodge joined the faculty of the Sanford School of Public Policy in September 1998. He is trained as a clinical and developmental psychologist, having earned his B.A. in psychology at Northwestern University in 1975 and his Ph.D. in psychology at Duke University in 1978. Prior to joining Duke, Dodge served on the faculty at Indiana University, the University of Colorado, and Vanderbilt University.

Dodge's research has resulted in the Family Connects Program, an evidence-based, population health approach to supporting families of newborn infants. Piloted in Durham, NC, and formerly known as Durham Connects, the program attempts to reach all families giving birth in a community to assess family needs, intervene where needed, and connect families to tailored community resources. Randomized trials indicate the program's success in improving family connections to the community, reducing maternal depression and anxiety, and preventing child abuse. The model is currently expanding to many communities across the U.S.

Dodge has published more than 500 scientific articles which have been cited more than 120,000 times.

Elected into the National Academy of Medicine in 2015, Dodge has received many honors and awards, including the following:

  • President (Elected), Society for Research in Child Development
  • Fellow, Society for Prevention Research
  • Distinguished Scientist, Child Mind Institute
  • Research Scientist Award from the National Institutes of Health
  • Distinguished Scientific Award for Early Career Contribution from the American Psychological Association
  • J.P. Scott Award for Lifetime Contribution to Aggression Research from the International Society for Research on Aggression
  • Science to Practice Award from the Society for Prevention Research
  • Inaugural recipient of the “Public Service Matters” Award from the Network of Schools of Public Policy, Affairs and Administration
  • Inaugural recipient of the Presidential Citation Award for Excellence in Research from the Society for Research on Adolescence

Unless otherwise indicated, scholarly articles published by Duke faculty members are made available here with a CC-BY-NC (Creative Commons Attribution Non-Commercial) license, as enabled by the Duke Open Access Policy. If you wish to use the materials in ways not already permitted under CC-BY-NC, please consult the copyright owner. Other materials are made available here through the author’s grant of a non-exclusive license to make their work openly accessible.