Machine Learning Classifier for Reward Responsiveness in Adolescents
Author Information
Author(s): Robert James Richard Blair, Johannah Bashford-Largo, Ahria Dominguez, Matthew Dobbertin, Karina S. Blair, Sahil Bajaj
Primary Institution: Child and Adolescent Mental Health Center, Copenhagen University Hospital
Hypothesis
Can a machine learning classifier distinguish reward responsiveness in adolescents and its association with psychiatric symptoms?
Conclusion
The study found that adolescents with conduct disorder and ADHD show significant disruptions in reward responsiveness compared to typically developing peers.
Supporting Evidence
- Machine learning analysis identified a hyperplane with 80.77% accuracy.
- Adolescents with externalizing diagnoses showed significantly less normative reward responses.
- Deficient reward response was linked to higher symptoms of conduct disorder, major depressive disorder, and ADHD.
Takeaway
This study used a computer program to see how well teenagers respond to rewards compared to punishments, finding that some kids with mental health issues don't respond as well to rewards.
Methodology
The study used a Support Vector Machine (SVM) algorithm to analyze brain responses to rewards and punishments in adolescents.
Potential Biases
Potential biases due to the reliance on self-reported measures and the lack of structured diagnostic interviews.
Limitations
The study did not use structured diagnostic interviews, which may affect the reliability of the psychiatric diagnoses.
Participant Demographics
299 adolescents aged 10-19 years, with a mean age of 15.07 years, including 117 females.
Statistical Information
P-Value
<0.001
Statistical Significance
p<0.05
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website