Predicting Adolescent Response to School-Based Mindfulness

Can machine learning identify which adolescents will benefit more from school-based mindfulness training vs standard social-emotional education?In this secondary analysis of a cluster trial involving 8376 adolescents from 84 UK schools, machine learning identified a subgroup with statistically significant but clinically trivial differences in depressive symptom change. Specifically, adolescents predicted to benefit from mindfulness training based on their baseline characteristics did show significantly better outcomes if they received mindfulness, but the effect was negligible across comparisons.Despite the use of 2 complementary machine learning approaches in a large sample of adolescents, personalization indicated negligible clinical benefit, which underscores the challenges of achieving clinically impactful personalization in universal school-based prevention.

Corresponding Author: Christian A. Webb, PhD, Harvard Medical School and McLean Hospital, 115 Mill St, Belmont, MA 02478 (cwebb@mclean.harvard.edu).

Link to the article in your story

We encourage you to link out to this article in your story using the link below. It includes an access token that will give free access to the article for your readers up to one year after publication. (The link will be live after the article publishes and embargo is lifted.)

Please see the article for additional information, including full author list, author contributions and affiliations, conflict of interest and financial disclosures, and funding and support.

Need more information? Contact us.