Predicting Adolescent Response to School-Based Mindfulness

Importance: Depression most commonly first emerges during adolescence, making early prevention critical. While school-based mindfulness training (SBMT) offers a scalable prevention approach with broad reach, evidence of its effectiveness is mixed, and there is a compelling case for a more personalized approach to prevention. Objective: To develop a data-driven algorithm from baseline characteristics to predict which adolescents are most likely to benefit from SBMT. Design, Setting, and Participants: The My Resilience in Adolescence (MYRIAD) cluster randomized clinical trial was conducted from October 2016 to July 2018. In this secondary analysis, school-level nested cross-validation was used to train and evaluate machine learning models for predicting individualized benefit from SBMT. Participants were students aged 11 to 13 years at baseline from broadly representative secondary schools across England, Scotland, Wales, and Northern Ireland. Data analysis was performed from April 2023 to October 2025. Interventions: SBMT teaching core mindfulness skills through psychoeducation, class discussion, and practices, compared with standard social-emotional learning (teaching as usual). Main Outcomes and Measures: Change in depressive symptoms from preintervention to postintervention measured by the Center for Epidemiologic Studies Depression scale. Causal forest (CF) and elastic net regression (ENR) models computed personalized advantage index scores quantifying individual expected benefit from SBMT vs teaching as usual. Results: Among 8376 adolescents from 84 UK secondary schools, the mean (SD) age at baseline was 12.2 (0.6) years; there were 4509 (54.9%) female participants and 3547 (43.2%) male participants. CF showed acceptable calibration (mean [SE] best linear predictor slope = 0.78 [0.15]), while ENR demonstrated modest predictive performance (r = 0.29; R2 = 0.09; root mean square error = 10.3). Both the CF and ENR models identified a subset of adolescents predicted to benefit from SBMT, but group differences in outcomes were negligible (CF: d = 0.07; 95% CI, 0.02-0.12; P = .007; ENR: d = 0.08; 95% CI, 0.02-0.13; P = .004). Top predictive features from the CF model were symptom severity (eg, low-to-moderate depression and anxiety predicted greater SBMT benefit) and several school factors with nonlinear patterns. ENR emphasized school-level characteristics with minimal differentiation. Conclusions and Relevance: This study found that machine learning identified a subgroup with statistically detectable but clinically trivial differential intervention response. These findings highlight the substantial challenges in achieving clinically useful personalization in universal school-based prevention programs. Trial Registration: isrctn.org Identifier: ISRCTN86619085.