Search reports, ask a question, or jump to a page.
The problem
Intervention: Machine learning-based early warning model using the p factor and 23 predictors across individual, school, family, and societal domains to identify at-risk adolescents
Who it was tested with: 5,283 Chinese adolescents for model training and testing; 968 for external validation.
Experience from people who deliver programmes: stories, case studies and lessons learned. Valuable for understanding how and why, and for spotting what to test next, but not a measure of effect.
"Seven machine learning algorithms were tested using the p factor as the outcome" and "The XGBoost model showed the best performance (macro F1 = 0.73 on internal validation, 0.80 on external validation)." The study demonstrates that a machine learning approach can accurately identify at-risk adolescents but does not test whether this identification improves actual mental health outcomes through intervention.
Study does not evaluate whether the model-based identification actually leads to improved outcomes when interventions are delivered. External validation limited to Chinese population, generalisability unknown. No comparison to clinician judgement or existing screening tools.
Across countries and designs
1 study · 1 country
