Abstract Background The prevalence of mental health problems in adolescents is a global public health concern. Machine learning (ML) can analyse multidimensional data collected by phone sensors (passive tracking) and symptom self-reporting (active tracking) to model and predict mental health states. However, research in adolescents is lacking. This study investigated the feasibility of using ML to predict mental health in a non-clinical population of adolescents from active and passive data collected through the Mindcraft mobile app. Methods We recruited 103 secondary students (aged 14-18) who first completed the Strengths and Difficulties Questionnaire (SDQ) and then used the Mindcraft app for two weeks. The app integrates sensor data (location, steps, noise, light, battery, app usage) and self-reports. We extracted 85 sensor-based features and 19 from questionnaires to develop a gradient-boosted ensemble ML model. This model identifies students with abnormal SDQ scores and was evaluated using leave-one-out cross-validation. Results All students completed the active questionnaires; 67 also provided passive sensor data. 31 had abnormal SDQ scores. Using passive data, the ML model reached a balanced accuracy of 0.64 and an AUC score of 0.57. Incorporating both data types improved accuracy to 0.67 and AUC to 0.70. Feature importance scores showed step count and questionnaire on racing thoughts and hopefulness as most significant. Conclusions Our findings affirm the potential of integrating passive and active data collection to monitor mental health in real-world settings. Our ML model demonstrated moderate accuracy in predicting adolescents’ mental health risk measured with a behavioural screening questionnaire. This study will guide the development of a ML-driven, personalised mobile intervention for early symptom detection and mental health self-management, which might constitute an innovative and scalable tool for mental health prevention and intervention in adolescents. Key messages • This study shows the feasibility of using active and passive data to predict mental health risk in adolescents. • This study informs the development of a personalised machine learning-driven mobile intervention.