Summary
Depression, anxiety, and stress are serious problems for teenagers and need tools that help doctors without replacing them. The authors created a challenge called AdoDAS that protects privacy by not sharing raw videos or audio but instead provides anonymous data and speech text. Many teams competed to use this data in two tasks: detecting these mental health issues and predicting detailed questionnaire answers. The best methods used smart ways to combine different types of information over time and understood how mental health questions relate. This work supports building AI tools that respect privacy while aiding mental health screening.
Adolescent mental healthDepression anxiety stress scale (DASS-21)Multimodal dataPrivacy preservationAutomated speech recognition (ASR)Binary classificationOrdinal predictionTemporal modelingMultimodal fusionPsychometrics
Authors
Zhaojie Luo, Junkun Wang, Tianhua Qi, Yuxuan Wu, Xin Zhao, Tetsuya Takiguchi, Tomoko Matsui, Kun Qian, Fei Wang, Shuqiong Wu, Zhengjun Yue, Hiroshi Ishiguro, Xinyuan Qian, Haizhou Li
Abstract
Adolescent depression, anxiety, and stress (D/A/S) call for scalable tools that complement, rather than replace, professional evaluation. Under a privacy-preserving policy, the AdoDAS Grand Challenge withholds minors' raw recordings and distributes anonymized audio-visual representations and ASR-derived text. Its 6,000 participants provide 24,000 segments across one scripted-reading and three open-response sessions. Two tracks assess multi-task binary D/A/S screening and ordinal prediction of 21 DASS-21 item responses. From 191 registrations, the final leaderboards included 95 eligible screening teams and 64 item-prediction teams. Audio-visual baselines achieved 0.4604 mean F1 and 0.2675 mean Quadratic Weighted Kappa; leading submissions reached 0.5921 and 0.2776. Representative systems emphasize cross-session modelling, temporal multimodal fusion, psychometric structure, and task-aware calibration.