AdoDAS: A Privacy-Preserving Multimodal Challenge for Adolescent Depression, Anxiety, and Stress Assessment

Zhaojie Luo; Junkun Wang; Tianhua Qi; Yuxuan Wu; Xin Zhao; Tetsuya Takiguchi; Tomoko Matsui; Kun Qian

cs.MMSep 7, 2026

AdoDAS: A Privacy-Preserving Multimodal Challenge for Adolescent Depression, Anxiety, and Stress Assessment

Authors: Zhaojie Luo, Junkun Wang, Tianhua Qi, Yuxuan Wu, Xin Zhao, Tetsuya Takiguchi, Tomoko Matsui, Kun Qian, +6 more

Organizations: Southeast University · Shenzhen Loop Area Institute · Southeast University Nanjing, Jiangsu, China · Shenzhen Loop Area Institute Shenzhen, China · Kobe University · Kobe University Kobe, Japan · Beijing Institute of Technology · Beijing Institute of Technology Beijing, China · Nanjing Medical University · Nanjing Medical University Nanjing, China · The University of Osaka · The University of Osaka Osaka, Japan · University of Science and Technology Beijing · University of Science and Technology Beijing Beijing, China · The Chinese University of Hong Kong · The Chinese University of Hong Kong (Shenzhen) Shenzhen, China

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.

Figures & tables

Figure 1. AdoDAS split sizes, D/A/S prevalence, DASS-21 subscale means (whiskers: one standard deviation), and item-response distributions. Four panels show split sizes, D/A/S prevalence, DASS-21 subscale means, and item-response distributions.

Track	Input	Primary	Tie-break
A1	Audio	F1 .3959	AUROC .6500
A1	Video	F1 .4093	AUROC .6749
A1	Audio+Video	F1 .4604	AUROC .7169
A2	Audio	QWK .1260	MAE .5675
A2	Video	QWK .1758	MAE .4700
A2	Audio+Video	QWK .2675	MAE .4679

Table 1. Official hidden-test baselines.

System	F1 $\uparrow$	AUROC $\uparrow$	QWK $\uparrow$	MAE $\downarrow$
Organizer A+V	.4604	.7169	.2675	.4679
HITSZ_HLT	.5921	.7652	.2740	.4392
ustc-ac	.5853	.8019	–	–
cog-simulation	.4747	.7051	–	–
HEALTH FIRST	.4710	.7320	.2776	.4807
Ritsumei	.4665	.7282	.2717	.4695

Table 2. Organizer baseline and leading hidden-test results.

Team	System characteristics
HITSZ_HLT	Cross-session Transformer; frame-level A–V attention; session-aware ASR-text adaptation; A1-guided item correction; staged task-head adjustment.
HEALTH FIRST	Dual Conformers; cross-session fusion; query-aligned 21-item CORAL heads; validation-selected item experts.
Ritsumei	DynaBridge multimodal/semantic summaries; item-to-D/A/S reconstruction; confidence-aware item refinement.

Table 3. Representative high-performing systems.

Explore similar work

DynaBridge: Dynamic Summary-Guided Cross-Task Multimodal Fusion for DASS-Structured Mental Health Assessment
Jul 28, 2026Shiyu Teng, Haichen Yu, Jiaqing Liu +6Medical Diagnosis Depression Severity Estimation
College of Information Science and Engineering Ritsumeikan University Ibaraki, Osaka, Japan · College of Computer Science and Technology Zhejiang University Hangzhou, Zhejiang, China
A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks
May 13, 2026Takehiro Ishikawa, Jon DukeDepression Detection Mental Health
College of Computing, Georgia Institute of Technology, Atlanta, GA, USA · Georgia Tech Research Institute, Georgia Institute of Technology, Atlanta, GA, USA
InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Information-Theoretic Optimization
Jun 4, 2026Xueyang Wu, Siyuan Liu, Kezhuo Yang +1Audio Representation Learning Depression Detection
Shenzhen NeurStar Inc., China · University of York, United Kingdom · Shanghai Jiao Tong University, China

Jul 28, 2026J/K move · Enter open · S save

DynaBridge: Dynamic Summary-Guided Cross-Task Multimodal Fusion for DASS-Structured Mental Health Assessment

Shiyu Teng, Haichen Yu, Jiaqing Liu, Hao Sun+5

College of Information Science and Engineering Ritsumeikan University Ibaraki, Osaka, Japan · College of Computer Science and Technology Zhejiang University Hangzhou, Zhejiang, China

Medical Diagnosis Depression Severity Estimation Multimodal Fusion

Open paper AskPDF arXiv

Multimodal behavioral analysis offers a scalable approach to assessing depression, anxiety, and stress, yet generic fusion models often ignore the psychometric structure of questionnaire labels. In DASS-21, risk labels are derived from ordered symptom items through fixed item-to-subscale mappings. We propose DynaBridge, a dynamic summary-guided cross-task multimodal framework for DASS-structured mental health assessment. DynaBridge encodes acoustic, visual, and textual cues across multiple sessions and augments them with frozen-LLM-generated DASS-aware summaries as participant-level semantic evidence. It predicts ordinal item distributions, reconstructs depression, anxiety, and stress risk evidence from item-level soft scores, and fuses this evidence with direct multimodal risk predictions. A confidence-aware refinement strategy further incorporates high-confidence semantic cues conservatively. On the official AdoDAS validation split, DynaBridge outperforms the official baseline and representative multimodal methods, achieving 0.5012 mean F1 for D/A/S risk prediction and 0.3216 mean QWK for DASS-21 item prediction. These results show the value of bridging multimodal cues, semantic summaries, and DASS-21 psychometric structure.

Abstract

Explore similar work

DynaBridge: Dynamic Summary-Guided Cross-Task Multimodal Fusion for DASS-Structured Mental Health Assessment

A Multi-Probe Audit of Clinical-Interview Depression Detection Benchmarks

InfoShield: Privacy-Preserving Speech Representations for Mental Health Screening via Information-Theoretic Optimization