{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T04:27:45Z","timestamp":1787027265548,"version":"build-2736575974"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T00:00:00Z","timestamp":1771891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100018563","name":"Social Science Planning Project of Shandong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100018563","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008279","name":"Ludong University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008279","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Psychiatry"],"abstract":"<jats:sec>\n                    <jats:title>Background and objectives<\/jats:title>\n                    <jats:p>Adolescent depression and anxiety are becoming increasingly prevalent in China, with rates reaching 20%\u201330%, driven largely by intense academic pressure and the cultural tendency toward somatization. Traditional screening tools, such as the Patient Health Questionnaire-9 (PHQ-9) and Generalized Anxiety Disorder-7 (GAD-7), often suffer from subjective bias, recall errors, and underreporting due to social stigma. This study developed an AI-based intelligent diagnosis system (IDS) using multitask deep learning to non-intrusively predict comorbid depression and anxiety severity based on the spontaneous textual expressions of Chinese adolescents.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Textual responses from approximately 1,275 adolescents were collected and labeled with clinician-assessed PHQ-9 and GAD-7 scores. Preprocessing involved jieba segmentation and variational autoencoder (VAE)-based data augmentation to address class imbalance, resulting in an expanded test set of 308 samples. The IDS architecture utilizes a Chinese-optimized BERT encoder with self-attention and dual-feature fusion (combining pooled [CLS] tokens and global pooling) to extract shared representations. These are processed through multitask heads for regression (MSE loss) and classification (weighted cross-entropy). The model was trained using an 8:1:1 split with AdamW optimization, cosine annealing, and regularization, supported by ablation studies to validate individual components.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>On the test set, the IDS achieved Pearson correlation coefficients of 0.706 for PHQ-9 and 0.693 for GAD-7, with AUC values of 0.877 and 0.902, respectively. Binary classification yielded F1-scores of 0.762 (PHQ-9) and 0.863 (GAD-7). Ablation analysis confirmed that the multitask learning framework improved F1-scores by 6.2%\u20137.8% and reduced MSE by 14.2%\u201318.4%. Furthermore, adaptations for somatization and data augmentation for severe cases significantly enhanced the system\u2019s sensitivity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The IDS offers a robust, culturally sensitive, and scalable tool for adolescent mental health screening. By outperforming single-task baselines, it provides a proactive, privacy-preserving alternative to traditional self-reports. Future research will focus on longitudinal validation, multimodal integration, and ethical deployment strategies to maximize the system\u2019s utility in educational and clinical settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpsyt.2026.1752423","type":"journal-article","created":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T10:31:19Z","timestamp":1771929079000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["An AI-based intelligent diagnosis system for adolescent mental health based on multitask deep learning"],"prefix":"10.3389","volume":"17","author":[{"given":"Wenyue","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Physical Education, Yantai Institute of Science and Technology","place":["Yantai, China"]},{"name":"Faculty of Education, Universiti Kebangsaan Malaysia","place":["Bangi, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Faculty of Education, Universiti Kebangsaan Malaysia","place":["Bangi, Malaysia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linkang","family":"Du","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Xi\u2019an Jiaotong University","place":["Xi\u2019an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianguo","family":"Qiu","sequence":"additional","affiliation":[{"name":"Faculty of Physical Education, Ludong University","place":["Yantai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,2,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.1001\/jamapediatrics.2021.2482","article-title":"Global prevalence of depressive and anxiety symptoms in children and adolescents during covid-19: A meta-analysis","volume":"175","author":"Racine","year":"2021","journal-title":"JAMA Pediatr"},{"key":"B2","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1111\/bjc.12333","article-title":"Global prevalence of depression and elevated depressive symptoms among adolescents: A systematic review and meta-analysis","volume":"61","author":"Shorey","year":"2022","journal-title":"Br J Clin Psychol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2024.03.074","article-title":"Global burden of depression or depressive symptoms in children and adolescents: a systematic review and meta-analysis","volume":"354","author":"Lu","year":"2024","journal-title":"Journal of affective disorders"},{"key":"B4","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1186\/s13034-024-00841-w","article-title":"Prevalence of depressive symptoms among children and adolescents in China: a systematic review and meta-analysis","volume":"18","author":"Zhou","year":"2024","journal-title":"Child Adolesc Psychiatry Ment Health"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2022.e10117","article-title":"Prevalence of anxiety symptoms among Chinese university students amid the covid-19 pandemic: A systematic review and meta-analysis","volume":"8","author":"Wang","year":"2022","journal-title":"Heliyon"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1038\/s41380-021-01161-7","article-title":"Age at onset of mental disorders worldwide: large-scale meta-analysis of 192 epidemiological studies","volume":"27","author":"Solmi","year":"2022","journal-title":"Mol Psychiatry"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.2147\/JMDH.S104807","article-title":"Information bias in health research: definition, pitfalls, and adjustment methods","volume":"9","author":"Althubaiti","year":"2016","journal-title":"J Multidiscip Healthcare"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1001\/jama.2017.11295","article-title":"Digital phenotyping: technology for a new science of behavior","volume":"318","author":"Insel","year":"2017","journal-title":"JAMA"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1002\/wps.20883","article-title":"The growing field of digital psychiatry: current evidence and the future of apps, social media, chatbots, and virtual reality","volume":"20","author":"Torous","year":"2021","journal-title":"World Psychiatry"},{"key":"B10","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1007\/s11920-022-01358-9","article-title":"Digital phenotyping for mental health: reviewing the challenges of using data to monitor and predict mental health problems","volume":"24","author":"Birk","year":"2022","journal-title":"Current psychiatry reports"},{"key":"B11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-022-00553-5","article-title":"Digital biomarkers of mood disorders and symptom change","volume":"5","author":"Jacobson","year":"2022","journal-title":"NPJ Digital Med"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1007\/BF00051427","article-title":"Neurasthenia and depression: A study of somatization and culture in China","volume":"6","author":"Kleinman","year":"1982","journal-title":"Culture Med Psychiatry"},{"key":"B13","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.psc.2011.11.006","article-title":"Depression in cultural context: \u201cChinese somatization,\u201d revisited","volume":"35","author":"Ryder","year":"2012","journal-title":"Psychiatr Clinics North America"},{"key":"B14","doi-asserted-by":"publisher","first-page":"e103860","DOI":"10.1136\/bmjopen-2025-103860","article-title":"Association between somatic symptoms and depression and anxiety in adolescents: a cross-sectional school-based study","volume":"15","author":"Lu","year":"2025","journal-title":"BMJ Open"},{"key":"B15","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1080\/02673843.2019.1590851","article-title":"A systematic review: the influence of social media on depression, anxiety and psychological distress in adolescents","volume":"25","author":"Keles","year":"2020","journal-title":"Int J Adolescence Youth"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00589-7","article-title":"Natural language processing applied to mental illness detection: a narrative review","volume":"5","author":"Zhang","year":"2022","journal-title":"NPJ Digital Med"},{"key":"B17","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1007\/s11920-019-1094-0","article-title":"Artificial intelligence for mental health and mental illnesses: an overview","volume":"21","author":"Graham","year":"2019","journal-title":"Curr Psychiatry Rep"},{"key":"B18","article-title":"Mentalbert: Publicly available pretrained language models for mental healthcare","author":"Ji","year":"2022"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2021.716298","article-title":"Mental health analysis using deep learning: a survey","volume":"12","author":"Iyortsuun","year":"2021","journal-title":"Front Psychiatry"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1111\/jcpp.13758","article-title":"Artificial intelligence in mental health: a review of applications in adolescents","volume":"64","author":"Andrew","year":"2023","journal-title":"J Child Psychol Psychiatry"},{"key":"B21","doi-asserted-by":"publisher","first-page":"293","DOI":"10.1111\/j.1468-2850.2010.01221.x","article-title":"Comorbidity of anxiety and depression in youth: Implications for treatment and prevention","volume":"17","author":"Garber","year":"2010","journal-title":"Clin Psychology: Sci Pract"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1037\/a0034733","article-title":"Comorbidity of anxiety and depression in children and adolescents: 20 years after","volume":"140","author":"Cummings","year":"2014","journal-title":"psychol Bull"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i23.34687","article-title":"Mental-perceiver: Audio-textual multi-modal learning for estimating mental disorders","author":"Qin","year":"2025"},{"key":"B24","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-70679-1_5","article-title":"Variational Autoencoder","volume-title":"Variational Methods for Machine Learning with Applications to Deep Networks","author":"Pinheiro Cinelli","year":"2021"},{"key":"B25","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.16362","article-title":"Multi-head attention: Collaborate instead of concatenate","author":"Cordonnier","year":"2020","journal-title":"arXiv preprint arXiv:2006.16362"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2019-033211","article-title":"Reliability and validity of the Chinese version of the patient health questionnaire-9 (c-phq-9) in patients with psoriasis: a cross-sectional study","volume":"10","author":"Ye","year":"2020","journal-title":"BMJ Open"},{"key":"B28","doi-asserted-by":"publisher","first-page":"463","DOI":"10.1037\/a0036523","article-title":"The psychometric properties of the generalized anxiety disorder-7 scale in hispanic americans with english or spanish language preference","volume":"20","author":"Mills","year":"2014","journal-title":"Cultural Diversity ethnic minority Psychol"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-023-05830-y","article-title":"Depression detection via a Chinese social media platform: a novel causal relation-aware deep learning approach","volume":"80","author":"Liu","year":"2024","journal-title":"J supercomputing"},{"key":"B30","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.specom.2015.05.004","article-title":"A review of depression and suicide risk assessment using speech analysis","volume":"71","author":"Cummins","year":"2015","journal-title":"Speech Communication"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyt.2022.917552","article-title":"Depression and anxiety among children and adolescents pre and post covid-19: A comparative meta-analysis","volume":"13","author":"Wang","year":"2022","journal-title":"Front Psychiatry"},{"key":"B32","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1002\/cyto.b.22167","article-title":"Translating the regulatory landscape of medical devices to create fit-for-purpose artificial intelligence (AI) cytometry solutions","volume":"106","author":"Bogdanoski","year":"2024","journal-title":"Cytometry Part B: Clin Cytometry"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v7i1.31732","article-title":"Fairness in AI-based mental health: Clinician perspectives and bias mitigation","volume":"7","author":"Sogancioglu","year":"2024","journal-title":"Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1142\/9789811270611_0008","article-title":"Data augmentation in high dimensional low sample size setting using a geometry-based variational autoencoder","volume":"45","author":"Chadebec","year":"2023","journal-title":"Pacific Symposium Biocomputing"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1109\/UBMK63289.2024.10773545","article-title":"PsychSynth: Advancing Mental Health AI Through Synthetic Data Generation and Curriculum Training","author":"Vedanta","year":"2024","journal-title":"2024 9th International Conference on Computer Science and Engineering (UBMK)"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2024.102789","article-title":"Explainable artificial intelligence for mental health assessment: A review","volume":"6","author":"Joyce","year":"2024","journal-title":"Artif Intell Med"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1752423\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,23]],"date-time":"2026-03-23T13:18:58Z","timestamp":1774271938000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1752423\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,24]]},"references-count":36,"alternative-id":["10.3389\/fpsyt.2026.1752423"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2026.1752423","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,24]]},"article-number":"1752423"}}