{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:12:47Z","timestamp":1778184767172,"version":"3.51.4"},"reference-count":18,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T00:00:00Z","timestamp":1767830400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to develop and compare machine learning (ML) models for predicting depressive symptoms in adolescents, based on teacher-reported textual descriptions of student behaviors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Participants were 441 adolescents from Tianjin, China. Their teachers provided written reports on behavioral or emotional concerns, while the students completed the Patient Health Questionnaire-9 (PHQ-9). Text data from reports were processed using Term Frequency-Inverse Document Frequency (TF-IDF). Four ML models\u2014Random Forest (RF), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost), and Least Absolute Shrinkage and Selection Operator (LASSO)\u2014were trained and evaluated using a 80\/20 data split and 5-fold cross-validation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      PHQ-9 screening identified 71.7% (\n                      <jats:italic>n<\/jats:italic>\n                      \u202f=\u202f316) of adolescents with clinically significant depressive symptoms (score \u226510). The Random Forest (RF) model demonstrated superior performance, achieving a recall of 0.97, accuracy of 0.91, precision of 0.92, and F1-score of 0.92. SVM and XGBoost also showed good performance, while LASSO was the weakest. The analysis demonstrated that teacher reports could identify depressive symptoms with up to 97% recall.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning, particularly Random Forest, can effectively predict adolescent depressive symptoms from teacher-reported text. This approach offers a practical and efficient tool for early identification in school settings, facilitating timely intervention.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/frai.2025.1732682","type":"journal-article","created":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T06:35:52Z","timestamp":1767854152000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Predicting adolescent depressive symptoms using teacher-reported textual descriptions of abnormal behaviors: a study based on machine learning"],"prefix":"10.3389","volume":"8","author":[{"given":"Nigela","family":"Wumaierjiang","sequence":"first","affiliation":[]},{"given":"Guoli","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Lidan","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Jianan","family":"Song","sequence":"additional","affiliation":[]},{"given":"Xiaofei","family":"Hou","sequence":"additional","affiliation":[]},{"given":"Minghui","family":"Li","sequence":"additional","affiliation":[]},{"given":"Ling","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Jiansong","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Huifang","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Guangming","family":"Xu","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2026,1,8]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"131","DOI":"10.12677\/ve.2018.74023","article-title":"Overview of classroom observation","volume":"7","author":"Anran Li","year":"2018","journal-title":"Voc. Educ."},{"key":"ref2","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1080\/j.1440-1614.2006.01741.x","article-title":"Stigma about depression and its impact on help-seeking intentions","volume":"40","author":"Barney","year":"2006","journal-title":"Aust. N. Z. J. Psychiatry"},{"key":"ref3","volume-title":"Blue book on mental health: 2022 National Report on adolescent mental health status survey","year":"2022"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"533949","DOI":"10.3389\/fpsyt.2020.533949","article-title":"Deep learning-based natural language processing for screening psychiatric patients","volume":"11","author":"Dai","year":"2021","journal-title":"Front. Psych."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"101486","DOI":"10.1016\/j.lanwpc.2025.101486","article-title":"The prevalence and associated disability burden of mental disorders in children and adolescents in China: a systematic analysis of data from the global burden of disease study","volume":"55","author":"Dong","year":"2025","journal-title":"Lancet Reg. Health Western Pacific"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"599","DOI":"10.1016\/j.jad.2018.08.062","article-title":"Depression literacy and stigma influence how parents perceive and respond to adolescent depressive symptoms","volume":"241","author":"Johnco","year":"2018","journal-title":"J. Affect. Disord."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"11846","DOI":"10.1038\/s41598-020-68764-y","article-title":"A deep learning model for detecting mental illness from user content on social media","volume":"10","author":"Kim","year":"2020","journal-title":"Sci. Rep."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"606","DOI":"10.1046\/j.1525-1497.2001.016009606.x","article-title":"The PHQ-9: validity of a brief depression severity measure","volume":"16","author":"Kroenke","year":"2001","journal-title":"J. Gen. Intern. Med."},{"key":"ref9","first-page":"n2183","article-title":"Accuracy of the patient health Questionnaire-9 for screening to detect major depression: updated systematic review and individual participant data meta-analysis","volume-title":"BMJs","author":"Negeri","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"825","DOI":"10.3390\/ijerph20010825","article-title":"Predictors of mental health literacy among parents, guardians, and teachers of adolescents in West Malaysia","volume":"20","author":"Phoa","year":"2023","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"e2425987","DOI":"10.1001\/jamanetworkopen.2024.25987","article-title":"Childhood and adolescent depression symptoms and young adult mental health and psychosocial outcomes","volume":"7","author":"Psychogiou","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"104410","DOI":"10.1016\/j.actpsy.2024.104410","article-title":"Anxiety in young people: analysis from a machine learning model","volume":"248","author":"Tabares Tabares","year":"2024","journal-title":"Acta Psychol."},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1016\/S0140-6736(22)01470-2","article-title":"The lancet commission on ending stigma and discrimination in mental health","volume":"400","author":"Thornicroft","year":"2022","journal-title":"Lancet"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"539","DOI":"10.1016\/j.genhosppsych.2014.05.021","article-title":"Reliability and validity of the Chinese version of the patient health questionnaire (PHQ-9) in the general population","volume":"36","author":"Wang","year":"2014","journal-title":"Gen. Hosp. Psychiatry"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"149","DOI":"10.11886\/scjsws20221021002","article-title":"Application analysis of the 9-item patient health questionnaire in adolescents","volume":"36","author":"Wei","year":"2023","journal-title":"Sichuan Mental Health."},{"key":"ref16","volume-title":"Mental health of adolescents","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"111","DOI":"10.3760\/cma.j.cn115682-20240327-01637","article-title":"Research progress on stigma associated with depressive disorder","volume":"31","author":"Yan","year":"2025","journal-title":"Chin. J. Mod. Nurs."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"152152","DOI":"10.1016\/j.comppsych.2019.152152","article-title":"Stigma towards depression in a community-based sample in China","volume":"97","author":"Yang","year":"2020","journal-title":"Compr. Psychiatry"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1732682\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T06:35:56Z","timestamp":1767854156000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1732682\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,8]]},"references-count":18,"alternative-id":["10.3389\/frai.2025.1732682"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1732682","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,8]]},"article-number":"1732682"}}