{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T06:04:53Z","timestamp":1780985093592,"version":"3.54.1"},"reference-count":36,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T00:00:00Z","timestamp":1780963200000},"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. Hum. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Adolescent depression, characterized by high incidence rates and significant recurrence risks, has emerged as a major global public health concern. Current diagnosis relies predominantly on subjective questionnaires, lacking objective biomarkers and presenting challenges for early identification. Although exercise intervention is recommended as a safe and effective first-line non-pharmacological treatment, individual responses vary considerably. Approximately 30\u201340% of patients experience limited symptom improvement, necessitating reliable neurobiological markers to predict intervention response and enable precision exercise prescription. Resting-state electroencephalography (rs-EEG), with its non-invasive nature, low cost, and high temporal resolution, represents an ideal tool for identifying objective markers of depression. This study aims to construct a high-performance auxiliary diagnostic model for adolescent depression based on static and dynamic functional connectivity features of rs-EEG, combined with machine learning algorithms. It further seeks to identify neurophysiological biomarkers capable of predicting exercise intervention efficacy, thereby providing objective and practical technical support for early identification and individualized non-pharmacological interventions.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methodology<\/jats:title>\n                    <jats:p>\n                      This study employed a machine learning framework combining diagnostic and predictive models. The diagnostic model aimed to identify depressed individuals among healthy adolescents (\n                      <jats:italic>N<\/jats:italic>\n                      \u202f=\u202f155) and those with subclinical depression (\n                      <jats:italic>N<\/jats:italic>\n                      \u202f=\u202f149), whilst the predictive model focused on the emotional response to a virtual reality-based exercise intervention within the same depressed cohort (\n                      <jats:italic>N<\/jats:italic>\n                      \u202f=\u202f149), categorizing participants into high, moderate, and low responders. Six-minute resting-state EEG signals were collected, preprocessed, and segmented into 78 brain regions using the Schaefer template. These regions were then grouped into five core networks (sensory-motor, dorsal attention, salience, default mode, and central executive networks). Forty-five phase-locked functional connectivity features across the theta, alpha, and beta frequency bands were subsequently extracted. A three-stage feature selection method (random forest importance ranking, Pearson correlation redundancy removal, exhaustive search to determine optimal subsets) was employed to screen key neural biomarkers. Four classification models - logistic regression, support vector machines, random forest, and XGBoost - were constructed and compared. Ten-fold cross-validation and grid search were employed to optimize hyperparameters, with performance evaluated using accuracy, recall, precision, F1-score, and AUC-ROC. Finally, the SHAP framework was applied for model interpretability analysis, revealing the contributions and interactions of key brain network features.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Diagnostic model: The XGBoost model demonstrated exceptional performance in distinguishing SCD patients from healthy controls (AUC of 0.994, accuracy of 96.7%). Core biomarkers primarily concentrated on connections within the dorsal attention network (DAN), salience network (SN), and sensorimotor network (SMN) across the\n                      <jats:italic>\u03b2<\/jats:italic>\n                      and\n                      <jats:italic>\u03b1<\/jats:italic>\n                      frequency bands, with intra-DAN connections in the\n                      <jats:italic>\u03b2<\/jats:italic>\n                      band contributing most significantly. SHAP interaction dependency analysis further revealed complex nonlinear interaction patterns that may underlie, including a \u201cfork-collider\u201d synergistic structure centered on\n                      <jats:italic>\u03b2<\/jats:italic>\n                      -DAN and\n                      <jats:italic>\u03b8<\/jats:italic>\n                      -SMN-DAN, cross-frequency inhibition of\n                      <jats:italic>\u03b2<\/jats:italic>\n                      -DAN by\n                      <jats:italic>\u03b1<\/jats:italic>\n                      -SN, and dynamic gating of\n                      <jats:italic>\u03b2<\/jats:italic>\n                      -DMN by\n                      <jats:italic>\u03b1<\/jats:italic>\n                      -SMN-DAN. The results of this study indicate that subclinical depression (ScD) manifests as a pattern of synergistic dysregulation involving multiple frequency bands and brain networks. In terms of predictive modeling, support vector machines (SVMs) performed best in predicting the response of ScD patients to exercise intervention, with baseline positive affect (PA) levels and functional connectivity between the somatosensory motor network (SMN) and the dorsal attentional network (DAN) in the\n                      <jats:italic>\u03b2<\/jats:italic>\n                      -band identified as key predictors. Furthermore, the patterns of feature interactions revealed by the model provide a testable framework for understanding the underlying model-derived neurophysiological patterns of subclinical depression from the perspective of multi-frequency, multi-network dyssynchrony; however, these results should still be interpreted as statistical associations rather than direct evidence of biological causality. SHAP analysis revealed an interpretable integration pathway (\u201cbehavior-driven \u2192 core coordination \u2192 dynamic gating \u2192 frequency band balance\u201d), providing model-driven insights into the role of behavior-neural integration in personalized interventions.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This study systematically elucidates for the first time the intricate model-derived neurophysiological patterns of subclinical depression at the multi-frequency brain network level. It confirms the substantial potential of EEG functional connectivity as an objective biomarker while providing an interpretable neurophysiological basis for the precise selection of exercise interventions. These findings deepen our understanding of the early pathophysiology of depression and lay a robust foundation for developing low-cost, non-invasive tools for early screening and personalized treatment decision-making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnhum.2026.1774822","type":"journal-article","created":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T05:45:06Z","timestamp":1780983906000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Building an auxiliary diagnostic and treatment efficacy prediction model for adolescent depression using machine learning based on electroencephalography technology"],"prefix":"10.3389","volume":"20","author":[{"given":"Ting","family":"Peng","sequence":"first","affiliation":[{"name":"School of Physical Education, Shaanxi Normal University","place":["Xi'an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aiping","family":"Chi","sequence":"additional","affiliation":[{"name":"School of Physical Education, Shaanxi Normal University","place":["Xi'an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinghui","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Physical Education, Shaanxi Normal University","place":["Xi'an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhong","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Physical Education, Shaanxi Normal University","place":["Xi'an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanru","family":"Li","sequence":"additional","affiliation":[{"name":"School of Physical Education, Shaanxi Normal University","place":["Xi'an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Fan","sequence":"additional","affiliation":[{"name":"Shaanxi Vocational and Technical College","place":["Xi'an, Shaanxi, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,6,9]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1080\/13803395.2025.2480139","article-title":"Structural equation modeling of problematic internet use based on executive function, interpersonal needs, fear of missing out and depression","volume":"47","author":"Alavinikoo","year":"2025","journal-title":"J Clin Exp Neuropsyc"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"103825","DOI":"10.1016\/j.medengphy.2022.103825","article-title":"A systematic review on machine learning approaches for cardiovascular disease prediction using medical big data","volume":"105","author":"Azmi","year":"2022","journal-title":"Med. Eng. Phys."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.schres.2023.02.007","article-title":"Abnormal brain network community structure related to psychological stress in schizophrenia","volume":"254","author":"Castro","year":"2023","journal-title":"Schizophr. Res."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1016\/j.ajo.2019.10.015","article-title":"Applying machine learning techniques in nomogram prediction and analysis for smile treatment","volume":"210","author":"Cui","year":"2020","journal-title":"Am. J. Ophthalmol."},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2246","DOI":"10.1007\/s10964-020-01315-w","article-title":"Loneliness, social anxiety symptoms, and depressive symptoms in adolescence: longitudinal distinctiveness and correlated change","volume":"49","author":"Danneel","year":"2020","journal-title":"J. Youth. Adolesc."},{"key":"ref6","doi-asserted-by":"publisher","first-page":"119399","DOI":"10.1016\/j.jad.2025.119399","article-title":"Machine learning-based predictive modeling of depressive symptoms in Chinese adolescents","volume":"385","author":"Ding","year":"2025","journal-title":"J. Affect Disord."},{"key":"ref7","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41583-024-00895-x","article-title":"The brain's action-mode network","volume":"26","author":"Dosenbach","year":"2025","journal-title":"Nat. Rev. Neurosci."},{"key":"ref8","doi-asserted-by":"publisher","first-page":"119545","DOI":"10.1016\/j.jad.2025.119545","article-title":"Inflammatory biomarkers as predictors for unlocking antidepressant efficacy: assessing predictive value and risk stratification in major depressive disorder in a prospective longitudinal study","volume":"387","author":"Elbakary","year":"2025","journal-title":"J. Affect. Disord."},{"key":"ref9","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1016\/j.pscychresns.2016.12.010","article-title":"Brain connectivity networks and longitudinal trajectories of depression symptoms in adolescence","volume":"260","author":"Ellis","year":"2017","journal-title":"Psychiat Res-Neuroim"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"710667","DOI":"10.3389\/fpubh.2021.710667","article-title":"Parenting styles, depressive symptoms, and problematic online game use in adolescents: a developmental cascades model","volume":"9","author":"Gan","year":"2021","journal-title":"Front. Public Health"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1016\/j.psc.2023.02.009","article-title":"Brain features of treatment-resistant depression: a review of structural and functional connectivity magnetic resonance imaging studies","volume":"46","author":"Grehl","year":"2023","journal-title":"Psychiat Clin N Am"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"116217","DOI":"10.1016\/j.neuroimage.2019.116217","article-title":"Relationships between depressive symptoms and brain responses during emotional movie viewing emerge in adolescence","volume":"216","author":"Gruskin","year":"2020","journal-title":"NeuroImage"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1097\/WNR.0000000000001773","article-title":"Disrupted default mode network and executive control network are associated with depression severity on structural network","volume":"33","author":"He","year":"2022","journal-title":"Neuroreport"},{"key":"ref1001","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1037\/\/0022-006x.59.1.12","article-title":"Clinical significance: a statistical approach to defining meaningful change in psychotherapy research","volume":"59","author":"Jacobson","year":"1991","journal-title":"J Consult Clin Psychol."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"e2216499120","DOI":"10.1073\/pnas.2216499120","article-title":"Elevated emotion network connectivity is associated with fluctuations in depression","volume":"120","author":"Kelley","year":"2023","journal-title":"Proc. Natl. Acad. Sci. U S A"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"116702","DOI":"10.1016\/j.psychres.2025.116702","article-title":"Machine learning-based prediction of suicide risk using adult attention-deficit\/hyperactivity disorder symptoms and depression indicators: insights from a nationally representative south korean survey","volume":"352","author":"Kim","year":"2025","journal-title":"Psychiatry Res."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"119678","DOI":"10.1016\/j.jad.2025.119678","article-title":"Machine learning identifies prominent risk factors for depressive symptoms among Chinese children and adolescents","volume":"389","author":"Lei","year":"2025","journal-title":"J Affect Disorders"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1002\/wps.21156","article-title":"Borderline personality disorder: a comprehensive review of diagnosis and clinical presentation, etiology, treatment, and current controversies","volume":"23","author":"Leichsenring","year":"2024","journal-title":"World Psychiatry."},{"key":"ref17","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1177\/10998004251318385","article-title":"Cytokines and depressive symptoms among adolescents","volume":"27","author":"Leung","year":"2025","journal-title":"Biol. Res. Nurs."},{"key":"ref18","doi-asserted-by":"publisher","first-page":"1980","DOI":"10.1038\/s41380-024-02450-7","article-title":"Divergent suicidal symptomatic activations converge on somato-cognitive action network in depression","volume":"29","author":"Li","year":"2024","journal-title":"Mol. Psychiatry"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1007\/s00787-022-01993-w","article-title":"Joint trajectories of loneliness, depressive symptoms, and social anxiety from middle childhood to early adolescence: associations with suicidal ideation","volume":"32","author":"Liang","year":"2023","journal-title":"Eur. Child. Adoles. Psy."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1186\/s12889-025-21506-z","article-title":"Identification of depressive symptoms in adolescents using machine learning combining childhood and adolescence features","volume":"25","author":"Liu","year":"2025","journal-title":"BMC Public Health"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"1522","DOI":"10.1123\/ijspp.2020-0518","article-title":"Injury prediction in competitive runners with machine learning","volume":"16","author":"L\u00f6vdal","year":"2021","journal-title":"Int J Sport Physiol"},{"key":"ref22","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1111\/jcpp.13961","article-title":"Annual research review: Neuroimmune network model of depression: a developmental perspective","volume":"65","author":"Nusslock","year":"2024","journal-title":"J. Child. Psychol. Psychiatry."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"102481","DOI":"10.1016\/j.arr.2024.102481","article-title":"Pathogenesis, diagnostics, and therapeutics for Alzheimer's disease: breaking the memory barrier","volume":"101","author":"Pt","year":"2024","journal-title":"Ageing Res. Rev."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1186\/s12967-025-06289-6","article-title":"Prediction of postpartum depression in women: development and validation of multiple machine learning models","volume":"23","author":"Qi","year":"2025","journal-title":"J. Transl. Med."},{"key":"ref25","doi-asserted-by":"publisher","first-page":"1478","DOI":"10.1177\/09544119221122012","article-title":"Role of artificial intelligence and machine learning in the prediction of the pain: a scoping systematic review","volume":"236","author":"Sankaran","year":"2022","journal-title":"Proc. Inst. Mech. Eng. H"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"148196","DOI":"10.1016\/j.brainres.2022.148196","article-title":"Reorganization of resting-state brain network functional connectivity across human brain developmental stages","volume":"1800","author":"Singh","year":"2023","journal-title":"Brain Res."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.jad.2024.08.016","article-title":"Body image and depressive symptoms in Danish adolescents: a cross-sectional national study","volume":"365","author":"Thorup","year":"2024","journal-title":"J. Affect. Disord."},{"key":"ref29","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1080\/09638237.2025.2478374","article-title":"Unveiling sex difference in factors associated with suicide attempt among Chinese adolescents with depression: a machine learning-based study","volume":"34","author":"Wang","year":"2025","journal-title":"J. Ment. Health"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1058","DOI":"10.1109\/TMI.2018.2877576","article-title":"Recognizing brain states using deep sparse recurrent neural network","volume":"38","author":"Wang","year":"2019","journal-title":"Ieee T Med Imaging"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1016\/j.jpsychires.2024.01.021","article-title":"Dysconnectivity of the brain functional network and abnormally expressed peripheral transcriptional profiles in patients with anxious depression","volume":"171","author":"Wei","year":"2024","journal-title":"J. Psychiatr. Res."},{"key":"ref32","doi-asserted-by":"publisher","first-page":"e241933","DOI":"10.1001\/jamanetworkopen.2024.1933","article-title":"Reconfiguration of structural and functional connectivity coupling in patient subgroups with adolescent depression","volume":"7","author":"Xu","year":"2024","journal-title":"JAMA Netw. Open"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1007\/s10964-024-02028-0","article-title":"Exploring the co-occurrence of depressive symptoms and aggression among Chinese adolescents: patterns and stability","volume":"54","author":"Yang","year":"2025","journal-title":"J. Youth. Adoles."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-981-33-6044-0_1","article-title":"Phenotype network and brain structural covariance network of major depression","volume":"1305","author":"Yun","year":"2021","journal-title":"Adv. Exp. Med. Biol."},{"key":"ref35","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1038\/mp.2016.44","article-title":"Gut microbiome remodeling induces depressive-like behaviors through a pathway mediated by the host's metabolism","volume":"21","author":"Zheng","year":"2016","journal-title":"Mol. Psychiatry"}],"container-title":["Frontiers in Human Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2026.1774822\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T05:45:07Z","timestamp":1780983907000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2026.1774822\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,9]]},"references-count":36,"alternative-id":["10.3389\/fnhum.2026.1774822"],"URL":"https:\/\/doi.org\/10.3389\/fnhum.2026.1774822","relation":{},"ISSN":["1662-5161"],"issn-type":[{"value":"1662-5161","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,9]]},"article-number":"1774822"}}