{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T19:30:12Z","timestamp":1774380612307,"version":"3.50.1"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T00:00:00Z","timestamp":1774310400000},"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. Psychiatry"],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Major depressive disorder (MDD) affects approximately one in six individuals over their lifetime, with many patients experiencing treatment-resistant depression, characterized by inadequate or insufficient response from at least one antidepressant treatment. Current classification strategies for depression rely primarily on clinical assessment of symptom severity, which are prone to reader bias and test-retest variability. Moreover, these symptom-based subtypes have shown limited utility in predicting treatment response. This study introduces a data-driven, non-biased classification framework that integrates clinical features with high-resolution magnetic resonance imaging (MRI)-derived features. Using canonical correlation analysis (CCA) and hierarchical clustering, the approach identifies distinct subtypes of MDD, offering a more objective and potentially predictive alternative to traditional methods.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials &amp;amp; methods<\/jats:title>\n                    <jats:p>\n                      Sixty-four participants with MDD currently experiencing a major depressive episode and not currently undergoing treatment completed a battery of 11 clinical symptom severity assessments and scanned with 7T T1-weighted MRI with parameters: TE\/TR = 3.62\/6000 ms, 320x240x240 array size with 224x168 mm\n                      <jats:sup>2<\/jats:sup>\n                      field-of-view (FOV) for voxel dimensions of 0.7 mm\n                      <jats:sup>3<\/jats:sup>\n                      isotropic. The images were automatically segmented using the FreeSurfer 6.0 package and 87 resulting imaging features, along with 11 clinical measures were processed through CCA to derive highly-correlated clinical-imaging phenotypes. An analysis using the Sillhouette and other methods determined an optimal number of clusters for this dataset. Participants with MDD were plotted on axes consisting of highly correlated clinical-imaging phenotypes derived from CCA and subsequently grouped through hierarchical clustering.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>CCA identified three highly correlated (r &amp;gt; 0.9) clinical-imaging variable pairs. The first, an anhedonia-related phenotype, showed high loadings from anhedonia severity and brainstem features. The second phenotype was associated with childhood trauma and anhedonia, with the right frontal pole as the primary imaging feature. The third phenotype linked general distress and perceived stress with the right superior temporal lobe. Hierarchical clustering along these canonical axes revealed two distinct clusters: one characterized by high childhood trauma scores and the other showing scores comparable to healthy controls.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Taken together, this study presents a novel ML framework for classifying depression using CCA and clustering.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpsyt.2026.1747824","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:11:23Z","timestamp":1774368683000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning framework for depression subtype grouping: integrating high-resolution imaging and clinical symptom analysis via correlation and clustering"],"prefix":"10.3389","volume":"17","author":[{"given":"Gaurav","family":"Verma","sequence":"first","affiliation":[{"name":"Department of Radiology, Icahn School of Medicine at Mount Sinai","place":["New York, NY, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yael","family":"Jacob","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Icahn School of Medicine at Mount Sinai","place":["New York, NY, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Laurel S.","family":"Morris","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Icahn School of Medicine at Mount Sinai","place":["New York, NY, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Xing","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Nebraska Omaha","place":["Omaha, NE, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bradley N.","family":"Delman","sequence":"additional","affiliation":[{"name":"Department of Radiology, Icahn School of Medicine at Mount Sinai","place":["New York, NY, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"James W.","family":"Murrough","sequence":"additional","affiliation":[{"name":"Depression and Anxiety Center for Discovery and Treatment, Department of Psychiatry, Icahn School of Medicine of Mount Sinai","place":["New York, NY, United States"]},{"name":"Nash Family Department of Neuroscience, Icahn School of Medicine at Mount Sinai","place":["New York, NY, United States"]},{"name":"VISN 2 Mental Illness Research, Education, and Clinical Center (MIRECC), James J. Peters VA Medical Center","place":["Bronx, NY, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ai-Ling","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Radiology, Division of Biological Sciences, and Institute for Data Science and Informatics, University of Missouri","place":["Columbia, MO, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Priti","family":"Balchandani","sequence":"additional","affiliation":[{"name":"Department of Radiology, Icahn School of Medicine at Mount Sinai","place":["New York, NY, United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2026,3,24]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1001\/archpsyc.62.6.593","article-title":"Lifetime prevalence and age-of-onset distributions of DSM-IV disorders in the National Comorbidity Survey Replication","volume":"62","author":"Kessler","year":"2005","journal-title":"Arch Gen Psychiatry"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1001\/jama.289.23.3095","article-title":"The epidemiology of major depressive disorder: results from the National Comorbidity Survey Replication (NCS-R)","volume":"289","author":"Kessler","year":"2003","journal-title":"Jama"},{"key":"B3","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1111\/j.1600-0447.1994.tb05786.x","article-title":"Major depressive disorder","volume":"89","author":"Spaner","year":"1994","journal-title":"Acta Psychiatrica Scandinavica"},{"key":"B4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s40273-021-01019-4","article-title":"The economic burden of adults with major depressive disorder in the United\u00a0States (2010 and 2018)","author":"Greenberg","year":"2021","journal-title":"Pharmacoeconomics"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/S0006-3223(03)00231-2","article-title":"Diagnosis and definition of treatment-resistant depression","volume":"53","author":"Fava","year":"2003","journal-title":"Biol Psychiatry"},{"key":"B6","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1126\/science.aab2358","article-title":"Brain disorders? precisely","volume":"348","author":"Insel","year":"2015","journal-title":"Science"},{"key":"B7","doi-asserted-by":"publisher","first-page":"416321","DOI":"10.1101\/416321","article-title":"Evaluating the evidence for biotypes of depression: attempted replication of Drysdale et\u00a0al., 2017","author":"Dinga","year":"2018","journal-title":". bioRxiv"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1097\/RMR.0000000000000210","article-title":"Ultrahigh field MR neuroimaging","volume":"28","author":"Verma","year":"2019","journal-title":"Topics Magnetic Resonance Imaging"},{"key":"B9","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.mric.2020.09.001","article-title":"Neuroimaging at 3T vs 7T: is it really worth it","volume":"29","author":"Jones","year":"2021","journal-title":"Magnetic Resonance Imaging Clinics"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2011.07.007","article-title":"Clinical applications of 7 T MRI in the brain","volume":"82","author":"Van der Kolk","year":"2013","journal-title":"Eur J Radiol"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1111\/j.1600-0447.1986.tb02723.x","article-title":"The Montgomery-\u00c5sberg Depression Scale: reliability and validity","volume":"73","author":"Davidson","year":"1986","journal-title":"Acta psychiatrica scandinavica"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1037\/t13679-000","article-title":"Mood and anxiety symptom questionnaire","author":"Watson","year":"1991","journal-title":"J Behav Ther Exp Psychiatry"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2307\/2136404","article-title":"Perceived stress scale","volume":"10","author":"Cohen","year":"1994","journal-title":"Measuring stress: A guide Health Soc scientists"},{"key":"B14","volume-title":"Childhood Trauma Questionnaire: a retrospective self-report manual","author":"Bernstein","year":"1998"},{"key":"B15","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1016\/j.jbtep.2006.03.002","article-title":"On the measurement of rumination: A psychometric evaluation of the ruminative response scale and the rumination on sadness scale in undergraduates","volume":"37","author":"Roelofs","year":"2006","journal-title":"J Behav Ther Exp Psychiatry"},{"key":"B16","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1192\/bjp.167.1.99","article-title":"A scale for the assessment of hedonic tone the Snaith\u2013Hamilton Pleasure Scale","volume":"167","author":"Snaith","year":"1995","journal-title":"Br J Psychiatry"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1016\/j.jrp.2005.11.001","article-title":"Anticipatory and consummatory components of the experience of pleasure: a scale development study","volume":"40","author":"Gard","year":"2006","journal-title":"J Res Pers"},{"key":"B18","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1037\/1040-3590.19.4.369","article-title":"Psychometric properties of the state-trait inventory for cognitive and somatic anxiety (STICSA): comparison to the state-trait anxiety inventory (STAI)","volume":"19","author":"Gr\u00f6s","year":"2007","journal-title":"psychol Assess"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.021","article-title":"FreeSurfer","volume":"62","author":"Fischl","year":"2012","journal-title":"Neuroimage"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpsc.2020.02.002","article-title":"Canonical correlation analysis for identifying biotypes of depression","volume":"5","author":"Mihalik","year":"2020","journal-title":"Biol Psychiatry: Cogn Neurosci Neuroimaging"},{"key":"B21","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1038\/nm.4246","article-title":"Resting-state connectivity biomarkers define neurophysiological subtypes of depression","volume":"23","author":"Drysdale","year":"2017","journal-title":"Nat Med"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.1177\/0004867419872248","article-title":"Clinical subtypes that\u00a0predict conversion to psychosis: a canonical correlation analysis study from the ShangHai At Risk for Psychosis program","volume":"54","author":"Zhang","year":"2020","journal-title":"Aust New Z J Psychiatry"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1007\/s11055-011-9425-6","article-title":"Use of canonical correfslation analysis to evaluate the strength of relationships between clinical and biological parameters","volume":"41","author":"Brusov","year":"2011","journal-title":"Neurosci Behav Physiol"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.1207\/S15327752JPA740108","article-title":"Exploring the factor structure of the Mood and Anxiety Symptom Questionnaire (MASQ)","volume":"74","author":"Keogh","year":"2000","journal-title":"J Pers Assess"},{"key":"B25","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","article-title":"Silhouettes: a graphical aid to the interpretation and validation of cluster analysis","volume":"20","author":"Rousseeuw","year":"1987","journal-title":"J Comput Appl mathematics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","article-title":"A dendrite method for cluster analysis","volume":"3","author":"Cali\u0144ski","year":"1974","journal-title":"Commun Statistics-theory Methods"},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.1979.4766909","volume-title":"A cluster separation measure","author":"Davies","year":"1979"},{"key":"B28","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1007\/s11222-007-9033-z","article-title":"A tutorial on spectral clustering","volume":"17","author":"Von Luxburg","year":"2007","journal-title":". Stat computing"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2012.01.021","article-title":"Tests for departure from normality. Empirical results for the distributions of b 2 and\u221a b","volume":"60","author":"D\u2019agostino","year":"1973","journal-title":"Biometrika"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1017\/S003329170300758X","article-title":"Depression with late onset is associated with right frontal lobe atrophy","volume":"33","author":"Almeida","year":"2003","journal-title":"psychol Med"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/424769","article-title":"Frontal lobe atrophy in depression after stroke","volume":"2013","author":"Tang","year":"2013","journal-title":"Stroke Res Treat"},{"key":"B32","article-title":"Neuroanatomy, nucleus raphe","volume-title":"StatPearls","author":"Walker","year":"2023"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.jad.2011.04.006","article-title":"Demonstration of decreased gray matter concentration in the midbrain encompassing the dorsal raphe nucleus and the limbic subcortical regions in major depressive disorder: an optimized voxel-based morphometry study","volume":"133","author":"Lee","year":"2011","journal-title":"J Affect Disord"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/j.biopsych.2005.05.019","article-title":"The neural correlates of anhedonia in major depressive disorder","volume":"58","author":"Keedwell","year":"2005","journal-title":"Biol Psychiatry"},{"key":"B35","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1016\/j.biopsych.2005.04.035","article-title":"A double dissociation of ventromedial prefrontal cortical responses to sad and happy stimuli in depressed and healthy individuals","volume":"58","author":"Keedwell","year":"2005","journal-title":"Biol Psychiatry"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/awab032","article-title":"Uncovering the prevalence and neural substrates of anhedonia in frontotemporal dementia","volume":"144","author":"Shaw","year":"2021","journal-title":"Brain"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1111\/bdi.12516","article-title":"Amygdala and hippocampus volumes are differently affected by childhood trauma in patients with bipolar disorders and healthy controls","volume":"19","author":"Janiri","year":"2017","journal-title":"Bipolar Disord"},{"key":"B38","doi-asserted-by":"publisher","first-page":"nsac064","DOI":"10.1093\/scan\/nsac064","article-title":"Right amygdala\u2013right precuneus connectivity is associated with childhood trauma in major depression patients and healthy controls","volume":"18","author":"Fan","year":"2023","journal-title":"Soc Cogn Affect Neurosci"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03057-9","article-title":"Personalized brain circuit scores identify clinically distinct biotypes in depression and anxiety","volume":"30","author":"Tozzi","year":"2024","journal-title":"Nat Med"},{"key":"B40","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1038\/s41380-019-0385-5","article-title":"Data-driven biological\u00a0subtypes of depression: systematic review of biological approaches to depression subtyping","volume":"24","author":"Beijers","year":"2019","journal-title":"Mol Psychiatry"}],"container-title":["Frontiers in Psychiatry"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1747824\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T16:11:24Z","timestamp":1774368684000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpsyt.2026.1747824\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,24]]},"references-count":40,"alternative-id":["10.3389\/fpsyt.2026.1747824"],"URL":"https:\/\/doi.org\/10.3389\/fpsyt.2026.1747824","relation":{},"ISSN":["1664-0640"],"issn-type":[{"value":"1664-0640","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,24]]},"article-number":"1747824"}}