{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,3]],"date-time":"2026-08-03T19:27:32Z","timestamp":1785785252852,"version":"3.56.0"},"reference-count":36,"publisher":"Cambridge University Press (CUP)","issue":"10","license":[{"start":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T00:00:00Z","timestamp":1711497600000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Psychol. Med."],"published-print":{"date-parts":[[2024,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec id=\"S0033291724000497_sec_a1\"><jats:title>Background<\/jats:title><jats:p>Less than a third of patients with depression achieve successful remission with standard first-step antidepressant monotherapy. The process for determining appropriate second-step care is often based on clinical intuition and involves a protracted course of trial and error, resulting in substantial patient burden and unnecessary delay in the provision of optimal treatment. To address this problem, we adopt an ensemble machine learning approach to improve prediction accuracy of remission in response to second-step treatments.<\/jats:p><\/jats:sec><jats:sec id=\"S0033291724000497_sec_a2\" sec-type=\"methods\"><jats:title>Method<\/jats:title><jats:p>Data were derived from the Level 2 stage of the STAR*D dataset, which included 1439 patients who were randomized into one of seven different second-step treatment strategies after failing to achieve remission during first-step antidepressant treatment. Ensemble machine learning models, comprising several individual algorithms, were evaluated using nested cross-validation on 155 predictor variables including clinical and demographic measures.<\/jats:p><\/jats:sec><jats:sec id=\"S0033291724000497_sec_a3\" sec-type=\"results\"><jats:title>Results<\/jats:title><jats:p>The ensemble machine learning algorithms exhibited differential classification performance in predicting remission status across the seven second-step treatments. For the full set of predictors, AUC values ranged from 0.51 to 0.82 depending on the second-step treatment type. Predicting remission was most successful for cognitive therapy (AUC = 0.82) and least successful for other medication and combined treatment options (AUCs = 0.51\u20130.66).<\/jats:p><\/jats:sec><jats:sec id=\"S0033291724000497_sec_a4\" sec-type=\"conclusions\"><jats:title>Conclusion<\/jats:title><jats:p>Ensemble machine learning has potential to predict second-step treatment. In this study, predictive performance varied by type of treatment, with greater accuracy in predicting remission in response to behavioral treatments than to pharmacotherapy interventions. Future directions include considering more informative predictor modalities to enhance prediction of second-step treatment response.<\/jats:p><\/jats:sec>","DOI":"10.1017\/s0033291724000497","type":"journal-article","created":{"date-parts":[[2024,3,27]],"date-time":"2024-03-27T10:14:12Z","timestamp":1711534452000},"page":"2361-2368","update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":12,"title":["Optimizing precision medicine for second-step depression treatment: a machine learning approach"],"prefix":"10.1017","volume":"54","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4872-5962","authenticated-orcid":false,"given":"Joshua","family":"Curtiss","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordan W.","family":"Smoller","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paola","family":"Pedrelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2024,3,27]]},"reference":[{"key":"S0033291724000497_ref24","doi-asserted-by":"crossref","first-page":"439","DOI":"10.31887\/DCNS.2008.10.4\/gipapakostas","article-title":"Predictors, moderators, and mediators (correlates) of treatment outcome in major depressive disorder","volume":"10","author":"Papakostas","year":"2008","journal-title":"Dialogues in Clinical Neuroscience"},{"key":"S0033291724000497_ref16","doi-asserted-by":"crossref","DOI":"10.1201\/9781315108230","volume-title":"Feature engineering and selection: A practical approach for predictive models","author":"Kuhn","year":"2019"},{"key":"S0033291724000497_ref23","doi-asserted-by":"crossref","first-page":"1482","DOI":"10.1001\/jamainternmed.2016.5057","article-title":"Treatment of adult depression in the United States","volume":"176","author":"Olfson","year":"2016","journal-title":"JAMA Internal Medicine"},{"key":"S0033291724000497_ref2","doi-asserted-by":"crossref","first-page":"572","DOI":"10.4088\/JCP.15r10003","article-title":"Risk prediction models in psychiatry: Toward a new frontier for the prevention of mental illnesses","volume":"78","author":"Bernardini","year":"2017","journal-title":"Journal of Clinical Psychiatry"},{"key":"S0033291724000497_ref22","doi-asserted-by":"crossref","first-page":"e0197268","DOI":"10.1371\/journal.pone.0197268","article-title":"Predictive modeling of treatment resistant depression using data from STAR* D and an independent clinical study","volume":"13","author":"Nie","year":"2018","journal-title":"PloS One"},{"key":"S0033291724000497_ref14","unstructured":"Kuhn, M. (2022). caret: Classification and regression training (R package version 6.0-93) [Computer software]. The Comprehensive R Archive Network. Available from https:\/\/CRAN.Rproject.org\/package=caret"},{"key":"S0033291724000497_ref27","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1038\/s41398-020-0716-y","article-title":"Predicting treatment dropout after antidepressant initiation","volume":"10","author":"Pradier","year":"2020","journal-title":"Translational Psychiatry"},{"key":"S0033291724000497_ref19","doi-asserted-by":"crossref","unstructured":"Lewis, M. , Spiliopoulou, A. , & Goldmann, K. (2022). nestedcv: Nested cross-validation with \u2018glmnet\u2019 and \u2018caret\u2019 (R package version 0.3.6) [Computer software]. The Comprehensive R Archive Network. Available from https:\/\/github.com\/myles-lewis\/nestedcv","DOI":"10.1093\/bioadv\/vbad048"},{"key":"S0033291724000497_ref33","doi-asserted-by":"crossref","first-page":"25","DOI":"10.2202\/1544-6115.1309","article-title":"Super learner","volume":"6","author":"Van der Laan","year":"2007","journal-title":"Statistical Applications in Genetics and Molecular Biology"},{"key":"S0033291724000497_ref5","doi-asserted-by":"crossref","first-page":"243","DOI":"10.1016\/S2215-0366(15)00471-X","article-title":"Cross-trial prediction of treatment outcome in depression: A machine learning approach","volume":"3","author":"Chekroud","year":"2016","journal-title":"The Lancet Psychiatry"},{"key":"S0033291724000497_ref8","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12888-020-02655-4","article-title":"Predictors of remission from body dysmorphic disorder after internet-delivered cognitive behavior therapy: A machine learning approach","volume":"20","author":"Flygare","year":"2020","journal-title":"BMC Psychiatry"},{"key":"S0033291724000497_ref18","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1016\/j.jad.2018.08.073","article-title":"Applications of machine learning algorithms to predict therapeutic outcomes in depression: A meta-analysis and systematic review","volume":"241","author":"Lee","year":"2018","journal-title":"Journal of Affective Disorders"},{"key":"S0033291724000497_ref6","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/978-3-319-97241-1_1","volume-title":"The Massachusetts general hospital guide to depression: New treatment insights and options","author":"Cusin","year":"2019"},{"key":"S0033291724000497_ref34","doi-asserted-by":"crossref","first-page":"978","DOI":"10.1007\/978-1-4419-9782-1","volume-title":"Targeted learning: Causal inference for observational and experimental data","volume":"10","author":"Van der Laan","year":"2011"},{"key":"S0033291724000497_ref13","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1097\/YCO.0000000000000377","article-title":"The potential of predictive analytics to provide clinical decision support in depression treatment planning","volume":"31","author":"Kessler","year":"2018","journal-title":"Current Opinion in Psychiatry"},{"key":"S0033291724000497_ref12","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1177\/1745691610393527","article-title":"Rebooting psychotherapy research and practice to reduce the burden of mental illness","volume":"6","author":"Kazdin","year":"2011","journal-title":"Perspectives on Psychological Science"},{"key":"S0033291724000497_ref7","first-page":"321","article-title":"Quality of life enjoyment and satisfaction questionnaire: A new measure","volume":"29","author":"Endicott","year":"1993","journal-title":"Psychopharmacology Bulletin"},{"key":"S0033291724000497_ref25","doi-asserted-by":"crossref","first-page":"503","DOI":"10.1016\/j.jad.2018.09.067","article-title":"A systematic meta-review of predictors of antidepressant treatment outcome in major depressive disorder","volume":"243","author":"Perlman","year":"2019","journal-title":"Journal of Affective Disorders"},{"key":"S0033291724000497_ref4","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"Journal of Artificial Intelligence Research"},{"key":"S0033291724000497_ref30","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1038\/s41746-023-00817-8","article-title":"AI-assisted prediction of differential response to antidepressant classes using electronic health records","volume":"6","author":"Sheu","year":"2023","journal-title":"NPJ Digital Medicine"},{"key":"S0033291724000497_ref1","first-page":"1","article-title":"Clinical guidelines for the management of treatment-resistant depression: French recommendations from experts, the French Association for Biological Psychiatry and Neuropsychopharmacology and the foundation FondaMental","volume":"19","author":"Bennabi","year":"2019","journal-title":"BMC Psychiatry"},{"key":"S0033291724000497_ref10","first-page":"56","article-title":"The hamilton depression scale \u2013 accelerator or break on antidepressant drug discovery","volume":"23","author":"Hamilton","year":"1960","journal-title":"Psychiatry"},{"key":"S0033291724000497_ref17","doi-asserted-by":"crossref","first-page":"254","DOI":"10.1016\/j.jad.2022.02.046","article-title":"Efficiently identifying individuals at high risk for treatment resistance in major depressive disorder using electronic health records","volume":"306","author":"Lage","year":"2022","journal-title":"Journal of Affective Disorders"},{"key":"S0033291724000497_ref26","unstructured":"Polley, E. , LeDell, E. , Kennedy, C. , & Laan, M. V. D. (2021). SuperLearner: Super learner prediction (R package version 2.0-28) [Computer software]. The Comprehensive R Archive Network. Available from https:\/\/CRAN.R-project.org\/package=SuperLearner"},{"key":"S0033291724000497_ref21","doi-asserted-by":"crossref","first-page":"461","DOI":"10.1192\/bjp.180.5.461","article-title":"The work and social adjustment scale: A simple measure of impairment in functioning","volume":"180","author":"Mundt","year":"2002","journal-title":"The British Journal of Psychiatry"},{"key":"S0033291724000497_ref28","doi-asserted-by":"crossref","first-page":"353","DOI":"10.2165\/00019053-199304050-00006","article-title":"The validity and reproducibility of a work productivity and activity impairment instrument","volume":"4","author":"Reilly","year":"1993","journal-title":"Pharmacoeconomics"},{"key":"S0033291724000497_ref15","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-6849-3","volume-title":"Applied predictive modeling","author":"Kuhn","year":"2013"},{"key":"S0033291724000497_ref29","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1016\/S0006-3223(02)01866-8","article-title":"The 16-item Quick Inventory of Depressive Symptomatology (QIDS), clinician rating (QIDS-C), and self-report (QIDS-SR): A psychometric evaluation in patients with chronic major depression","volume":"54","author":"Rush","year":"2003","journal-title":"Biological psychiatry"},{"key":"S0033291724000497_ref11","doi-asserted-by":"crossref","first-page":"e205308","DOI":"10.1001\/jamanetworkopen.2020.5308","article-title":"Assessment of a prediction model for antidepressant treatment stability using supervised topic models","volume":"3","author":"Hughes","year":"2020","journal-title":"JAMA Network Open"},{"key":"S0033291724000497_ref35","doi-asserted-by":"crossref","first-page":"220","DOI":"10.1097\/00005650-199603000-00003","article-title":"A 12-item short-form health survey: Construction of scales and preliminary tests of reliability and validity","volume":"34","author":"Ware","year":"1996","journal-title":"Medical Care"},{"key":"S0033291724000497_ref20","doi-asserted-by":"crossref","first-page":"61","DOI":"10.1162\/cpsy_a_00029","article-title":"Differential treatment benefit prediction for treatment selection in depression: A deep learning analysis of STAR*D and CO-MED data","volume":"4","author":"Mehltretter","year":"2020","journal-title":"Computational Psychiatry"},{"key":"S0033291724000497_ref3","doi-asserted-by":"crossref","DOI":"10.1201\/9780367816377","volume-title":"Hands-on machine learning with R","author":"Boehmke","year":"2019"},{"key":"S0033291724000497_ref9","first-page":"9","article-title":"American Psychiatric association practice guidelines for the treatment of patients with major depressive disorder","volume":"167","author":"Gelenberg","year":"2010","journal-title":"American Journal of Psychiatry"},{"key":"S0033291724000497_ref32","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1176\/appi.ajp.163.1.28","article-title":"Evaluation of outcomes with citalopram for depression using measurement-based care in STAR* D: Implications for clinical practice","volume":"163","author":"Trivedi","year":"2006","journal-title":"American Journal of Psychiatry"},{"key":"S0033291724000497_ref36","doi-asserted-by":"crossref","first-page":"787","DOI":"10.1001\/archpsyc.58.8.787","article-title":"A self-report scale to help make psychiatric diagnoses: The psychiatric diagnostic screening questionnaire","volume":"58","author":"Zimmerman","year":"2001","journal-title":"Archives of General Psychiatry"},{"key":"S0033291724000497_ref31","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1080\/10503307.2017.1422214","article-title":"Moderators in psychotherapy meta-analysis","volume":"28","author":"Spielmans","year":"2018","journal-title":"Psychotherapy Research: Journal of the Society for Psychotherapy Research"}],"container-title":["Psychological Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0033291724000497","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T08:30:08Z","timestamp":1728462608000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0033291724000497\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,27]]},"references-count":36,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,7]]}},"alternative-id":["S0033291724000497"],"URL":"https:\/\/doi.org\/10.1017\/s0033291724000497","relation":{},"ISSN":["0033-2917","1469-8978"],"issn-type":[{"value":"0033-2917","type":"print"},{"value":"1469-8978","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,27]]},"assertion":[{"value":"Copyright \u00a9 The Author(s), 2024. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}]}}