{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:57:24Z","timestamp":1782845844100,"version":"3.54.5"},"reference-count":22,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR AI"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Online depression screening tools may increase uptake of evidence-based care and consequently lead to symptom reduction. However, results of the DISCOVER trial suggested no effect of automated results feedback compared with no feedback after online depression screening on depressive symptom reduction six months after screening. Interpersonal variation in symptom representation, health care needs, and treatment preferences may nonetheless have led to differential response to feedback mode on an individual level.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n The aim of this study was to examine heterogeneity of treatment effects (HTE), that is, differential responses to two feedback modes (tailored or nontailored) versus no feedback (control) following online depression screening.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n We used causal forests, a machine learning method that applies recursive partitioning to estimate conditional average treatment effects (CATEs). In this secondary data analysis of the DISCOVER trial, eligible participants screened positive for at least moderate depression severity but had not been diagnosed or treated for depression in the preceding year. The primary outcome was heterogeneity in depression severity change, over a and six-month follow up period, measured with the Patient Health Questionnaire-9. Analysis comprised exploration of average treatment effects (ATE), HTE, operationalized with the area under the targeting operator characteristic curve (AUTOC), and differences in ATE when allocating feedback based on predicted CATE. We extracted top predictors of depression severity change, given feedback and explored high-CATE covariate profiles. Prior to analysis, data was split into training and test sets (1:1) to minimize the risk of overfitting and evaluate predictions in held-out test data.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n \n Data from 946 participants of the DISCOVER trial without missing data were analyzed. We did not detect HTE; no versus nontailored feedback, AUTOC \u22120.48 (95% CI \u22121.62 to 0.67,\n P=<\/jats:italic>\n .41); no versus tailored feedback, AUTOC 0.06 (95% CI \u22121.21 to 1.33,\n P=<\/jats:italic>\n .93); and no versus any feedback, AUTOC \u22120.20 (95% CI \u22121.30 to 0.89,\n P=<\/jats:italic>\n .72). There was no evidence of alteration to the ATE in the test set when allocating feedback (tailored or nontailored) based on the predicted CATE. By examining covariate profiles, we observed a potentially detrimental role of control beliefs, given feedback compared with no feedback.\n <\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n We applied causal forests to describe higher-level interactions among a broad range of predictors to detect HTE. In absence of evidence for HTE, treatment prioritization based on trained models did not improve ATEs. We did not find evidence of harm or benefit from providing tailored or nontailored feedback after online depression screening regarding depression severity change after six months. Future studies may test whether screening alone prompts behavioral activation and downstream depression severity reduction, considering the observed uniform changes across groups.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/70001","type":"journal-article","created":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T05:35:57Z","timestamp":1756100157000},"page":"e70001-e70001","source":"Crossref","is-referenced-by-count":0,"title":["Heterogeneity in Effects of Automated Results Feedback After Online Depression Screening: Secondary Machine-Learning Based Analysis of the DISCOVER Trial"],"prefix":"10.2196","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1629-482X","authenticated-orcid":false,"given":"Matthias","family":"Klee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7399-2299","authenticated-orcid":false,"given":"Byron C","family":"Jaeger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1191-5073","authenticated-orcid":false,"given":"Franziska","family":"Sikorski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4220-3378","authenticated-orcid":false,"given":"Bernd","family":"L\u00f6we","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1307-4618","authenticated-orcid":false,"given":"Sebastian","family":"Kohlmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"issue":"7","key":"R1","doi-asserted-by":"publisher","first-page":"e446","DOI":"10.1016\/S2589-7500(24)00070-0","article-title":"The efficacy of automated feedback after internet-based depression screening (DISCOVER): an observer-masked, three-armed, randomised controlled trial in Germany","volume":"6","author":"Kohlmann","journal-title":"Lancet Digit Health"},{"issue":"6","key":"R2","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1007\/s10865-016-9782-2","article-title":"The Common-Sense Model of self-regulation (CSM): a dynamic framework for understanding illness self-management","volume":"39","author":"Leventhal","journal-title":"J Behav Med"},{"issue":"4","key":"R3","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1111\/j.0887-378X.2004.00327.x","article-title":"Evidence-based medicine, heterogeneity of treatment effects, and the trouble with averages","volume":"82","author":"Kravitz","journal-title":"Milbank Q"},{"issue":"2","key":"R4","doi-asserted-by":"publisher","DOI":"10.1002\/mpr.70015","article-title":"Estimating treatment effect heterogeneity in psychiatry: a review and tutorial with causal forests","volume":"34","author":"Sverdrup","journal-title":"Int J Methods Psychiatr Res"},{"issue":"2","key":"R5","doi-asserted-by":"publisher","first-page":"1148","DOI":"10.1214\/18-AOS1709","article-title":"Generalized random forests","volume":"47","author":"Athey","journal-title":"Ann Statist"},{"issue":"523","key":"R6","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1080\/01621459.2017.1319839","article-title":"Estimation and inference of heterogeneous treatment effects using random forests","volume":"113","author":"Wager","journal-title":"J Am Stat Assoc"},{"issue":"1","key":"R7","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"Breiman","journal-title":"Mach Learn"},{"issue":"111538","key":"R8","doi-asserted-by":"publisher","first-page":"111538","DOI":"10.1016\/j.jclinepi.2024.111538","article-title":"Machine learning approaches to evaluate heterogeneous treatment effects in randomized controlled trials: a scoping review","volume":"176","author":"Inoue","journal-title":"J Clin Epidemiol"},{"key":"R9","doi-asserted-by":"publisher","DOI":"10.1016\/j.invent.2021.100435","article-title":"The efficacy of automated feedback after internet-based depression screening: study protocol of the German, three-armed, randomised controlled trial DISCOVER","volume":"25","author":"Sikorski","journal-title":"Internet Interv"},{"issue":"4","key":"R10","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1016\/j.genhosppsych.2010.03.006","article-title":"The Patient Health Questionnaire Somatic, Anxiety, and Depressive Symptom scales: a systematic review","volume":"32","author":"Kroenke","journal-title":"Gen Hosp Psychiatry"},{"issue":"3","key":"R11","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1097\/MLR.0b013e318160d093","article-title":"Validation and standardization of the Generalized Anxiety Disorder screener (GAD-7) in the general population","volume":"46","author":"L\u00f6we","journal-title":"Med Care"},{"issue":"3","key":"R12","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1001\/jamainternmed.2013.12179","article-title":"The somatic symptom scale-8 (SSS-8): a brief measure of somatic symptom burden","volume":"174","author":"Gierk","journal-title":"JAMA Intern Med"},{"issue":"1-3","key":"R13","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.jad.2007.04.018","article-title":"The responsiveness of EQ-5D utility scores in patients with depression: a comparison with instruments measuring quality of life, psychopathology and social functioning","volume":"105","author":"G\u00fcnther","journal-title":"J Affect Disord"},{"issue":"6","key":"R14","doi-asserted-by":"publisher","first-page":"631","DOI":"10.1016\/j.jpsychores.2005.10.020","article-title":"The brief illness perception questionnaire","volume":"60","author":"Broadbent","journal-title":"J Psychosom Res"},{"issue":"11","key":"R15","doi-asserted-by":"publisher","first-page":"1361","DOI":"10.1080\/08870446.2015.1070851","article-title":"A systematic review and meta-analysis of the Brief Illness Perception questionnaire","volume":"30","author":"Broadbent","journal-title":"Psychol Health"},{"key":"R16","unstructured":"Klee M . Primary analysis code repository for \u2018Heterogeneity in effects of automated results feedback after online depression screening: a secondary machine-learning based analysis of the DISCOVER trial. GitHub. 2024. URL: https:\/\/github.com\/makleelux\/discover_hte [Accessed 15-08-2025]"},{"key":"R17","unstructured":"Tibshirani J Athey S Sverdrup E Wager S . Grf: generalized random forests. 2.3.2 ed. GitHub. 2024. [Accessed 15-08-2025]"},{"key":"R18","doi-asserted-by":"publisher","DOI":"10.2196\/59476","article-title":"Potential harms of feedback after web-based depression screening: secondary analysis of negative effects in the randomized controlled DISCOVER trial","volume":"27","author":"Sikorski","journal-title":"J Med Internet Res"},{"issue":"6","key":"R19","doi-asserted-by":"publisher","first-page":"2700","DOI":"10.1038\/s41380-022-01528-4","article-title":"Clinical prediction models in psychiatry: a systematic review of two decades of progress and challenges","volume":"27","author":"Meehan","journal-title":"Mol Psychiatry"},{"issue":"1","key":"R20","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-018-0289-1","article-title":"Predicting the naturalistic course of depression from a wide range of clinical, psychological, and biological data: a machine learning approach","volume":"8","author":"Dinga","journal-title":"Transl Psychiatry"},{"issue":"5","key":"R21","doi-asserted-by":"publisher","DOI":"10.1002\/14651858.CD013491.pub2","article-title":"Prognostic models for predicting relapse or recurrence of major depressive disorder in adults","volume":"5","author":"Moriarty","journal-title":"Cochrane Database Syst Rev"},{"issue":"100685","key":"R22","doi-asserted-by":"publisher","first-page":"100685","DOI":"10.1016\/j.invent.2023.100685","article-title":"How adults with suspected depressive disorder experience online depression screening: a qualitative interview study","volume":"34","author":"Sikorski","journal-title":"Internet Interv"}],"container-title":["JMIR AI"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e70001","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:58:19Z","timestamp":1782842299000},"score":1,"resource":{"primary":{"URL":"https:\/\/ai.jmir.org\/2025\/1\/e70001"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":22,"URL":"https:\/\/doi.org\/10.2196\/70001","relation":{},"ISSN":["2817-1705"],"issn-type":[{"value":"2817-1705","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"article-number":"v4i7e70001"}}