{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T12:03:22Z","timestamp":1790165002433,"version":"4.1.0"},"reference-count":48,"publisher":"Cambridge University Press (CUP)","issue":"14","license":[{"start":{"date-parts":[[2018,11,5]],"date-time":"2018-11-05T00:00:00Z","timestamp":1541376000000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Psychol. Med."],"published-print":{"date-parts":[[2019,10]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec id=\"S003329171800315X_sec_a1\"><jats:title>Background<\/jats:title><jats:p>Some Internet interventions are regarded as effective treatments for adult depression, but less is known about who responds to this form of treatment.<\/jats:p><\/jats:sec><jats:sec id=\"S003329171800315X_sec_a2\" sec-type=\"methods\"><jats:title>Method<\/jats:title><jats:p>An elastic net and random forest were trained to predict depression symptoms and related disability after an 8-week course of an Internet intervention, Deprexis, involving adults (<jats:italic>N<\/jats:italic> = 283) from across the USA. Candidate predictors included psychopathology, demographics, treatment expectancies, treatment usage, and environmental context obtained from population databases. Model performance was evaluated using predictive <jats:italic>R<\/jats:italic><jats:sup>2<\/jats:sup> <jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"gif\" xlink:href=\"S003329171800315X_inline1a\" xlink:type=\"simple\"\/><jats:tex-math>$\\lpar R_{{\\rm pred}}^2\\rpar\\comma $<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula> the expected variance explained in a <jats:italic>new<\/jats:italic> sample, estimated by 10 repetitions of 10-fold cross-validation.<\/jats:p><\/jats:sec><jats:sec id=\"S003329171800315X_sec_a3\" sec-type=\"results\"><jats:title>Results<\/jats:title><jats:p>An ensemble model was created by averaging the predictions of the elastic net and random forest. Model performance was compared with a benchmark linear autoregressive model that predicted each outcome using only its baseline. The ensemble predicted more variance in post-treatment depression (8.0% gain, 95% CI 0.8\u201315; total <jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"gif\" xlink:href=\"S003329171800315X_inline1\" xlink:type=\"simple\"\/><jats:tex-math>$R_{{\\rm pred}}^2 \\; $<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula>= 0.25), disability (5.0% gain, 95% CI \u22120.3 to 10; total <jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"gif\" xlink:href=\"S003329171800315X_inline2\" xlink:type=\"simple\"\/><jats:tex-math>$R_{{\\rm pred}}^2 \\; $<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula>= 0.25), and well-being (11.6% gain, 95% CI 4.9\u201319; total <jats:inline-formula><jats:alternatives><jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mime-subtype=\"gif\" xlink:href=\"S003329171800315X_inline3\" xlink:type=\"simple\"\/><jats:tex-math>$R_{{\\rm pred}}^2 \\; $<\/jats:tex-math><\/jats:alternatives><\/jats:inline-formula>= 0.29) than the benchmark model. Important predictors included comorbid psychopathology, particularly total psychopathology and dysthymia, low symptom-related disability, treatment credibility, lower access to therapists, and time spent using certain Deprexis modules.<\/jats:p><\/jats:sec><jats:sec id=\"S003329171800315X_sec_a4\" sec-type=\"conclusion\"><jats:title>Conclusion<\/jats:title><jats:p>A number of variables predict symptom improvement following an Internet intervention, but each of these variables makes relatively small contributions. Machine learning ensembles may be a promising statistical approach for identifying the cumulative contribution of many weak predictors to psychosocial depression treatment response.<\/jats:p><\/jats:sec>","DOI":"10.1017\/s003329171800315x","type":"journal-article","created":{"date-parts":[[2018,11,5]],"date-time":"2018-11-05T04:57:27Z","timestamp":1541393847000},"page":"2330-2341","source":"Crossref","is-referenced-by-count":81,"title":["A machine learning ensemble to predict treatment outcomes following an Internet intervention for depression"],"prefix":"10.1017","volume":"49","author":[{"given":"Rahel","family":"Pearson","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek","family":"Pisner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bj\u00f6rn","family":"Meyer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jason","family":"Shumake","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4480-0902","authenticated-orcid":false,"given":"Christopher G.","family":"Beevers","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2018,11,5]]},"reference":[{"key":"S003329171800315X_ref39","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btr597"},{"key":"S003329171800315X_ref40","first-page":"1365","volume":"72","year":"2004","journal-title":"Blackwell Publishing Journal of Personality"},{"key":"S003329171800315X_ref9","first-page":"59","volume":"2","year":"2007","journal-title":"Cancer Informatics"},{"key":"S003329171800315X_ref37","doi-asserted-by":"publisher","DOI":"10.1159\/000334909"},{"key":"S003329171800315X_ref8","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-clinpsy-050817-084746"},{"key":"S003329171800315X_ref7","doi-asserted-by":"publisher","DOI":"10.1016\/S2215-0366(15)00471-X"},{"key":"S003329171800315X_ref36","first-page":"89","volume":"11","year":"1996","journal-title":"International Clinical Psychopharmacology"},{"key":"S003329171800315X_ref6","first-page":"2079","volume":"11","year":"2010","journal-title":"Journal of Machine Learning Research"},{"key":"S003329171800315X_ref35","doi-asserted-by":"publisher","DOI":"10.1093\/aje\/kwt312"},{"key":"S003329171800315X_ref5","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"S003329171800315X_ref34","doi-asserted-by":"publisher","DOI":"10.1001\/jamapsychiatry.2016.0316"},{"key":"S003329171800315X_ref3","first-page":"51","volume-title":"Proceedings of the 20th International Conference on Machine Learning","year":"2003"},{"key":"S003329171800315X_ref32","first-page":"18","volume":"2","year":"2002","journal-title":"R News"},{"key":"S003329171800315X_ref2","doi-asserted-by":"publisher","DOI":"10.1037\/ccp0000171"},{"key":"S003329171800315X_ref31","first-page":"121","volume":"3","year":"2016","journal-title":"Psychology of Consciousness: Theory, Research, and Practice"},{"key":"S003329171800315X_ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinph.2013.04.010"},{"key":"S003329171800315X_ref29","doi-asserted-by":"publisher","DOI":"10.1017\/S2045796016000020"},{"key":"S003329171800315X_ref28","first-page":"351","volume":"4","year":"2017","journal-title":"JAMA Psychiatry"},{"key":"S003329171800315X_ref27","doi-asserted-by":"publisher","DOI":"10.32614\/RJ-2013-014"},{"key":"S003329171800315X_ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.brat.2013.01.006"},{"key":"S003329171800315X_ref25","volume-title":"An Introduction to Statistical Learning","volume":"103","year":"2013"},{"key":"S003329171800315X_ref24","doi-asserted-by":"publisher","DOI":"10.1136\/amiajnl-2014-002733"},{"key":"S003329171800315X_ref23","volume-title":"The Elements of Statistical Learning","year":"2009"},{"key":"S003329171800315X_ref22","doi-asserted-by":"publisher","DOI":"10.1136\/jnnp.23.1.56"},{"key":"S003329171800315X_ref21","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1006304"},{"key":"S003329171800315X_ref52","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"},{"key":"S003329171800315X_ref20","doi-asserted-by":"publisher","DOI":"10.1198\/tast.2009.08199"},{"key":"S003329171800315X_ref51","doi-asserted-by":"publisher","DOI":"10.1053\/comp.2001.23126"},{"key":"S003329171800315X_ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpr.2005.03.002"},{"key":"S003329171800315X_ref18","first-page":"1","volume":"33","year":"2010","journal-title":"Journal of Statistical Software"},{"key":"S003329171800315X_ref49","volume-title":"ggplot2: Elegant Graphics for Data Analysis","year":"2009"},{"key":"S003329171800315X_ref17","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291710000553"},{"key":"S003329171800315X_ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.ress.2015.05.018"},{"key":"S003329171800315X_ref16","doi-asserted-by":"publisher","DOI":"10.1037\/ccp0000026"},{"key":"S003329171800315X_ref47","doi-asserted-by":"publisher","DOI":"10.1037\/a0012570"},{"key":"S003329171800315X_ref15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0178806"},{"key":"S003329171800315X_ref46","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen-2013-002847"},{"key":"S003329171800315X_ref14","doi-asserted-by":"publisher","DOI":"10.2196\/jmir.2771"},{"key":"S003329171800315X_ref45","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2105-7-91"},{"key":"S003329171800315X_ref13","doi-asserted-by":"publisher","DOI":"10.1016\/S0005-7916(00)00012-4"},{"key":"S003329171800315X_ref44","first-page":"1","volume":"6","year":"2007","journal-title":"Statistical Applications in Genetics and Molecular Biology"},{"key":"S003329171800315X_ref12","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0184604"},{"key":"S003329171800315X_ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0962280206074463"},{"key":"S003329171800315X_ref11","doi-asserted-by":"publisher","DOI":"10.1126\/science.2648573"},{"key":"S003329171800315X_ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2017.06.081"},{"key":"S003329171800315X_ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.beth.2016.04.007"},{"key":"S003329171800315X_ref41","doi-asserted-by":"publisher","DOI":"10.1176\/appi.ajp.163.1.28"},{"key":"S003329171800315X_ref38","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291706008944"}],"container-title":["Psychological Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S003329171800315X","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,26]],"date-time":"2019-09-26T06:43:50Z","timestamp":1569480230000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S003329171800315X\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,5]]},"references-count":48,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["S003329171800315X"],"URL":"https:\/\/doi.org\/10.1017\/s003329171800315x","relation":{},"ISSN":["0033-2917","1469-8978"],"issn-type":[{"value":"0033-2917","type":"print"},{"value":"1469-8978","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,11,5]]}}}