{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T20:45:30Z","timestamp":1786999530683,"version":"build-2736575974"},"reference-count":23,"publisher":"Cambridge University Press (CUP)","license":[{"start":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T00:00:00Z","timestamp":1765411200000},"content-version":"unspecified","delay-in-days":344,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["Psychol. Med."],"published-print":{"date-parts":[[2025]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec id=\"S0033291725102742_sec1\">\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Machine learning (ML) models show promise in predicting post-traumatic stress disorder (PTSD) treatment outcomes, but it is unknown how their predictions compare to those of clinicians. This study directly compared the accuracy of clinicians\u2019 predictions of patient treatment outcomes with those of three ML models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"S0033291725102742_sec2\" sec-type=\"methods\">\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Twenty clinicians providing cognitive processing therapy repeatedly predicted outcomes for 194 veterans. We compared their accuracy against three ML models on two key endpoints: clinically meaningful symptom reduction (\u226510-point PCL-5 decrease) and posttreatment severity (final PCL-5\u00a0&lt;\u00a033). Clinician predictions were compared against a recurrent neural network, a mixed-effects random forest, and a generalized linear mixed-effects model. We analyzed prediction accuracy and the association between clinician confidence and accuracy using logistic mixed-effects models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"S0033291725102742_sec3\" sec-type=\"results\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      ML models were significantly more accurate than clinicians at predicting whether a patient\u2019s posttreatment PCL-5 score would be below 33 (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0&lt;\u00a0.001). However, no significant difference in accuracy was found for predicting a \u226510-point symptom reduction (\n                      <jats:italic>p<\/jats:italic>\n                      \u00a0=\u00a0.734). Clinician confidence increased throughout treatment and was significantly associated with greater prediction accuracy for both outcomes (ORs\u00a0=\u00a01.06,\n                      <jats:italic>p<\/jats:italic>\n                      s\u00a0&lt;\u00a0.001).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"S0033291725102742_sec4\" sec-type=\"conclusions\">\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>ML models can outperform clinicians in predicting posttreatment symptom severity, particularly early in treatment, suggesting they could be a useful tool for identifying patients at risk for suboptimal outcomes. However, ML models were not superior in predicting symptom reduction, where clinicians also performed at a high level. Findings support the selective use of ML to enhance, rather than replace, clinical judgment in PTSD treatment.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1017\/s0033291725102742","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T06:23:10Z","timestamp":1765434190000},"update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":1,"title":["When does machine learning outperform clinicians? A comparison of prediction accuracy for PTSD treatment outcomes"],"prefix":"10.1017","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3974-1802","authenticated-orcid":false,"given":"Philip","family":"Held","sequence":"first","affiliation":[{"name":"Rush University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0854-9973","authenticated-orcid":false,"given":"Dale L.","family":"Smith","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6777-3636","authenticated-orcid":false,"given":"Daniel R.","family":"Szoke","sequence":"additional","affiliation":[{"name":"Rush University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2640-8050","authenticated-orcid":false,"given":"Sarah A.","family":"Pridgen","sequence":"additional","affiliation":[{"name":"Rush University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"56","published-online":{"date-parts":[[2025,12,11]]},"reference":[{"key":"S0033291725102742_r1","doi-asserted-by":"publisher","DOI":"10.1080\/16506073.2018.1522371"},{"key":"S0033291725102742_r13","volume-title":"Cognitive processing therapy for PTSD: A comprehensive therapist manual","author":"Resick","year":"2024"},{"key":"S0033291725102742_r2","doi-asserted-by":"publisher","DOI":"10.1126\/science.2648573"},{"key":"S0033291725102742_r16","doi-asserted-by":"publisher","DOI":"10.1037\/a0030359"},{"key":"S0033291725102742_r15","doi-asserted-by":"publisher","DOI":"10.1037\/tra0001864"},{"key":"S0033291725102742_r4","volume-title":"Longitudinal data analysis","author":"Hedeker","year":"2006"},{"key":"S0033291725102742_r6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2021.07.004"},{"key":"S0033291725102742_r5","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2022.03.066"},{"key":"S0033291725102742_r11","unstructured":"National Center for PTSD. (n.d.). PTSD Checklist for DSM-5 (PCL-5). https:\/\/www.ptsd.va.gov\/professional\/assessment\/adult-sr\/ptsd-checklist.asp"},{"key":"S0033291725102742_r12","doi-asserted-by":"publisher","DOI":"10.1016\/j.brat.2021.103920"},{"key":"S0033291725102742_r21","doi-asserted-by":"publisher","DOI":"10.4088\/JCP.12r08225"},{"key":"S0033291725102742_r22","unstructured":"Weathers, F. W. , Litz, B. T. , Keane, T. M. , Palmieri, P. A. , Marx, B. P. , & Schnurr, P. P. (2013). The PTSD Checklist for DSM-5 (PCL-5). Scale available from the National Center for PTSD at www.ptsd.va.gov; https:\/\/www.ptsd.va.gov\/professional\/assessment\/adult-sr\/ptsd-checklist.asp"},{"key":"S0033291725102742_r19","doi-asserted-by":"publisher","DOI":"10.1111\/1529-1006.001"},{"key":"S0033291725102742_r9","doi-asserted-by":"publisher","DOI":"10.1186\/s12888-015-0399-8"},{"key":"S0033291725102742_r23","doi-asserted-by":"publisher","DOI":"10.1017\/S003329172100163X"},{"key":"S0033291725102742_r14","doi-asserted-by":"publisher","DOI":"10.1037\/a0026602"},{"key":"S0033291725102742_r3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpsychires.2014.08.017"},{"key":"S0033291725102742_r7","doi-asserted-by":"publisher","DOI":"10.1037\/tra0001257"},{"key":"S0033291725102742_r18","first-page":"1","article-title":"Moving toward precision PTSD treatment: Predicting veterans\u2019 intensive PTSD treatment response using continuously updating machine learning models","author":"Smith","year":"2022","journal-title":"Psychological Medicine"},{"key":"S0033291725102742_r8","doi-asserted-by":"publisher","DOI":"10.1080\/20008066.2024.2350908"},{"key":"S0033291725102742_r20","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01117-5"},{"key":"S0033291725102742_r17","doi-asserted-by":"publisher","DOI":"10.1016\/j.cbpra.2014.01.010"},{"key":"S0033291725102742_r10","doi-asserted-by":"publisher","DOI":"10.1037\/pas0001098"}],"container-title":["Psychological Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0033291725102742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T06:23:12Z","timestamp":1765434192000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0033291725102742\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":23,"alternative-id":["S0033291725102742"],"URL":"https:\/\/doi.org\/10.1017\/s0033291725102742","relation":{},"ISSN":["0033-2917","1469-8978"],"issn-type":[{"value":"0033-2917","type":"print"},{"value":"1469-8978","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"\u00a9 The Author(s), 2025. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This is an Open Access article, distributed under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives licence (http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0), which permits non-commercial re-use, distribution, and reproduction in any medium, provided that no alterations are made and the original article is properly cited. The written permission of Cambridge University Press or the rights holder(s) must be obtained prior to any commercial use and\/or adaptation of the article.","name":"license","label":"License","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}],"article-number":"e376"}}