{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T12:26:24Z","timestamp":1789475184161,"version":"build-2803163510"},"reference-count":30,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T00:00:00Z","timestamp":1784592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Can J Psychiatry"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Posttraumatic stress disorder (PTSD) is common yet frequently underdiagnosed, in part due to barriers to systematic screening and the reliance on self-report instruments. Large language models (LLMs) have shown promise in extracting clinically relevant information from unstructured language, but their ability to infer item-level PTSD symptom severity from clinical interviews remains unclear.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using the Distress Analysis Interview Corpus\u2014Wizard of Oz (DAIC-WoZ), we analyzed 100 semi-structured clinical interview transcripts paired with item-level PTSD Checklist\u2014Civilian Version (PCL-C) scores. Six LLMs (DeepSeek 3.1, Claude Sonnet 4, LLaMA 4 Scout, GPT-4o, GPT-5, and Gemini 2.5 Flash) used zero-shot prompting to predict all 17 PCL-C items. Performance was assessed for binary symptom endorsement (\u22653 vs.\u2009&lt;\u20093), 5-point Likert prediction, and DSM-IV symptom-cluster analyses using accuracy, F1 score, and Matthews correlation coefficient (MCC).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>For binary prediction, Claude 4 achieved the highest mean accuracy (0.705; 95% CI, 0.681-0.728), followed by DeepSeek 3.1(0.699; 95% CI, 0.675-0.724) and Gemini 2.5 (0.698; 95% CI, 0.677-0.718). For Likert prediction, DeepSeek 3.1 performed best (accuracy = 0.438; 95% CI, 0.401-0.475), only modestly above the majority-class baseline (0.399; 95% CI, 0.355-0.443). Performance varied by symptom domain, with re-experiencing and hyperarousal symptoms generally predicted more accurately than avoidance\/numbing symptoms. Across models, predicted item-level symptom patterns showed a meaningful alignment with observed PCL-C responses despite reduced accuracy in fine-grained severity estimation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Zero-shot LLMs\u2019 performance was insufficient for clinical application in predicting PTSD symptoms from semi-structured interview transcripts. While models showed some ability to capture overall symptom patterns, performance varied across domains and remained limited for fine-grained severity estimation. Given these constraints and the non-trauma-specific nature of the dataset, findings should be interpreted as preliminary, with only modest differences observed between models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Plain Language Summary Title<\/jats:title>\n                    <jats:p>Can Artificial Intelligence Identify PTSD Symptoms from Conversations? A Study Using Clinical Interview Transcripts<\/jats:p>\n                    <jats:sec>\n                      <jats:title>Plain Language Summary<\/jats:title>\n                      <jats:p>Post-traumatic stress disorder (PTSD) is a common mental health condition, but it is often missed in clinical settings. Screening usually relies on questionnaires that patients must complete themselves, which may not always happen due to time, stigma, or discomfort discussing trauma. Researchers are exploring whether artificial intelligence (AI) could help identify PTSD symptoms from conversations instead.<\/jats:p>\n                      <jats:p>In this study, we tested several advanced AI systems, known as large language models, to see if they could estimate PTSD symptoms based on written transcripts of clinical interviews. These interviews were not specifically designed to assess trauma, which makes the task more challenging but closer to real-world situations. We compared the AI predictions to participants' own questionnaire responses about their symptoms.<\/jats:p>\n                      <jats:p>We found that the AI models were somewhat able to recognize general patterns of PTSD symptoms, especially more visible ones like sleep problems or distressing dreams. However, they struggled with more internal or less obvious symptoms, such as avoidance or emotional numbness. Overall, their accuracy was moderate and not reliable enough for clinical use, particularly when trying to estimate how severe symptoms were.<\/jats:p>\n                      <jats:p>Importantly, differences between the AI models were small, and none performed well enough to replace existing screening methods. These findings suggest that while AI may have future potential as a supportive tool, it is not yet ready to be used for diagnosing or screening PTSD on its own.<\/jats:p>\n                      <jats:p>Further research using better data, improved methods, and real clinical settings is needed before this approach could be considered for practical use.<\/jats:p>\n                    <\/jats:sec>\n                  <\/jats:sec>","DOI":"10.1177\/07067437261468897","type":"journal-article","created":{"date-parts":[[2026,7,21]],"date-time":"2026-07-21T11:48:14Z","timestamp":1784634494000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":1,"title":["Zero-Shot Large Language Models for Preliminary Prediction of PTSD Symptoms From Clinical Interview Transcripts: Grands mod\u00e8les de langage sans exemple pour la pr\u00e9diction pr\u00e9liminaire des sympt\u00f4mes de TSPT \u00e0 partir de transcriptions d'entrevues cliniques"],"prefix":"10.1177","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5325-9639","authenticated-orcid":false,"given":"Bazen Gashaw","family":"Teferra","sequence":"first","affiliation":[{"name":"St. Michael's Hospital, Unity Health Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian Kevin","family":"Sidharta","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5064-804X","authenticated-orcid":false,"given":"Wei-Ni","family":"Hsiang","sequence":"additional","affiliation":[{"name":"University of Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9977-9653","authenticated-orcid":false,"given":"Alice","family":"Rueda","sequence":"additional","affiliation":[{"name":"St. Michael's Hospital, Unity Health Toronto"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9761-2577","authenticated-orcid":false,"given":"Beier","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Alberta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2421-157X","authenticated-orcid":false,"given":"Yanbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Alberta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lisa","family":"Burback","sequence":"additional","affiliation":[{"name":"University of Alberta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7297-1250","authenticated-orcid":false,"given":"Olga","family":"Winkler","sequence":"additional","affiliation":[{"name":"University of Alberta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9097-900X","authenticated-orcid":false,"given":"Andrew","family":"Greenshaw","sequence":"additional","affiliation":[{"name":"University of Alberta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eric","family":"Vermetten","sequence":"additional","affiliation":[{"name":"Leiden University Medical Center"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rakesh","family":"Jetly","sequence":"additional","affiliation":[{"name":"Institute of Mental Health Research, University of Ottawa, Ottawa, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jitendar","family":"Sareen","sequence":"additional","affiliation":[{"name":"University of Manitoba"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruth","family":"Lanius","sequence":"additional","affiliation":[{"name":"Department of Psychiatry, Western University, London, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard J.","family":"Zeifman","sequence":"additional","affiliation":[{"name":"The New School for Social Research"},{"name":"NYU Grossman School of Medicine"},{"name":"Imperial College London"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Divya","family":"Sharma","sequence":"additional","affiliation":[{"name":"York University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4659-564X","authenticated-orcid":false,"given":"Sri","family":"Krishnan","sequence":"additional","affiliation":[{"name":"Toronto Metropolitan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Candice","family":"Monson","sequence":"additional","affiliation":[{"name":"Toronto Metropolitan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8768-1173","authenticated-orcid":false,"given":"Venkat","family":"Bhat","sequence":"additional","affiliation":[{"name":"St. Michael's Hospital, Unity Health Toronto"},{"name":"Department of Psychiatry, University of Toronto, Toronto, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,7,21]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Mann SK Marwaha R Torrico TJ. Posttraumatic stress disorder. In: StatPearls. Treasure Island (FL): StatPearls Publishing; phttp:\/\/www.ncbi.nlm.nih.gov\/books\/NBK559129\/ (2025 accessed August 29 2025)."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.4088\/PCC.v03n0504"},{"key":"e_1_3_2_4_2","unstructured":"Post-traumatic stress disorder. https:\/\/www.who.int\/news-room\/fact-sheets\/detail\/post-traumatic-stress-disorder (accessed December 5 2025)."},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291717000708"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.30773\/pi.2020.0458"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1002\/jts.2490030314"},{"key":"e_1_3_2_8_2","first-page":"1833","article-title":"Management of posttraumatic stress disorder: Diagnostic and therapeutic issues","volume":"60","author":"Davidson JR","year":"1999","unstructured":"Davidson JR, Connor KM. Management of posttraumatic stress disorder: Diagnostic and therapeutic issues. J Clin Psychiatry. 1999;60:1833-1838.","journal-title":"J Clin Psychiatry"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1002\/da.20837"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.1186\/1471-244X-10-113"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1037\/t02622-000"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.psychres.2022.114994"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1017\/S0033291721002294"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1037\/tra0001734"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.2196\/39998"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000943"},{"key":"e_1_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Tu S Powers A Merrill N et al. Automating PTSD diagnostics in clinical interviews: Leveraging large language models for trauma assessments. In: Proceedings of the 25th Annual Meeting of the Special Interest Group on Discourse and Dialogue. Kyoto Japan: Association for Computational Linguistics p644-663.","DOI":"10.18653\/v1\/2024.sigdial-1.55"},{"key":"e_1_3_2_18_2","unstructured":"DAIC-WOZ Database. https:\/\/dcapswoz.ict.usc.edu\/ (2022 accessed August 29 2025)."},{"key":"e_1_3_2_19_2","doi-asserted-by":"crossref","unstructured":"Gratch J Artstein R Lucas G et al. The distress analysis interview corpus of human and computer interviews. In: Calzolari N Choukri K Declerck T et al. editors. Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC\u201914). Reykjavik Iceland: European Language Resources Association (ELRA); p3123-3128.","DOI":"10.63317\/3o7bccg9xequ"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"DeVault D Artstein R Benn G et al. SimSensei kiosk: a virtual human interviewer for healthcare decision support. In: Proceedings of the 2014 International Conference on Autonomous Agents and Multi-Agent Systems. Richland SC: International Foundation for Autonomous Agents and Multiagent Systems; 2014. p1061-1068.","DOI":"10.65109\/MXIV3169"},{"key":"e_1_3_2_21_2","first-page":"3","article-title":"AVEC 2019 workshop and challenge: State-of-mind, detecting depression with AI, and cross-cultural affect recognition","volume":"9","author":"Ringeval F","year":"2019","unstructured":"Ringeval F, Schuller B, Valstar M, et al. AVEC 2019 workshop and challenge: State-of-mind, detecting depression with AI, and cross-cultural affect recognition. Epub ahead of print. 2019;Proceedings of the 9th International on Audio\/Visual Emotion Challenge and Workshop:3-12. doi:https:\/\/doi.org\/10.48550\/ARXIV.1907.11510.","journal-title":"Epub ahead of print"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/0005-7967(96)00033-2"},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1056\/AIp2401106"},{"key":"e_1_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Chen F Ben-Zeev D Sparks G et al. Detecting PTSD in clinical interviews: A comparative analysis of NLP methods and large language models. Biocomputing 2026: Proceedings of the Pacific SymposiumWorld Scientific; 2025:265-279.","DOI":"10.1142\/9789819824755_0019"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40708-023-00185-9"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10960-004-5795-7"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpsc.2019.09.006"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-024-02754-2"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.janxdis.2004.06.003"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2018.02346"},{"key":"e_1_3_2_31_2","article-title":"Leveraging audio and text modalities in mental health: A study of LLMs performance","author":"Ali AA","year":"2024","unstructured":"Ali AA, Fouda AE, Hanafy RJ, et al. Leveraging audio and text modalities in mental health: A study of LLMs performance. Epub ahead of print. 2024. doi:https:\/\/doi.org\/10.48550\/ARXIV.2412.10417","journal-title":"Epub ahead of print"}],"container-title":["The Canadian Journal of Psychiatry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/07067437261468897","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/07067437261468897","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/07067437261468897","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T14:00:48Z","timestamp":1784815248000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/07067437261468897"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,21]]},"references-count":30,"alternative-id":["10.1177\/07067437261468897"],"URL":"https:\/\/doi.org\/10.1177\/07067437261468897","relation":{},"ISSN":["0706-7437","1497-0015"],"issn-type":[{"value":"0706-7437","type":"print"},{"value":"1497-0015","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,21]]},"article-number":"07067437261468897"}}