{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T05:44:40Z","timestamp":1792215880688,"version":"4.4.0"},"reference-count":10,"publisher":"Wiley","issue":"8","license":[{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T00:00:00Z","timestamp":1785369600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Early Intervention Psych"],"published-print":{"date-parts":[[2026,8]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This study aimed to evaluate the quality of GPT\u20104\u2013generated responses to commonly asked psychosis\u2010related psychoeducational questions from patients, caregivers and relatives in a first\u2010episode psychosis programme. Evaluation focused on accuracy, clarity, inclusivity, completeness, clinical utility and overall quality.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Design<\/jats:title>\n                    <jats:p>This cross\u2010sectional study employed a qualitative evaluation design. GPT\u20104, accessed via the ChatGPT interface, generated responses to 20 psychosis\u2010related psychoeducational questions. These questions were developed through iterative discussion and consensus among clinicians working in a first\u2010episode psychosis treatment programme, informed by commonly encountered questions from patients, caregivers and relatives in clinical practice and are provided in Appendix\u00a0A. The generated responses were subsequently evaluated for their potential clinical applicability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Primary Outcome<\/jats:title>\n                    <jats:p>ChatGPT was presented with 20 psychoeducational questions derived from real\u2010world clinical interactions with patients, caregivers and relatives. Two experts in psychosis independently assessed the responses using a structured six\u2010domain rubric: accuracy (1\u20133), clarity (1\u20133), inclusivity (1\u20133), completeness (0\u20131), clinical utility (1\u20135) and overall quality (1\u20134), where lower scores indicate poorer performance and higher scores indicate stronger performance across domains. Discrepancies in ratings were resolved through discussion and consensus.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Using a structured evaluation rubric,\n                      <jats:styled-content style=\"fixed-case\">LLM<\/jats:styled-content>\n                      \u2010generated responses were assessed across accuracy, clarity, inclusivity, completeness, clinical utility and overall quality. Responses were generally coherent, well\u2010organized and readable across all 20 psychoeducational questions. Performance was strongest in accuracy (M \u00b1\n                      <jats:styled-content style=\"fixed-case\">SD<\/jats:styled-content>\n                      =\u20092.88\u2009\u00b1\u20090.22), clarity (2.93 \u00b1\u20090.18), completeness (0.93 \u00b1\u20090.18) and clinical utility (4.35 \u00b1\u20090.52), indicating that responses were largely correct, understandable and clinically relevant. Inclusivity scores were comparatively lower (2.30 \u00b1\u20090.41). A descriptive linguistic analysis showed that responses were written at a relatively high Flesch\u2013Kincaid Grade Level (\n                      <jats:styled-content style=\"fixed-case\">FKGL<\/jats:styled-content>\n                      ) (mean\u2009=\u200915.59 \u00b1\u20091.59), indicating increased reading complexity. Although responses addressed core aspects of the questions, some lacked sufficient nuance for complex or individualized clinical scenarios.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>GPT\u20104, as an example of a large language model (LLM), may have a limited adjunctive role in supporting psychoeducation for psychosis when used within structured and clinician\u2010guided contexts. Although responses were generally readable and clinically relevant, their complexity and variability in inclusivity highlight potential limitations in accessibility for diverse patient populations, and cautious use is warranted given the ongoing concerns regarding accuracy, safety and real\u2010world implementation. Further research is needed before broader clinical integration can be recommended.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/eip.70230","type":"journal-article","created":{"date-parts":[[2026,7,30]],"date-time":"2026-07-30T13:53:26Z","timestamp":1785419606000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Large Language Models for Individualized Psychoeducational Tools for Psychosis: A Cross\u2010Sectional Study"],"prefix":"10.1111","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5007-5041","authenticated-orcid":false,"given":"Musa","family":"Yilanli","sequence":"first","affiliation":[{"name":"Nationwide Children's Hospital  Columbus Ohio USA"},{"name":"The Ohio State University College of Medicine  Columbus Ohio USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian","family":"McKay","sequence":"additional","affiliation":[{"name":"Nationwide Children's Hospital  Columbus Ohio USA"},{"name":"The Ohio State University College of Medicine  Columbus Ohio USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4751-1063","authenticated-orcid":false,"given":"Daniel I.","family":"Jackson","sequence":"additional","affiliation":[{"name":"The Abigail Wexner Research Institute, Nationwide Children's Hospital  Columbus Ohio USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8798-9605","authenticated-orcid":false,"given":"Emre","family":"Sezgin","sequence":"additional","affiliation":[{"name":"Nationwide Children's Hospital  Columbus Ohio USA"},{"name":"The Ohio State University College of Medicine  Columbus Ohio USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,30]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-32-9721-0_6"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00127-014-0928-7"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bpsc.2021.02.001"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1097\/YCT.0000000000000941"},{"issue":"5","key":"e_1_2_8_6_1","first-page":"1115","article-title":"Artificial Intelligence and the Risk of Delusion Reinforcement in Psychiatry","volume":"49","author":"\u00d8stergaard S. D.","year":"2023","journal-title":"Schizophrenia Bulletin"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1111\/acps.70022"},{"issue":"1","key":"e_1_2_8_8_1","first-page":"70","article-title":"Psychotic Spectrum Disorders: Definitions, Classifications, Neural Correlates and Clinical Profiles","volume":"4","author":"Perrotta G.","year":"2020","journal-title":"Annals of Psychiatry and Treatment"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1002\/cam4.70554"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.2196\/51243"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1002\/wps.20883"}],"container-title":["Early Intervention in Psychiatry"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/eip.70230","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/eip.70230","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/eip.70230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T05:24:09Z","timestamp":1792214649000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/eip.70230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,30]]},"references-count":10,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,8]]}},"alternative-id":["10.1111\/eip.70230"],"URL":"https:\/\/doi.org\/10.1111\/eip.70230","archive":["Portico"],"relation":{"has-preprint":[{"id-type":"doi","id":"10.22541\/au.174002762.28205569\/v1","asserted-by":"object"}]},"ISSN":["1751-7885","1751-7893"],"issn-type":[{"value":"1751-7885","type":"print"},{"value":"1751-7893","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,30]]},"assertion":[{"value":"2025-02-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70230"}}