{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T02:38:40Z","timestamp":1792550320577,"version":"4.5.0"},"reference-count":0,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T00:00:00Z","timestamp":1792454400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T00:00:00Z","timestamp":1792454400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["acrjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Arthritis Care &amp;amp; Research"],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Our objective was to evaluate the ability of different large language models (LLMs) to translate and analyze qualitative interviews describing pregnancy experiences among women with systemic lupus erythematosus (SLE). An additional objective was to compare themes identified by LLMs with those identified by human researchers.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We analyzed 26 semi\u2010structured interviews originally conducted in Portuguese by Rodrigues et al. among women with SLE exploring their perinatal care experiences. Three prompting strategies (zero\u2010shot, few\u2010shot, and chain\u2010of\u2010thought) were used on the transcripts across four state\u2010of\u2010the\u2010art LLMs (GPT\u20104o, Claude Sonnet 4.5, Gemini 2.5 Flash, and DeepSeek R) to generate key themes. Model outputs were evaluated using an LLM\u2010as\u2010a\u2010judge framework assessing thematic coverage, thematic unity, and semantic similarity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Across models and prompting strategies, LLMs generated similar themes that closely aligned with those identified by human researchers. LLM\u2010as\u2010a\u2010judge evaluations demonstrated high thematic unity and semantic similarity. Claude Sonnet 4.5 showed the most consistent performance. Few\u2010shot prompting consistently outperformed zero\u2010shot and chain\u2010of\u2010thought approaches.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>LLMs show promise as supportive tools for analyzing qualitative research by preserving thematic coherence and capturing the complexity of pregnancy experiences in women with SLE. Although zero\u2010shot prompting is widely used, it produced lower thematic results in our study, whereas few\u2010shot prompting achieved the most comprehensive and coherent theme extraction. LLM\u2010assisted qualitative analysis may complement human interpretation and has the potential to support the inclusion of non\u2010English language data and diverse patient perspectives in lupus research.<\/jats:p>\n                    <jats:p>\n                      <jats:boxed-text content-type=\"graphic\" position=\"anchor\">\n                        <jats:graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" mimetype=\"image\/png\" position=\"anchor\" specific-use=\"enlarged-web-image\" xlink:href=\"graphic\/acr80193-toc-0001-m.png\">\n                          <jats:alt-text>image<\/jats:alt-text>\n                        <\/jats:graphic>\n                      <\/jats:boxed-text>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1002\/acr.80193","type":"journal-article","created":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T01:59:10Z","timestamp":1792547950000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Using Artificial Intelligence in Qualitative Lupus Pregnancy Research: The Potential of Large Language Models and Prompting Strategies"],"prefix":"10.1002","author":[{"given":"Julia Romina M.","family":"Boers","sequence":"first","affiliation":[{"name":"Weill Medical College of Cornell University New York US"},{"name":"Amsterdam UMC location Vrije Universiteit Amsterdam  Amsterdam The Netherlands"},{"name":"Amsterdam Reproduction and Development Research Institute  Amsterdam The Netherlands"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Grace","family":"Terry","sequence":"additional","affiliation":[{"name":"Weill Medical College of Cornell University New York US"},{"name":"Hunter College  New York US"},{"name":"CUNY Graduate Center  New York US"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Larissa","family":"Rodrigues","sequence":"additional","affiliation":[{"name":"niversidade Estadual de Campinas\/UNICAMP  Campinas Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fernanda","family":"Surita","sequence":"additional","affiliation":[{"name":"niversidade Estadual de Campinas\/UNICAMP  Campinas Brazil"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jainesh","family":"Doshi","sequence":"additional","affiliation":[{"name":"Hospital for Special Surgery  New York NY"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2535-0974","authenticated-orcid":false,"given":"Bella","family":"Mehta","sequence":"additional","affiliation":[{"name":"Hospital for Special Surgery  New York NY"},{"name":"NY Weill Cornell Medicine  New York US"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,10,20]]},"container-title":["Arthritis Care &amp; Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acr.80193","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/acr.80193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T01:59:11Z","timestamp":1792547951000},"score":1,"resource":{"primary":{"URL":"https:\/\/acrjournals.onlinelibrary.wiley.com\/doi\/10.1002\/acr.80193"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,20]]},"references-count":0,"alternative-id":["10.1002\/acr.80193"],"URL":"https:\/\/doi.org\/10.1002\/acr.80193","archive":["Portico"],"relation":{},"ISSN":["2151-464X","2151-4658"],"issn-type":[{"value":"2151-464X","type":"print"},{"value":"2151-4658","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,20]]},"assertion":[{"value":"2026-03-06","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-10-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"acr.80193"}}