{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:52:42Z","timestamp":1782910362740,"version":"3.54.5"},"reference-count":29,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Pediatr."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Parents of children with immune thrombocytopenia (ITP) increasingly turn to freely available large language models (LLMs) when they need quick explanations. In pediatric hematology, such advice must be clear, safe, and aligned with clinical guidance, not simply fluent.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>To assess the quality, safety, readability, and guideline\/reference concordance of freely accessible LLM responses to parent-oriented questions about childhood ITP, as an evaluation of parent-facing educational content rather than diagnostic or predictive AI performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Forty standardized parent-facing ITP questions were submitted once to GPT-5.3-mini, Gemini 3 Flash, and Claude Sonnet 4.6 through free public web interfaces. Reporting followed STROBE and was cross-mapped to relevant TRIPOD-LLM items. Three model-name-blinded clinical reviewers independently rated 120 responses using the study-specific, expert-developed seven-domain AI-ITP Parent Response Score (AI-ITP-PRS; range, 7\u201335) and recorded unsafe-content and hallucination flags. Readability was measured with automated indices. Paired model comparisons used the Friedman test with Holm-adjusted Wilcoxon analyses; repeated-measures ANOVA and mixed-effects models were used as sensitivity analyses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      All 360 reviewer-level assessments were complete. The unweighted clinical-communication composite AI-ITP-PRS differed significantly across models (Friedman chi-square\u2009=\u200963.52,\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&amp;lt;\u20090.001; Kendall's W\u2009=\u20090.794). Gemini 3 Flash had the highest mean composite score (32.78\u2009\u00b1\u20092.54), followed by Claude Sonnet 4.6 (30.60\u2009\u00b1\u20091.39) and GPT-5.3-mini (29.98\u2009\u00b1\u20091.52), but this difference was driven primarily by completeness, comprehensibility, empathy\/supportiveness, and objective readability. Medical accuracy, guideline\/reference concordance, safety\/emergency triage, and low harmful misinformation risk were largely similar across models. Two response-level unsafe-content and hallucination events were detected, both in Gemini 3 Flash responses (2\/40, 5.0%; exact 95% CI, 0.6%\u201316.9%). The matched categorical comparison was not statistically significant, so these rare-event findings were interpreted descriptively and as hypothesis-generating. The events involved overgeneralized autoimmune-testing advice and unsupported MMR vaccination counseling.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Freely accessible LLMs can produce supportive, high-scoring parent-facing explanations about childhood ITP. However, the highest composite score in this single-response snapshot reflected stronger communication performance rather than definitive superiority across safety-sensitive domains. This study detected high-impact safety failure modes but cannot precisely estimate true safety-event rates, establish robust rare-event safety differences between models, or define stable model behavior across repeated generations.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fped.2026.1889520","type":"journal-article","created":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:29:26Z","timestamp":1782908966000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Freely accessible large language models for parent education in pediatric immune thrombocytopenia: an expert-rated cross-sectional study of safety, readability, and guideline concordance"],"prefix":"10.3389","volume":"14","author":[{"given":"Orkun","family":"Din\u00e7","sequence":"first","affiliation":[{"name":"Department of Pediatric Hematology and Oncology, Van Education and Research Hospital","place":["Van, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eray","family":"Akay","sequence":"additional","affiliation":[{"name":"Department of Pediatric Hematology and Oncology, Bilkent City Hospital","place":["Ankara, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Belen","family":"Ates","sequence":"additional","affiliation":[{"name":"Department of Pediatrics, Prof. Dr. Cemil Ta\u015fc\u0131o\u011flu City Hospital","place":["\u0130stanbul, T\u00fcrkiye"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,7,1]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"3829","DOI":"10.1182\/bloodadvances.2019000966","article-title":"American Society of Hematology 2019 guidelines for immune thrombocytopenia","volume":"3","author":"Neunert","year":"2019","journal-title":"Blood Adv"},{"key":"B2","doi-asserted-by":"publisher","first-page":"3780","DOI":"10.1182\/bloodadvances.2019000812","article-title":"Updated international consensus report on the investigation and management of primary immune thrombocytopenia","volume":"3","author":"Provan","year":"2019","journal-title":"Blood Adv"},{"key":"B3","doi-asserted-by":"publisher","first-page":"2386","DOI":"10.1182\/blood-2008-07-162503","article-title":"Standardization of terminology, definitions and outcome criteria in immune thrombocytopenic purpura of adults and children: report from an international working group","volume":"113","author":"Rodeghiero","year":"2009","journal-title":"Blood"},{"key":"B4","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1111\/j.1365-2141.2010.08176.x","article-title":"Epidemiology of paediatric immune thrombocytopenia in the general practice research database","volume":"149","author":"Yong","year":"2010","journal-title":"Br J Haematol"},{"key":"B5","doi-asserted-by":"publisher","first-page":"2377","DOI":"10.1111\/j.1538-7836.2006.02147.x","article-title":"Prevalence of immune thrombocytopenia: analyses of administrative data","volume":"4","author":"Segal","year":"2006","journal-title":"J Thromb Haemost"},{"key":"B6","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1111\/jth.12813","article-title":"Severe bleeding events in adults and children with primary immune thrombocytopenia: a systematic review","volume":"13","author":"Neunert","year":"2015","journal-title":"J Thromb Haemost"},{"key":"B7","doi-asserted-by":"publisher","first-page":"e26736","DOI":"10.1002\/pbc.26736","article-title":"Predictors of remission in children with newly diagnosed immune thrombocytopenia: data from the intercontinental cooperative ITP study group registry II participants","volume":"65","author":"Bennett","year":"2018","journal-title":"Pediatr Blood Cancer"},{"key":"B8","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1038\/s41586-023-06291-2","article-title":"Large language models encode clinical knowledge","volume":"620","author":"Singhal","year":"2023","journal-title":"Nature"},{"key":"B9","doi-asserted-by":"publisher","first-page":"589","DOI":"10.1001\/jamainternmed.2023.1838","article-title":"Comparing physician and artificial intelligence chatbot responses to patient questions posted to a public social media forum","volume":"183","author":"Ayers","year":"2023","journal-title":"JAMA Intern Med"},{"key":"B10","volume-title":"Ethics and Governance of Artificial Intelligence for Health: Guidance on Large Multi-modal models","year":"2025"},{"key":"B11","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41591-024-03425-5","article-title":"The TRIPOD-LLM reporting guideline for studies using large language models","volume":"31","author":"Gallifant","year":"2025","journal-title":"Nat Med"},{"key":"B12","doi-asserted-by":"publisher","first-page":"e296","DOI":"10.1371\/journal.pmed.0040296","article-title":"The strengthening the reporting of observational studies in epidemiology statement: guidelines for reporting observational studies","volume":"4","author":"von Elm","year":"2007","journal-title":"PLoS Med"},{"key":"B13","doi-asserted-by":"publisher","first-page":"4190","DOI":"10.1182\/blood-2010-08-302984","article-title":"The American Society of Hematology 2011 evidence-based practice guideline for immune thrombocytopenia","volume":"117","author":"Neunert","year":"2011","journal-title":"Blood"},{"key":"B14","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","article-title":"A guideline of selecting and reporting intraclass correlation coefficients for reliability research","volume":"15","author":"Koo","year":"2016","journal-title":"J Chiropr Med"},{"key":"B15","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","article-title":"Measuring nominal scale agreement among many raters","volume":"76","author":"Fleiss","year":"1971","journal-title":"Psychol Bull"},{"key":"B16","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1348\/000711006X126600","article-title":"Computing inter-rater reliability and its variance in the presence of high agreement","volume":"61","author":"Gwet","year":"2008","journal-title":"Br J Math Stat Psychol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1037\/h0026256","article-title":"Weighted kappa: nominal scale agreement with provision for scaled disagreement or partial credit","volume":"70","author":"Cohen","year":"1968","journal-title":"Psychol Bull"},{"key":"B18","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1080\/19312450709336664","article-title":"Answering the call for a standard reliability measure for coding data","volume":"1","author":"Hayes","year":"2007","journal-title":"Commun Methods Meas"},{"key":"B19","doi-asserted-by":"publisher","first-page":"65","DOI":"10.2307\/4615733","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"Holm","year":"1979","journal-title":"Scand J Stat"},{"key":"B20","doi-asserted-by":"publisher","first-page":"1613150","DOI":"10.3389\/fped.2025.1613150","article-title":"Applications of artificial intelligence in early childhood health management: a systematic review from fetal to pediatric periods","volume":"13","author":"Wang","year":"2025","journal-title":"Front Pediatr"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1679463","DOI":"10.3389\/fped.2025.1679463","article-title":"Study on the influencing factors of the first-line treatment response to primary immune thrombocytopenia in children","volume":"13","author":"Zhang","year":"2025","journal-title":"Front Pediatr"},{"key":"B22","doi-asserted-by":"publisher","first-page":"1461026","DOI":"10.3389\/fped.2025.1461026","article-title":"A clinician-based comparative study of large language models in answering medical questions: the case of asthma","volume":"13","author":"Yin","year":"2025","journal-title":"Front Pediatr"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1610671","DOI":"10.3389\/fdgth.2025.1610671","article-title":"Evaluating large language models in pediatric fever management: a two-layer study","volume":"7","author":"Yang","year":"2025","journal-title":"Front Digit Health"},{"key":"B24","doi-asserted-by":"publisher","first-page":"1694035","DOI":"10.3389\/fped.2025.1694035","article-title":"The effectiveness of artificial intelligence models in addressing the concerns of families of children with cerebral palsy: a comparative analysis of ChatGPT, Gemini, and DeepSeek","volume":"13","author":"Erem","year":"2025","journal-title":"Front Pediatr"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1659812","DOI":"10.3389\/fped.2025.1659812","article-title":"Reliability of ChatGPT answers to common questions on developmental dysplasia of the hip as an information source for parents","volume":"13","author":"Vertesich","year":"2025","journal-title":"Front Pediatr"},{"key":"B26","doi-asserted-by":"publisher","first-page":"1654482","DOI":"10.3389\/fpubh.2025.1654482","article-title":"Parents\u2019 understanding and attitudes toward the application of AI in pediatric healthcare: a cross-sectional survey study","volume":"13","author":"Huang","year":"2025","journal-title":"Front Public Health"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1646989","DOI":"10.3389\/fped.2025.1646989","article-title":"Critical conversations: a user-centric approach to chatbots for history taking in the pediatric intensive care unit","volume":"13","author":"Collins","year":"2025","journal-title":"Front Pediatr"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1739217","DOI":"10.3389\/fped.2026.1739217","article-title":"Should we leave paediatric emergency triage to artificial intelligence? A comparison of ChatGPT 4o and Grok 3","volume":"14","author":"Aygun","year":"2026","journal-title":"Front Pediatr"},{"key":"B29","doi-asserted-by":"publisher","first-page":"1519751","DOI":"10.3389\/fped.2025.1519751","article-title":"Enhancing pediatric asthma management in underdeveloped regions through ChatGPT training for doctors: a randomized controlled trial","volume":"13","author":"Zhang","year":"2025","journal-title":"Front Pediatr"}],"container-title":["Frontiers in Pediatrics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1889520\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T12:29:28Z","timestamp":1782908968000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fped.2026.1889520\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,1]]},"references-count":29,"alternative-id":["10.3389\/fped.2026.1889520"],"URL":"https:\/\/doi.org\/10.3389\/fped.2026.1889520","relation":{},"ISSN":["2296-2360"],"issn-type":[{"value":"2296-2360","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,1]]},"article-number":"1889520"}}