{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T14:24:37Z","timestamp":1786112677787,"version":"build-2736575974"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"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. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Large language models (LLMs) are increasingly consulted for pediatric health information, yet their demographic biases remain unsystematically evaluated in pediatric contexts.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To assess bias and variability in childhood obesity risk attribution across seven LLMs (ChatGPT, Claude, DeepSeek, Gemini, GLM, Grok, and Qwen), spanning both Western and Chinese-origin developers; all prompts, including those submitted to the Chinese-origin models, were in English only.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A structured prompt-based experimental design was employed across six clinical domains (general obesity risk, dietary pattern, physical activity, sleep, mental health, and genetic predisposition) and six demographic comparison dimensions (sex, three race\/ethnicity pairings, socioeconomic status, and urban-rural residence). Seventy-eight unique prompts were submitted to each model in triplicate, yielding 1,638 outputs. Neutral prompts were scored on a five-dimension binary rubric (accuracy, representation, stigmatizing\/harmful language, social determinants, cultural fit); comparative prompts were coded for directional risk attribution.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Claude achieved the highest neutral prompt composite score (mean 3.00 \u00b1 0.91) and GLM the lowest (1.44 \u00b1 0.51); between-model differences were statistically significant (Kruskal\u2013Wallis\n                      <jats:italic>H<\/jats:italic>\n                      = 46.21,\n                      <jats:italic>p<\/jats:italic>\n                      &amp;lt; 0.001). All models achieved a 100% Stigmatizing\/Harmful Language pass rate, yet representation and cultural fit were universally weak. Socioeconomic status produced the most consistent attribution pattern (low-income attribution in 40\/42 decisions; decision change rate 19.0%). Most models attributed higher obesity risk to Black and Hispanic\/Latino children across the majority of domains. Urban\u2013rural attribution showed the greatest cross-model directional inconsistency (decision change rate 52.4%), with Western-origin models favoring rural attribution and Chinese-origin models favoring urban attribution.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Publicly accessible English-language web-interface outputs from current LLMs showed systematic demographic patterns in pediatric obesity risk attribution, supporting the need for pre-deployment and post-deployment bias auditing before clinical or consumer health use.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1850996","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T15:30:39Z","timestamp":1785943839000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Same child, different risk: demographic bias in childhood obesity attribution by large language models"],"prefix":"10.3389","volume":"14","author":[{"given":"Can","family":"Wang","sequence":"first","affiliation":[{"name":"School of Nursing, Gansu University of Chinese Medicine, Lanzhou","place":["Gansu, China"]},{"name":"Department of Pediatrics","place":["Gansu Provincial Central Hospital, Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhendong","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Nursing, Gansu University of Chinese Medicine, Lanzhou","place":["Gansu, China"]},{"name":"Department of Pediatrics","place":["Gansu Provincial Central Hospital, Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yan","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Pediatrics","place":["Gansu Provincial Central Hospital, Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Taining","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Pediatrics","place":["Gansu Provincial Central Hospital, Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyan","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Pediatrics","place":["Gansu Provincial Central Hospital, Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Xue","sequence":"additional","affiliation":[{"name":"Department of Pediatrics","place":["Gansu Provincial Central Hospital, Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Nursing, Gansu University of Chinese Medicine, Lanzhou","place":["Gansu, China"]},{"name":"Department of Pediatrics","place":["Gansu Provincial Central Hospital, Lanzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"1027","DOI":"10.1016\/S0140-6736(23)02750-2","article-title":"Worldwide trends in underweight and obesity from 1990 to 2022: a pooled analysis of 3663 population-representative studies with 222 million children, adolescents, and adults","volume":"403","author":"Phelps","year":"2024","journal-title":"Lancet."},{"key":"B2","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1016\/S0140-6736(25)00397-6","article-title":"Global, regional, and national prevalence of child and adolescent overweight and obesity, 1990\u20132021, with forecasts to 2050: a forecasting study for the Global Burden of Disease Study 2021","volume":"405","author":"Kerr","year":"2025","journal-title":"Lancet."},{"key":"B3","unstructured":"Obesity and Overweight Fact Sheet\n          \n          2025"},{"key":"B4","doi-asserted-by":"publisher","first-page":"129","DOI":"10.4274\/jcrpe.1471","article-title":"Overweight and obesity in children and adolescents","volume":"6","author":"G\u00fcng\u00f6r","year":"2014","journal-title":"J Clin Res Paediatr Endocrinol."},{"key":"B5","doi-asserted-by":"publisher","first-page":"e20173459","DOI":"10.1542\/peds.2017-3459","article-title":"Prevalence of obesity and severe obesity in US children, 1999\u20132016","volume":"141","author":"Skinner","year":"2018","journal-title":"Paediatrics."},{"key":"B6","doi-asserted-by":"publisher","first-page":"1670","DOI":"10.1002\/oby.23500","article-title":"Childhood obesity risk factors by race and ethnicity","volume":"30","author":"Pineros-Leano","year":"2022","journal-title":"Obesity."},{"key":"B7","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.7326\/ANNALS-25-00389","article-title":"Obesity prevalence among children and adolescents in the United States, 2011 to 2023","volume":"178","author":"Liu","year":"2025","journal-title":"Ann Intern Med."},{"key":"B8","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1038\/s41366-023-01448-5","article-title":"Paediatric obesity during COVID-19: the role of neighborhood social vulnerability and collective efficacy","volume":"48","author":"Min","year":"2024","journal-title":"Int J Obes."},{"key":"B9","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1007\/s13679-024-00578-9","article-title":"Social and structural determinants of health and social injustices contributing to obesity disparities","volume":"13","author":"Williams","year":"2024","journal-title":"Curr Obes Rep."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat Med."},{"key":"B11","doi-asserted-by":"publisher","first-page":"141","DOI":"10.1038\/s43856-023-00370-1","article-title":"The future landscape of large language models in medicine","volume":"3","author":"Clusmann","year":"2023","journal-title":"Commun Med."},{"key":"B12","doi-asserted-by":"publisher","first-page":"e64290","DOI":"10.2196\/64290","article-title":"Laypeople's use of and attitudes toward large language models and search engines for health queries: survey study","volume":"27","author":"Mendel","year":"2025","journal-title":"J Med Internet Res."},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1101\/2024.08.06.24311544","article-title":"Pilot study of large language models as an age-appropriate explanatory tool for chronic paediatric conditions","author":"Young","year":"2024","journal-title":"medRxiv."},{"key":"B14","doi-asserted-by":"publisher","first-page":"e70554","DOI":"10.1002\/cam4.70554","article-title":"Can large language models aid caregivers of paediatric cancer patients in information seeking? A cross-sectional investigation","volume":"14","author":"Sezgin","year":"2025","journal-title":"Cancer Med."},{"key":"B15","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1038\/s41591-024-03097-1","article-title":"Evaluation and mitigation of the limitations of large language models in clinical decision-making","volume":"30","author":"Hager","year":"2024","journal-title":"Nat Med."},{"key":"B16","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41746-023-00939-z","article-title":"Large language models propagate race-based medicine","volume":"6","author":"Omiye","year":"2023","journal-title":"NPJ Digit Med."},{"key":"B17","doi-asserted-by":"publisher","first-page":"1873","DOI":"10.1038\/s41591-025-03626-6","article-title":"Sociodemographic biases in medical decision making by large language models","volume":"31","author":"Omar","year":"2025","journal-title":"Nat Med."},{"key":"B18","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1186\/s12939-025-02419-0","article-title":"Evaluating and addressing demographic disparities in medical large language models: a systematic review","volume":"24","author":"Omar","year":"2025","journal-title":"Int J Equity Health."},{"key":"B19","doi-asserted-by":"publisher","first-page":"e0000651","DOI":"10.1371\/journal.pdig.0000651","article-title":"Bias in medical AI: implications for clinical decision-making","volume":"3","author":"Cross","year":"2024","journal-title":"PLOS Digit Health."},{"key":"B20","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1038\/s41746-024-01283-6","article-title":"Evaluation and mitigation of cognitive biases in medical language models","volume":"7","author":"Schmidgall","year":"2024","journal-title":"NPJ Digit Med."},{"key":"B21","doi-asserted-by":"publisher","first-page":"e2022060640","DOI":"10.1542\/peds.2022-060640","article-title":"Clinical practice guideline for the evaluation and treatment of children and adolescents with obesity","volume":"151","author":"Hampl","year":"2023","journal-title":"Paediatrics."},{"key":"B22","volume-title":"WHO Guidelines on Physical Activity and Sedentary Behaviour","year":"2020"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1710594","DOI":"10.3389\/fdgth.2025.1710594","article-title":"Uncovering bias and variability in how large language models attribute cardiovascular risk","volume":"7","author":"Chan","year":"2025","journal-title":"Front Digit Health."},{"key":"B24","year":"2017","journal-title":"Guideline: Assessing and Managing Children at Primary Health-Care Facilities to Prevent Overweight and Obesity in the Context of the Double Burden of Malnutrition"},{"key":"B25","volume-title":"Meningitis (Bacterial) and Meningococcal Disease: Recognition, Diagnosis and Management","year":"2024"},{"key":"B26","doi-asserted-by":"publisher","first-page":"E372","DOI":"10.1503\/cmaj.241456","article-title":"Managing obesity in children: a clinical practice guideline","volume":"197","author":"Ball","year":"2025","journal-title":"CMAJ."},{"key":"B27","doi-asserted-by":"publisher","first-page":"507","DOI":"10.3760\/cma.j.cn112140-20220112-00043","article-title":"Expert consensus on diagnosis, assessment, and management of obesity in Chinese children","volume":"60","year":"2022","journal-title":"Zhonghua er ke za zhi"},{"key":"B28","doi-asserted-by":"publisher","first-page":"e2416228122","DOI":"10.1073\/pnas.2416228122","article-title":"Explicitly unbiased large language models still form biased associations","volume":"122","author":"Bai","year":"2025","journal-title":"Proc Nat Acad Sci USA."},{"key":"B29","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1186\/s12916-018-1116-5","article-title":"How and why weight stigma drives the obesity \u2018epidemic'and harms health","volume":"16","author":"Tomiyama","year":"2018","journal-title":"BMC Med."},{"key":"B30","doi-asserted-by":"publisher","first-page":"e12","DOI":"10.1016\/S2589-7500(23)00225-X","article-title":"Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study","volume":"6","author":"Zack","year":"2024","journal-title":"Lancet Digit Health."},{"key":"B31","doi-asserted-by":"publisher","first-page":"e59069","DOI":"10.2196\/59069","article-title":"Revolutionizing health care: the transformative impact of large language models in medicine","volume":"27","author":"Zhang","year":"2025","journal-title":"J Med Internet Res."},{"key":"B32","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1186\/s12887-024-04970-1","article-title":"Epidemiology of obesity and influential factors in China: a multicenter cross-sectional study of children and adolescents","volume":"24","author":"Li","year":"2024","journal-title":"BMC Paediatr."},{"key":"B33","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1038\/s41746-025-01786-w","article-title":"Framework for bias evaluation in large language models in healthcare settings","volume":"8","author":"Templin","year":"2025","journal-title":"Npj Digit Med."},{"key":"B34","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1850996\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T15:30:42Z","timestamp":1785943842000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1850996\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":34,"alternative-id":["10.3389\/fpubh.2026.1850996"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1850996","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"article-number":"1850996"}}