{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T21:43:54Z","timestamp":1792273434870,"version":"4.4.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T00:00:00Z","timestamp":1792195200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T00:00:00Z","timestamp":1792195200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Pediatr Res"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Evaluating how appropriate current large language models (LLMs) respond to common pediatric infectious disease (PID) questions is important for understanding their potential role in education and clinical support. Therefore, we evaluated and compared the clinical quality of answers produced by different LLMs when given professionally written, clinician-style case descriptions, using a purpose-built multi-domain evaluation tool.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Three different LLMs, including DeepSeek-V3.2-Exp, ChatGPT-5, and Gemini 2.5 Flash, were investigated using 12 relevant PID scenarios. Each scenario included five open-ended questions: etiology, clinical features, diagnostics, treatment options, and complications. Two PID specialists independently reviewed all responses using a Likert scoring tool.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      All three models received high overall scores. ChatGPT-5 achieved perfect domain scores (10.0), whereas DeepSeek-V3.2-Exp showed similarly strong results, with only minor reductions in diagnostics (9.83) and treatment (9.92). Gemini 2.5 Flash demonstrated higher variability, particularly in treatment (8.83) and diagnostics (9.75), while matching the other models in clinical findings and complications (10.0) and scoring 9.83 in etiology. However, there were no statistically significant differences across models in domain-level comparisons (all\n                      <jats:italic>p<\/jats:italic>\n                      \u2009&gt;\u20090.05). In addition, model-level analyses similarly demonstrated high accuracy (6.0; 5.98; 5.85), completeness (3.0; 2.97; 2.87), and safety (1.0; 1.0; 0.97) for ChatGPT-5, DeepSeek-V3.2-Exp, and Gemini 2.5 Flash, respectively (accuracy:\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.074; completeness:\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.066; safety:\n                      <jats:italic>p<\/jats:italic>\n                      \u2009=\u20090.14).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Current LLMs performed highly in structured, expert-reviewed PID scenarios and may assist with information organization and early-stage clinical reasoning. However, their optimal use remains within clinician-supervised workflows, where AI-generated outputs complement, rather than replace, human clinical judgment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Impact<\/jats:title>\n                    <jats:p>\n                      <jats:list list-type=\"bullet\">\n                        <jats:list-item>\n                          <jats:p>Current large language models (LLMs) show consistently high-quality performance across pediatric infectious disease scenarios, with no significant differences between models.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>Our study adds a structured, multi-domain comparison using clinician-style cases and expert evaluation, providing detailed insights into accuracy, completeness, and safety.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>The findings support the use of LLMs in medical education and early clinical reasoning, while highlighting their role as clinician-supervised tools rather than replacements for clinical judgment.<\/jats:p>\n                        <\/jats:list-item>\n                        <jats:list-item>\n                          <jats:p>The results demonstrate the reliability of LLMs in organizing clinical information and identifying key diagnostic and management elements in standardized scenarios.<\/jats:p>\n                        <\/jats:list-item>\n                      <\/jats:list>\n                    <\/jats:p>\n                  <\/jats:sec>","DOI":"10.1038\/s41390-026-05578-0","type":"journal-article","created":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T10:25:21Z","timestamp":1792232721000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Performance of large language models in pediatric infectious disease education: a multi-condition comparative study"],"prefix":"10.1038","author":[{"given":"Kubra","family":"Aykac","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osman","family":"Cubuk","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osman Oguz","family":"Demir","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Young June","family":"Choe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soichiro","family":"Kawata","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kamila","family":"Ludwikowska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mike Yat Wah","family":"Kwan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Malik","family":"Aydin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yasemin","family":"Ozsurekci","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,17]]},"reference":[{"key":"5578_CR1","doi-asserted-by":"publisher","first-page":"e65263","DOI":"10.2196\/65263","volume":"6","author":"Masab Mansoor","year":"2025","unstructured":"Mansoor, M., Ibrahim, A.F., Grindem, D. & Baig, A. sad Large language models for pediatric differential diagnoses in rural health care: multicenter retrospective cohort study comparing GPT-3 with pediatrician performance. JMIRx Med. 6, e65263 https:\/\/doi.org\/10.2196\/65263 (2025).","journal-title":"JMIRx Med."},{"key":"5578_CR2","doi-asserted-by":"publisher","first-page":"807","DOI":"10.3390\/jcm14030807","volume":"14","author":"HA Ganatra","year":"2025","unstructured":"Ganatra, H. A. Machine learning in pediatric healthcare: current trends, challenges, and future directions. J. Clin. Med. 14, 807 https:\/\/doi.org\/10.3390\/jcm14030807 (2025).","journal-title":"J. Clin. Med."},{"key":"5578_CR3","doi-asserted-by":"publisher","first-page":"745","DOI":"10.1590\/1806-9282.20220177","volume":"68","author":"FY Matsushita","year":"2022","unstructured":"Matsushita, F. Y., Krebs, V. L. J. & Carvalho, W. B. Artificial intelligence and machine learning in pediatrics and neonatology healthcare. Rev. Assoc. Med. Bras (1992) 68, 745\u2013750 https:\/\/doi.org\/10.1590\/1806-9282.20220177 (2022).","journal-title":"Rev. Assoc. Med. Bras (1992)"},{"key":"5578_CR4","doi-asserted-by":"publisher","DOI":"10.1186\/s12909-025-07106-w","volume":"25","author":"Y Lindb\u00e4ck","year":"2025","unstructured":"Lindb\u00e4ck, Y., Schr\u00f6der, K., Engstr\u00f6m, T., Valeskog, K. & Sonesson, S. Generative artificial intelligence in physiotherapy education: great potential amidst challenges- a qualitative interview study. BMC Med. Educ. 25, 603 https:\/\/doi.org\/10.1186\/s12909-025-07106-w (2025).","journal-title":"BMC Med. Educ."},{"key":"5578_CR5","doi-asserted-by":"publisher","unstructured":"Durgungoz, A. & Kharrufa, A. \u201cChatGPT is like a study buddy, a teacher and sometimes just a friend\u201d: a longitudinal exploration of students\u2019 interactions, perception and acceptance. Interact. Learn. Environ. 1\u201320 https:\/\/doi.org\/10.1080\/10494820.2025.2509276 (2025).","DOI":"10.1080\/10494820.2025.2509276"},{"key":"5578_CR6","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","volume":"29","author":"ArunJames Thirunavukarasu","year":"2023","unstructured":"Thirunavukarasu, A.J. et al. Large language models in medicine. Nat. Med. 29, 1930\u20131940 https:\/\/doi.org\/10.1038\/s41591-023-02448-8 (2023).","journal-title":"Nat. Med."},{"key":"5578_CR7","doi-asserted-by":"publisher","DOI":"10.3389\/fdgth.2025.1610671","volume":"7","author":"Guijun Yang","year":"2025","unstructured":"Yang, G. et al. Evaluating large language models in pediatric fever management: a two-layer study. Front. Digit Health. 7, 1610671 https:\/\/doi.org\/10.3389\/fdgth.2025.1610671 (2025).","journal-title":"Front. Digit Health."},{"key":"5578_CR8","doi-asserted-by":"publisher","first-page":"641","DOI":"10.3345\/cep.2025.00962","volume":"68","author":"T Park","year":"2025","unstructured":"Park, T., Lee, I. H., Lee, S. W. & Kong, S. W. Artificial intelligence in pediatric healthcare: current applications, potential, and implementation considerations. Clin. Exp. Pediatr. 68, 641\u2013651 https:\/\/doi.org\/10.3345\/cep.2025.00962 (2025).","journal-title":"Clin. Exp. Pediatr."},{"key":"5578_CR9","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-27722-2","volume":"15","author":"Kubra Aykac","year":"2025","unstructured":"Aykac, K. et al. Comparing ChatGPT-3.5, Gemini 2.0, and DeepSeek V3 for pediatric pneumonia learning in medical students. Sci. Rep. 15, 40342 https:\/\/doi.org\/10.1038\/s41598-025-27722-2 (2025).","journal-title":"Sci. Rep."},{"key":"5578_CR10","unstructured":"World Health Organization. Communicable diseases among children. World Health Organization website. Accessed 2026. https:\/\/www.who.int\/teams\/maternal-newborn-child-adolescent-health-and-ageing\/child-health\/communicable-diseases-among-children."},{"key":"5578_CR11","unstructured":"Carter-Hamilton, G. V. & Coffin, S. E. Childcare and communicable diseases. In: Nelson Textbook of Pediatrics (Kliegman, R. M. et al. eds) 22nd edn, 1621\u20131626 (Elsevier, 2023)."},{"key":"5578_CR12","doi-asserted-by":"publisher","unstructured":"Douglas, J. et al. Assessing the accuracy and reliability of AI-generated medical responses: an evaluation of the Chat-GPT model. Preprint. Res. Sq. Preprint at https:\/\/doi.org\/10.21203\/rs.3.rs-2566942\/v1","DOI":"10.21203\/rs.3.rs-2566942\/v1"},{"key":"5578_CR13","doi-asserted-by":"publisher","first-page":"130","DOI":"10.3390\/nursrep15040130","volume":"15","author":"Marica Soddu","year":"2025","unstructured":"Soddu, M. et al. Assessing the accuracy, completeness and safety of ChatGPT-4o responses on pressure injuries in infants: clinical applications and future implications. Nurs. Rep. 15, 130 https:\/\/doi.org\/10.3390\/nursrep15040130 (2025).","journal-title":"Nurs. Rep."},{"key":"5578_CR14","doi-asserted-by":"publisher","first-page":"2144","DOI":"10.3390\/healthcare13172144","volume":"13","author":"AA Othman","year":"2025","unstructured":"Othman, A. A. et al. Assessing the accuracy and completeness of AI-generated dental responses: an evaluation of the Chat-GPT model. Healthcare 13, 2144 https:\/\/doi.org\/10.3390\/healthcare13172144 (2025).","journal-title":"Healthcare"},{"key":"5578_CR15","doi-asserted-by":"publisher","first-page":"e45312","DOI":"10.2196\/45312","volume":"9","author":"Gilson","year":"2023","unstructured":"Gilson A. et al. How does ChatGPT perform on the United States Medical Licensing Examination (USMLE)? The implications of large language models for medical education and knowledge assessment. JMIR Med. Educ. 9, e45312 (2023).","journal-title":"JMIR Med. Educ."},{"key":"5578_CR16","doi-asserted-by":"publisher","first-page":"e60807","DOI":"10.2196\/60807","volume":"26","author":"L Mingxin","year":"2024","unstructured":"Mingxin, L. et al. Performance of ChatGPT across different versions in medical licensing examinations worldwide: systematic review and meta-analysis. J. Med. Internet Res. 26, e60807 https:\/\/doi.org\/10.2196\/60807 (2024).","journal-title":"J. Med. Internet Res."},{"key":"5578_CR17","doi-asserted-by":"publisher","first-page":"e0000198","DOI":"10.1371\/journal.pdig.0000198","volume":"2","author":"H Tiffany","year":"2023","unstructured":"Tiffany, H., Kung et al. Performance of ChatGPT on USMLE: potential for AI-assisted medical education using large language models. PLOS Digit. Health 2, e0000198 https:\/\/doi.org\/10.1371\/journal.pdig.0000198 (2023).","journal-title":"PLOS Digit. Health"},{"key":"5578_CR18","doi-asserted-by":"publisher","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","volume":"388","author":"P Lee","year":"2023","unstructured":"Lee, P., Bubeck, S. & Petro, J. Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine. N. Engl. J Med. 388, 1233\u20131239 https:\/\/doi.org\/10.1056\/NEJMsr2214184 (2023).","journal-title":"N. Engl. J Med."},{"key":"5578_CR19","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1038\/s41746-025-01543-z","volume":"8","author":"H Takita","year":"2025","unstructured":"Takita, H. et al. A systematic review and meta-analysis of diagnostic performance comparison between generative AI and physicians. NPJ Digit. Med. 8, 175, https:\/\/doi.org\/10.1038\/s41746-025-01543-z (2025).","journal-title":"NPJ Digit. Med."},{"key":"5578_CR20","doi-asserted-by":"publisher","DOI":"10.1002\/hsr2.71219","volume":"8","author":"SF Ghasemi","year":"2025","unstructured":"Ghasemi, S. F., Amiri, P. & Galavi, Z. Advantages and limitations of ChatGPT in healthcare: a scoping review. Health Sci. Rep. 8, e71219 https:\/\/doi.org\/10.1002\/hsr2.71219 (2025).","journal-title":"Health Sci. Rep."},{"key":"5578_CR21","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2025.1518049","volume":"8","author":"JA Tangsrivimol","year":"2025","unstructured":"Tangsrivimol, J. A. et al. Benefits, limits, and risks of ChatGPT in medicine. Front. Artif. Intell. 8, 1518049 https:\/\/doi.org\/10.3389\/frai.2025.1518049 (2025).","journal-title":"Front. Artif. Intell."},{"key":"5578_CR22","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat Med. 25, 44\u201356 https:\/\/doi.org\/10.1038\/s41591-018-0300-7 (2019).","journal-title":"Nat Med."},{"key":"5578_CR23","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1002\/ohn.70143","volume":"174","author":"A Aliyeva","year":"2026","unstructured":"Aliyeva, A., Muradova, A., Hashimli, R. & M\u00fcderris, T. Multi-model artificial intelligence evaluation in sudden sensorineural hearing loss. Otolaryngol. Head Neck Surg. 174, 980\u2013988 https:\/\/doi.org\/10.1002\/ohn.70143 (2026).","journal-title":"Otolaryngol. Head Neck Surg."},{"key":"5578_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.bas.2026.105997","volume":"6","author":"A Aliyeva","year":"2026","unstructured":"Aliyeva, A. et al. AI at the sella turcica: multi-model large language model evaluation in pituitary adenomas. Brain Spine 6, 105997 https:\/\/doi.org\/10.1016\/j.bas.2026.105997 (2026).","journal-title":"Brain Spine"},{"key":"5578_CR25","doi-asserted-by":"publisher","first-page":"S3","DOI":"10.1016\/j.jpeds.2020.02.039","volume":"221S","author":"H Lonsdale","year":"2020","unstructured":"Lonsdale, H., Jalali, A., Ahumada, L. & Matava, C. Machine learning and artificial intelligence in pediatric research: current state, future prospects, and examples in perioperative and critical care. J. Pediatr. 221S, S3\u2013S10 https:\/\/doi.org\/10.1016\/j.jpeds.2020.02.039 (2020).","journal-title":"J. Pediatr."},{"key":"5578_CR26","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1056\/NEJMra2119215","volume":"388","author":"JS Brownstein","year":"2023","unstructured":"Brownstein, J. S., Rader, B., Astley, C. M. & Tian, H. Advances in artificial intelligence for infectious-disease surveillance. N. Engl. J. Med. 388, 1597\u20131607 https:\/\/doi.org\/10.1056\/NEJMra2119215 (2023).","journal-title":"N. Engl. J. Med."},{"key":"5578_CR27","doi-asserted-by":"publisher","first-page":"2602","DOI":"10.3390\/diagnostics15202602","volume":"15","author":"C Dong","year":"2025","unstructured":"Dong, C. et al. Artificial intelligence in infectious disease diagnostic technologies. Diagnostics 15, 2602 https:\/\/doi.org\/10.3390\/diagnostics15202602 (2025).","journal-title":"Diagnostics"}],"container-title":["Pediatric Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41390-026-05578-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41390-026-05578-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41390-026-05578-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T21:02:12Z","timestamp":1792270932000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41390-026-05578-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,17]]},"references-count":27,"alternative-id":["5578"],"URL":"https:\/\/doi.org\/10.1038\/s41390-026-05578-0","relation":{},"ISSN":["0031-3998","1530-0447"],"issn-type":[{"value":"0031-3998","type":"print"},{"value":"1530-0447","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,17]]},"assertion":[{"value":"26 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 August 2026","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 September 2026","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2026","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Ethics"}},{"value":"AI-assisted copy editing was used to improve the readability, grammar, and style of the manuscript text. All AI-assisted content was carefully reviewed, edited, and approved by the authors to ensure accuracy and accountability.","order":2,"name":"Ethics","label":"Use of large language models (LLMs)","group":{"name":"EthicsHeading","label":"Ethics"}}]}}