{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,4]],"date-time":"2026-11-04T00:36:56Z","timestamp":1793752616931,"version":"4.6.1"},"reference-count":44,"publisher":"American Academy of Pediatrics (AAP)","issue":"5","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,11,1]]},"abstract":"<jats:sec>\n                    <jats:title>OBJECTIVES<\/jats:title>\n                    <jats:p>To determine if ChatGPT can incorporate patient-specific information to provide high-quality answers to parental questions in the PICU. We hypothesized that ChatGPT would generate high-quality, patient-specific responses.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>In this cross-sectional study, we generated assessments and plans for 3 PICU patients with respiratory failure, septic shock, and status epilepticus and paired them with 8 typical parental questions. We prompted ChatGPT with instructions, an assessment and plan, and 1 question. Six PICU physicians evaluated the responses for accuracy (1\u20136), completeness (yes\/no), empathy (1\u20136), and understandability (Patient Education Materials Assessment Tool, PEMAT, 0% to 100%; Flesch\u2013Kincaid grade level). We compared answer quality among scenarios and question types using the Kruskal\u2013Wallis and Fischer\u2019s exact tests. We used percent agreement, Cohen\u2019s Kappa, and Gwet\u2019s agreement coefficient to estimate inter-rater reliability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>All answers incorporated patient details, utilizing them for reasoning in 59% of sentences. Responses had high accuracy (median 5.0, [interquartile range (IQR), 4.0\u20136.0]), empathy (median 5.0, [IQR, 5.0\u20136.0]), completeness (97% of all questions), and understandability (PEMAT % median 100, [IQR, 87.5\u2013100]; Flesch\u2013Kincaid level 8.7). Only 4\/144 reviewer scores were &amp;lt;4\/6 in accuracy, and no response was deemed likely to cause harm. There was no difference in accuracy, completeness, empathy, or understandability among scenarios or question types. We found fair, substantial, and almost perfect agreement among reviewers for accuracy, empathy, and understandability, respectively.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSIONS<\/jats:title>\n                    <jats:p>ChatGPT used patient-specific information to provide high-quality answers to parental questions in PICU clinical scenarios.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1542\/peds.2024-066615","type":"journal-article","created":{"date-parts":[[2024,10,7]],"date-time":"2024-10-07T04:06:27Z","timestamp":1728273987000},"source":"Crossref","is-referenced-by-count":13,"title":["Using ChatGPT to Provide Patient-Specific Answers to Parental Questions in the PICU"],"prefix":"10.1542","volume":"154","author":[{"given":"R. Brandon","family":"Hunter","sequence":"first","affiliation":[{"name":"aTexas Children\u2019s Hospital, Houston, Texas"},{"name":"bBaylor College of Medicine, Houston, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satid","family":"Thammasitboon","sequence":"additional","affiliation":[{"name":"aTexas Children\u2019s Hospital, Houston, Texas"},{"name":"bBaylor College of Medicine, Houston, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sreya S.","family":"Rahman","sequence":"additional","affiliation":[{"name":"bBaylor College of Medicine, Houston, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nina","family":"Fainberg","sequence":"additional","affiliation":[{"name":"cChildren\u2019s Healthcare of Atlanta, Atlanta, Georgia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew","family":"Renuart","sequence":"additional","affiliation":[{"name":"dBoston Children\u2019s Hospital, Boston, Massachusetts"},{"name":"eHarvard Medical School, Boston, Massachusetts"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shelley","family":"Kumar","sequence":"additional","affiliation":[{"name":"aTexas Children\u2019s Hospital, Houston, Texas"},{"name":"bBaylor College of Medicine, Houston, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Parag N.","family":"Jain","sequence":"additional","affiliation":[{"name":"aTexas Children\u2019s Hospital, Houston, Texas"},{"name":"bBaylor College of Medicine, Houston, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brian","family":"Rissmiller","sequence":"additional","affiliation":[{"name":"aTexas Children\u2019s Hospital, Houston, Texas"},{"name":"bBaylor College of Medicine, Houston, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Moushumi","family":"Sur","sequence":"additional","affiliation":[{"name":"aTexas Children\u2019s Hospital, Houston, Texas"},{"name":"bBaylor College of Medicine, Houston, Texas"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjiv","family":"Mehta","sequence":"additional","affiliation":[{"name":"fThe Children\u2019s Hospital of Philadelphia, Philadelphia, Pennsylvania"},{"name":"gUniversity of Pennsylvania, Philadelphia, Pennsylvania"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"417","published-online":{"date-parts":[[2024,10,7]]},"reference":[{"issue":"1","key":"2024110102503271700_B1","doi-asserted-by":"crossref","first-page":"363","DOI":"10.1111\/scs.12470","article-title":"Parents\u2019 experiences of their child being admitted to a paediatric intensive care unit: a qualitative study\u2013like being in another world","volume":"32","author":"Dahav","year":"2018","journal-title":"Scand J Caring Sci"},{"issue":"6","key":"2024110102503271700_B2","doi-asserted-by":"crossref","first-page":"1082","DOI":"10.1007\/s00134-009-1491-7","article-title":"Perceptions of parents on satisfaction with care in the pediatric intensive care unit: the EMPATHIC study","volume":"35","author":"Latour","year":"2009","journal-title":"Intensive Care Med"},{"issue":"3","key":"2024110102503271700_B3","doi-asserted-by":"crossref","first-page":"779","DOI":"10.1016\/j.pcl.2008.02.013","article-title":"Parent satisfaction in the pediatric ICU","volume":"55","author":"Latour","year":"2008","journal-title":"Pediatr Clin North Am"},{"issue":"8","key":"2024110102503271700_B4","doi-asserted-by":"crossref","first-page":"1101","DOI":"10.1016\/j.acap.2020.06.008","article-title":"Parent perspectives in shared decision-making for children with medical complexity","volume":"20","author":"Lin","year":"2020","journal-title":"Acad Pediatr"},{"key":"2024110102503271700_B5","doi-asserted-by":"crossref","first-page":"101172","DOI":"10.1016\/j.ppedcard.2019.101172","article-title":"Understanding parents\u2019 informational needs in the pediatric intensive care unit: a qualitative study","volume":"57","author":"Laudato","year":"2020","journal-title":"Progress in Pediatric Cardiology"},{"issue":"8","key":"2024110102503271700_B6","doi-asserted-by":"crossref","first-page":"e19985","DOI":"10.2196\/19985","article-title":"Online health information seeking by parents for their children: systematic review and agenda for further research","volume":"22","author":"Kubb","year":"2020","journal-title":"J Med Internet Res"},{"issue":"5","key":"2024110102503271700_B7","doi-asserted-by":"crossref","first-page":"805","DOI":"10.1002\/pbc.22674","article-title":"Information seeking behaviors of parents whose children have life-threatening illnesses","volume":"56","author":"Knapp","year":"2011","journal-title":"Pediatr Blood Cancer"},{"issue":"6","key":"2024110102503271700_B8","doi-asserted-by":"crossref","first-page":"617","DOI":"10.1177\/0033354919874074","article-title":"Online health information seeking among US adults: measuring progress toward a Healthy People 2020 objective","volume":"134","author":"Finney Rutten","year":"2019","journal-title":"Public Health Rep"},{"key":"2024110102503271700_B9","unstructured":"OpenAI. OpenAI API. Available at: https:\/\/platform.openai.com. Accessed April 12, 2023"},{"key":"2024110102503271700_B10","doi-asserted-by":"crossref","first-page":"1169595","DOI":"10.3389\/frai.2023.1169595","article-title":"ChatGPT in medicine: an overview of its applications, advantages, limitations, future prospects, and ethical considerations","volume":"6","author":"Dave","year":"2023","journal-title":"Front Artif Intell"},{"issue":"4","key":"2024110102503271700_B11","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1007\/s00167-023-07355-6","article-title":"Artificial intelligence bot ChatGPT in medical research: the potential game changer as a double-edged sword","volume":"31","author":"Dahmen","year":"2023","journal-title":"Knee Surg Sports Traumatol Arthrosc"},{"issue":"1","key":"2024110102503271700_B12","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1007\/s10916-023-01925-4","article-title":"Evaluating the feasibility of ChatGPT in healthcare: an analysis of multiple clinical and research scenarios","volume":"47","author":"Cascella","year":"2023","journal-title":"J Med Syst"},{"key":"2024110102503271700_B13","unstructured":"Bruce\u2008G\n          . Hospital ghosts? Report says Microsoft\u2019s BioGPT riddled with inaccuracies. Available at: https:\/\/www.beckershospitalreview.com\/innovation\/hospital-ghosts-report-says-microsofts-biogpt-riddled-with-inaccuracies.html. Accessed March 31, 2023"},{"issue":"1","key":"2024110102503271700_B14","doi-asserted-by":"crossref","first-page":"17885","DOI":"10.1038\/s41598-023-45223-y","article-title":"A vignette-based evaluation of ChatGPT\u2019s ability to provide appropriate and equitable medical advice across care contexts","volume":"13","author":"Nastasi","year":"2023","journal-title":"Sci Rep"},{"issue":"3","key":"2024110102503271700_B15","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1001\/jamapediatrics.2023.5750","article-title":"Diagnostic accuracy of a large language model in pediatric case studies","volume":"178","author":"Barile","year":"2024","journal-title":"JAMA Pediatr"},{"issue":"7","key":"2024110102503271700_B16","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1097\/PCC.0000000000002956","article-title":"Epidemiology of pediatric critical care admissions in 43 United States children\u2019s hospitals, 2014\u20132019","volume":"23","author":"Heneghan","year":"2022","journal-title":"Pediatr Crit Care Med"},{"key":"2024110102503271700_B17","unstructured":"OpenAI. GPT-4. Available at: https:\/\/openai.com\/product\/gpt-4. Accessed March 18, 2023"},{"key":"2024110102503271700_B18","unstructured":"Nori\u2008H, King\u2008N, McKinney\u2008SM, . Capabilities of GPT-4 on medical challenge problems. Available at: https:\/\/arxiv.org\/abs\/2303.13375. Accessed May 8, 2024"},{"issue":"13","key":"2024110102503271700_B19","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, limits, and risks of GPT-4 as an AI chatbot for medicine","volume":"388","author":"Lee","year":"2023","journal-title":"N Engl J Med"},{"key":"2024110102503271700_B20","volume-title":"Health Literacy And Patient Safety: Help Patients Understand","author":"Barry","year":"2007","edition":"2nd ed"},{"key":"2024110102503271700_B21","unstructured":"Ratner\u2008N, Levine\u2008Y, Belinkov\u2008Y, . Parallel context windows for large language models. Available at: http:\/\/arxiv.org\/abs\/2212.10947. Accessed February 29, 2024"},{"key":"2024110102503271700_B22","doi-asserted-by":"crossref","article-title":"Assessing the accuracy and reliability of AI-generated medical responses: an evaluation of the Chat-GPT model","author":"Johnson","DOI":"10.21203\/rs.3.rs-2566942\/v1"},{"issue":"6","key":"2024110102503271700_B23","doi-asserted-by":"crossref","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"},{"issue":"3","key":"2024110102503271700_B24","doi-asserted-by":"crossref","first-page":"395","DOI":"10.1016\/j.pec.2014.05.027","article-title":"Development of the Patient Education Materials Assessment Tool (PEMAT): a new measure of understandability and actionability for print and audiovisual patient information","volume":"96","author":"Shoemaker","year":"2014","journal-title":"Patient Educ Couns"},{"issue":"6","key":"2024110102503271700_B25","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1001\/jamaoto.2023.0704","article-title":"Comparison between ChatGPT and Google search as sources of postoperative patient instructions","volume":"149","author":"Ayoub","year":"2023","journal-title":"JAMA Otolaryngol Head Neck Surg"},{"key":"2024110102503271700_B26","unstructured":"Agency for Healthcare Research and Quality. The Patient Education Materials Assessment Tool (PEMAT) and user\u2019s guide. Available at: https:\/\/www.ahrq.gov\/health-literacy\/patient-education\/pemat.html. Accessed August 10, 2023"},{"issue":"Pt 1","key":"2024110102503271700_B27","doi-asserted-by":"crossref","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":"2024110102503271700_B28","volume-title":"Inter-Rater Reliability Analysis Using SAS: A Practical Guide for Analyzing, Categorical and Quantitative Ratings","author":"Gwet","year":"2021"},{"issue":"1","key":"2024110102503271700_B29","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"},{"key":"2024110102503271700_B30","unstructured":"Huang\u2008J, Chang\u2008KCC. Toward reasoning in large language models: a survey. Available at: http:\/\/arxiv.org\/abs\/2212.10403. Accessed February 29, 2024"},{"issue":"6","key":"2024110102503271700_B31","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1016\/j.amjmed.2016.01.008","article-title":"Examining the reading level of internet medical information for common internal medicine diagnoses","volume":"129","author":"Hutchinson","year":"2016","journal-title":"Am J Med"},{"key":"2024110102503271700_B32","unstructured":"Wei\u2008J, Tay\u2008Y, Bommasani\u2008R, . Emergent abilities of large language models. Available at: http:\/\/arxiv.org\/abs\/2206.07682. Accessed February 29, 2024"},{"issue":"9","key":"2024110102503271700_B33","doi-asserted-by":"crossref","first-page":"1526","DOI":"10.1038\/s41562-023-01659-w","article-title":"Emergent analogical reasoning in large language models","volume":"7","author":"Webb","year":"2023","journal-title":"Nat Hum Behav"},{"key":"2024110102503271700_B34","unstructured":"Stephen Wolfram. What is ChatGPT doing \u2026 and why does it work? Stephen Wolfram writings. Available at: https:\/\/writings.stephenwolfram.com\/2023\/02\/what-is-chatgpt-doing-and-why-does-it-work\/. Accessed March 30, 2023"},{"key":"2024110102503271700_B35","doi-asserted-by":"crossref","first-page":"1281255","DOI":"10.3389\/fpsyg.2023.1281255","article-title":"ChatGPT\u2019s advice is perceived as better than that of professional advice columnists","volume":"14","author":"Howe","year":"2023","journal-title":"Front Psychol"},{"key":"2024110102503271700_B36","doi-asserted-by":"crossref","first-page":"1199058","DOI":"10.3389\/fpsyg.2023.1199058","article-title":"ChatGPT outperforms humans in emotional awareness evaluations","volume":"14","author":"Elyoseph","year":"2023","journal-title":"Front Psychol"},{"issue":"2","key":"2024110102503271700_B37","doi-asserted-by":"crossref","first-page":"985","DOI":"10.1007\/s00405-023-08319-9","article-title":"Artificial intelligence chatbots as sources of patient education material for obstructive sleep apnoea: ChatGPT versus Google Bard","volume":"281","author":"Cheong","year":"2024","journal-title":"Eur Arch Otorhinolaryngol"},{"issue":"1","key":"2024110102503271700_B38","doi-asserted-by":"crossref","first-page":"104085","DOI":"10.1016\/j.amjoto.2023.104085","article-title":"Answering head and neck cancer questions: an assessment of ChatGPT responses","volume":"45","author":"Wei","year":"2024","journal-title":"Am J Otolaryngol"},{"issue":"10","key":"2024110102503271700_B39","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1001\/jamaoncol.2023.2947","article-title":"Assessment of artificial intelligence chatbot responses to top searched queries about cancer","volume":"9","author":"Pan","year":"2023","journal-title":"JAMA Oncol"},{"issue":"1","key":"2024110102503271700_B40","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.eururo.2023.07.004","article-title":"How well do artificial intelligence chatbots respond to the top search queries about urological malignancies?","volume":"85","author":"Musheyev","year":"2024","journal-title":"Eur Urol"},{"issue":"8","key":"2024110102503271700_B41","doi-asserted-by":"crossref","first-page":"e2330320","DOI":"10.1001\/jamanetworkopen.2023.30320","article-title":"Comparison of ophthalmologist and large language model chatbot responses to online patient eye care questions","volume":"6","author":"Bernstein","year":"2023","journal-title":"JAMA Netw Open"},{"issue":"12","key":"2024110102503271700_B42","doi-asserted-by":"crossref","first-page":"1989","DOI":"10.5664\/jcsm.10728","article-title":"Evaluating ChatGPT responses on obstructive sleep apnea for patient education","volume":"19","author":"Campbell","year":"2023","journal-title":"J Clin Sleep Med"},{"issue":"5","key":"2024110102503271700_B43","doi-asserted-by":"crossref","first-page":"e230922","DOI":"10.1148\/radiol.230922","article-title":"How AI responds to common lung cancer questions: ChatGPT versus Google Bard","volume":"307","author":"Rahsepar","year":"2023","journal-title":"Radiology"},{"issue":"3","key":"2024110102503271700_B44","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1089\/thy.2023.0491","article-title":"Evaluating ChatGPT responses on thyroid nodules for patient education","volume":"34","author":"Campbell","year":"2024","journal-title":"Thyroid"}],"container-title":["Pediatrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/publications.aap.org\/pediatrics\/article-pdf\/doi\/10.1542\/peds.2024-066615\/1732453\/peds.2024-066615.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/publications.aap.org\/pediatrics\/article-pdf\/doi\/10.1542\/peds.2024-066615\/1732453\/peds.2024-066615.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T22:51:04Z","timestamp":1730415064000},"score":1,"resource":{"primary":{"URL":"https:\/\/publications.aap.org\/pediatrics\/article\/154\/5\/e2024066615\/199602\/Using-ChatGPT-to-Provide-Patient-Specific-Answers"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,7]]},"references-count":44,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2024,10,7]]},"published-print":{"date-parts":[[2024,11,1]]}},"URL":"https:\/\/doi.org\/10.1542\/peds.2024-066615","relation":{},"ISSN":["0031-4005","1098-4275"],"issn-type":[{"value":"0031-4005","type":"print"},{"value":"1098-4275","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,7]]},"article-number":"e2024066615"}}