{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,28]],"date-time":"2026-10-28T23:00:00Z","timestamp":1793228400172,"version":"4.5.0"},"reference-count":40,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T00:00:00Z","timestamp":1772236800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["J Diabetes Sci Technol"],"abstract":"<jats:sec>\n                    <jats:title>Introduction:<\/jats:title>\n                    <jats:p>Type 1 diabetes mellitus (T1D) requires precise carbohydrate estimation to manage blood glucose and prevent chronic and acute complications to hyperglycemia or hypoglycemia. This study evaluates the accuracy of ChatGPT in estimating carbohydrate content in images of meals, compared with the considered gold standard of manually counting carbohydrates.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method:<\/jats:title>\n                    <jats:p>\n                      Carbohydrate content of 60 fruits and vegetables (F&amp;V) and 60 composite meals was manually counted as the reference standard. Images (\n                      <jats:italic toggle=\"yes\">n<\/jats:italic>\n                      = 240), with and without a size reference, were uploaded to ChatGPT-4o with a standardized prompt in separate sessions. ChatGPT\u2019s estimates were then compared with the manual counts to assess accuracy.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results:<\/jats:title>\n                    <jats:p>The performance of ChatGPT-4o compared with the manual calculation was assessed primarily using mean absolute error, percentage of agreement (PoA), and Bland-Altman analysis. ChatGPT-4o achieved a PoA of 93.3% for F&amp;V\u2019s estimates, increasing to 95% with a size reference, while composite meal estimates yielded a PoA of 46.7%, reducing to 43.3% with a size reference, based on a \u00b110 g carbohydrates limit. Bland-Altman analysis showed a slight bias tendency in both ChatGPT-4o\u2019s estimates of F&amp;V and composite meals with a size reference. ChatGPT-4o\u2019s estimate for F&amp;V and composite meals without a size reference exhibited a systematic bias, with both overestimation and underestimation of the carbohydrate content.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion:<\/jats:title>\n                    <jats:p>This study suggests that adolescents living with T1D should employ ChatGPT-4o for carbohydrate estimating with caution. ChatGPT-4o showed inaccuracies in its application to composite meals, increasing the risk of inaccurate insulin administration and potentially causing postprandial hyperglycemia or hypoglycemia.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/19322968261424270","type":"journal-article","created":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T02:59:12Z","timestamp":1772333952000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":7,"title":["Evaluating Accuracy of ChatGPT-4o in Automated Carbohydrate Estimation From Images as a Self-Management Tool for Adolescents With Type 1 Diabetes"],"prefix":"10.1177","author":[{"given":"Asta Risak","family":"Johansen","sequence":"first","affiliation":[{"name":"Department of Health Science and Technology, Aalborg University, Gistrup, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4030-6592","authenticated-orcid":false,"given":"Isabella Kj\u00e6r","family":"Laursen","sequence":"additional","affiliation":[{"name":"Department of Health Science and Technology, Aalborg University, Gistrup, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"V\u00e1r","family":"Jacobsen","sequence":"additional","affiliation":[{"name":"Department of Health Science and Technology, Aalborg University, Gistrup, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zacharias Henriksson","family":"M\u00f8ller","sequence":"additional","affiliation":[{"name":"Department of Health Science and Technology, Aalborg University, Gistrup, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3484-7571","authenticated-orcid":false,"given":"Simon Lebech","family":"Cichosz","sequence":"additional","affiliation":[{"name":"Department of Health Science and Technology, Aalborg University, Gistrup, Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"179","published-online":{"date-parts":[[2026,2,28]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Quattrin T Mastrandrea LD Walker LSK. Type 1 diabetes. Lancet. 2023;401(10394):2149-2162. https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S0140673623002234. Accessed November 19 2025.","DOI":"10.1016\/S0140-6736(23)00223-4"},{"key":"e_1_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Gregory GA Robinson TIG Linklater SE et al. Global incidence prevalence and mortality of type 1 diabetes in 2021 with projection to 2040: a modelling study. Lancet Diabetes Endocrinol. 2022;10(10):741-760. https:\/\/www.sciencedirect.com\/science\/article\/abs\/pii\/S2213858722002182. Accessed November 19 2025.","DOI":"10.1016\/S2213-8587(22)00218-2"},{"key":"e_1_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Ogle GD James S Dabelea D et al. Global estimates of incidence of type 1 diabetes in children and adolescents: results from the International Diabetes Federation Atlas 10th edition. Diabetes Res Clin Pract. 2022;183:109083. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0168822721004423. Accessed November 19 2025.","DOI":"10.1016\/j.diabres.2021.109083"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.3390\/nu10010109"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1399-5448.2009.00572.x"},{"key":"e_1_3_2_7_2","doi-asserted-by":"crossref","unstructured":"Wu Y Ehlert B Metwally AA et al. Individual variations in glycemic responses to carbohydrates and underlying metabolic physiology. Nat Med. 2025;31(7):2232-2243. https:\/\/www.nature.com\/articles\/s41591-025-03719-2. Accessed October 8 2025.","DOI":"10.1038\/s41591-025-03719-2"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1365-2710.2011.01283.x"},{"key":"e_1_3_2_9_2","doi-asserted-by":"crossref","unstructured":"Chotwanvirat P Prachansuwan A Sridonpai P Kriengsinyos W. Advancements in using AI for dietary assessment based on food images: scoping review. J Med Internet Res. 2024;26(1):e51432. https:\/\/www.jmir.org\/2024\/1\/e51432. Accessed November 16 2025.","DOI":"10.2196\/51432"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.5603\/DK.a2022.0066"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1089\/dia.2019.0502"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11892-016-0762-2"},{"key":"e_1_3_2_13_2","doi-asserted-by":"crossref","unstructured":"Borus JS Laffel L. Adherence challenges in the management of type 1 diabetes in adolescents: prevention and intervention. Curr Opin Pediatr. 2010;22(4):405-411. https:\/\/pubmed.ncbi.nlm.nih.gov\/20489639\/. Accessed September 9 2025.","DOI":"10.1097\/MOP.0b013e32833a46a7"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.2337\/ds16-0032"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1111\/pedi.12554"},{"key":"e_1_3_2_16_2","unstructured":"It-anvendelse i befolkningen. Copenhagen Denmark: Danmarks Statistik; 2022."},{"key":"e_1_3_2_17_2","volume-title":"Sm\u00e5b\u00f8rns brug af digitale medier","author":"Medier\u00e5det for B\u00f8rn og Unge","year":"2023","unstructured":"Medier\u00e5det for B\u00f8rn og Unge. Sm\u00e5b\u00f8rns brug af digitale medier. Copenhagen, Denmark: Medier\u00e5det for B\u00f8rn og Unge; 2023."},{"key":"e_1_3_2_18_2","unstructured":"Hello GPT-4o. OpenAI. https:\/\/openai.com\/index\/hello-gpt-4o\/. Accessed March 1 2025."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.48185\/jaai.v4i2.870"},{"key":"e_1_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Piazza CD Laesser CI Kastrati L et al. App-based automated meal analysis in adults with type 1 diabetes using automated insulin delivery: a randomized controlled trial. EClinicalMedicine. 2025;89:103537. www.thelancet.com. Accessed February 6 2026.","DOI":"10.1016\/j.eclinm.2025.103537"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.isci.2025.113051"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2024.3417280"},{"key":"e_1_3_2_23_2","doi-asserted-by":"crossref","unstructured":"Khlaisamniang P Kerdthaisong K Vorathammathorn S et al. Decomposing food images for better nutrition analysis: a nutritionist-inspired two-step multimodal LLM approach 2025. https:\/\/www.researchgate.net\/publication\/392803871. Accessed February 5 2026.","DOI":"10.1109\/CVPRW67362.2025.00053"},{"key":"e_1_3_2_24_2","unstructured":"CR80 card specification. CardLogix Corporation. https:\/\/www.cardlogix.com\/glossary\/cr80\/?srsltid=AfmBOoqSyrYQsPst-u9SMIlwHaSQeVWwnJDX0j-jsEYgpd-sygw25jbj. Accessed April 10 2025."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdiacomp.2015.08.014"},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1177\/1932296816679180"},{"key":"e_1_3_2_27_2","volume-title":"39th National Nutrient Databank Conference","author":"Biltoft-Jensen PA","unstructured":"Biltoft-Jensen PA, Knuthsen P, Saxholt E, Christensen T. The New version of Danish food composition database FRIDA including a case study on recipe calculation compared to a chemical analysis. 39th National Nutrient Databank Conference; May 2016; Alexandria, VA."},{"key":"e_1_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Li Y. A Practical Survey on Zero-Shot Prompt Design for In-Context Learning. Shoumen Bulgaria: INCOMA Ltd; 2023:641-647. https:\/\/aclanthology.org\/2023.ranlp-1.69\/. Accessed October 8 2025.","DOI":"10.26615\/978-954-452-092-2_069"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/324\/1\/012049"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1177\/19322968211001402"},{"key":"e_1_3_2_31_2","volume-title":"Stata Statistical Software: Release 18","author":"StataCorp","year":"2023","unstructured":"StataCorp. Stata Statistical Software: Release 18. College Station, TX: StataCorp LLC; 2023."},{"key":"e_1_3_2_32_2","unstructured":"Meal images and carbohydrate content pr. meal. Mendeley Data. https:\/\/data.mendeley.com\/datasets\/98kpkwy698\/2?fbclid=IwY2xjawNTCUxleHRuA2FlbQIxMABicmlkETBGaTY3OFZIcFpVS04zM0l3AR60RecptAz6LWxkELxmUjConXDvmsQbKCIUdukNU-papUDCLWeAVVlXhGGGBA_aem_FbPl-AEGeZxhxhRMpE9wyA. Accessed October 8 2025."},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.3390\/nu17040607"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.2196\/51300"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.2196\/22074"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.180"},{"key":"e_1_3_2_37_2","unstructured":"Eskengren A. Realtidsber\u00e4kning av insulindosering f\u00f6r typ 1-diabetes med GPT-4-Turbo [Real-time insulin dosage estimation for type 1 diabetes using GPT-4-Turbo]. Vol. trita\u2013eecs-ex. https:\/\/kth.diva-portal.org\/smash\/record.jsf?dswid=144&pid=diva2%3A1912368"},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10439-023-03272-4"},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101861"},{"key":"e_1_3_2_40_2","unstructured":"Hua A Dhaliwal MP Pullela L Burke R Qin Y. Nutribench: a dataset for evaluating large language models on nutrition estimation from meal descriptions. https:\/\/mehak126.github.io\/nutribench.html. Accessed February 5 2026."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare9121676"}],"container-title":["Journal of Diabetes Science and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/19322968261424270","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/19322968261424270","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/19322968261424270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T18:15:51Z","timestamp":1777400151000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/19322968261424270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,28]]},"references-count":40,"alternative-id":["10.1177\/19322968261424270"],"URL":"https:\/\/doi.org\/10.1177\/19322968261424270","relation":{},"ISSN":["1932-2968","1932-2968"],"issn-type":[{"value":"1932-2968","type":"print"},{"value":"1932-2968","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,28]]},"article-number":"19322968261424270"}}