{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T12:24:41Z","timestamp":1777551881017,"version":"3.51.4"},"reference-count":32,"publisher":"SAGE Publications","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"funder":[{"name":"Collaborative Research Fund of Sapporo City University"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["DIGITAL HEALTH"],"published-print":{"date-parts":[[2026,2]]},"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>This feasibility study aimed to assess whether minimally customized large language models (LLMs) can achieve knowledge levels relevant for self-medication support by evaluating their performance on the Japanese Registered Salesperson Examination. Registered salespersons provide consumers with guidance on appropriate selection and safe use of over-the-counter drugs in Japan. We explored whether LLMs customized through simple reference materials upload, without requiring programming skills or advanced prompt engineering, could achieve comparable knowledge levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We used the 2024 Registered Salesperson Examination in Japan as a benchmark dataset, comprising 838 text-only multiple-choice questions across five domains. We created customized GPTs by uploading the official guide for examination question development as a PDF file to GPT-4o, without additional prompts or instructions. Both GPT-4o and the customized GPTs were evaluated using a zero-shot approach with web-browsing capabilities disabled.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The overall accuracy was 78.40% for GPT-4o and 92.36% for the GPTs, with this difference being statistically significant (\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009&lt;\u20090.001). The GPTs significantly outperformed GPT-4o across all five domains (\n                      <jats:italic toggle=\"yes\">p<\/jats:italic>\n                      \u2009&lt;\u20090.05).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This feasibility study demonstrates that minimal customization through reference materials upload can achieve performance improvements on knowledge-based assessments. However, examination performance represents only an indirect indicator of knowledge for self-medication support. Future research should evaluate LLMs performance in real-world case scenarios and assess practical utility and safety before implementation in consumer self-medication settings.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1177\/20552076261427504","type":"journal-article","created":{"date-parts":[[2026,2,20]],"date-time":"2026-02-20T17:39:04Z","timestamp":1771609144000},"update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["A comparison of customized GPTs and GPT-4o for self-medication knowledge: A feasibility study using the Japanese registered salesperson examination"],"prefix":"10.1177","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5901-0012","authenticated-orcid":false,"given":"Shota","family":"Okazaki","sequence":"first","affiliation":[{"name":"Sapporo City University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7057-1955","authenticated-orcid":false,"given":"Yuichi","family":"Mine","sequence":"additional","affiliation":[{"name":"Hiroshima University"},{"name":"Project Research Center for Integrating Digital Dentistry, Hiroshima University, Hiroshima, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saori","family":"Takeda","sequence":"additional","affiliation":[{"name":"Hiroshima University"},{"name":"Project Research Center for Integrating Digital Dentistry, Hiroshima University, Hiroshima, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takeshi","family":"Murayama","sequence":"additional","affiliation":[{"name":"Hiroshima University"},{"name":"Project Research Center for Integrating Digital Dentistry, Hiroshima University, Hiroshima, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2026,2,20]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"OpenAI. Introducing ChatGPT. (2022). https:\/\/openai.com\/blog\/chatgpt\/ (accessed 12 October 2025)."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2024.105673"},{"key":"e_1_3_2_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijmedinf.2023.105173"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jds.2025.03.018"},{"key":"e_1_3_2_6_2","article-title":"Accuracy of latest large language models in answering multiple choice questions in dentistry: a comparative study","volume":"29","author":"Nguyen HC","year":"2025","unstructured":"Nguyen HC, Dang HP, Nguyen TL, et al. Accuracy of latest large language models in answering multiple choice questions in dentistry: a comparative study. PLoS One 2025; 29: e0317423.","journal-title":"PLoS One"},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.2196\/57451"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.2196\/56850"},{"key":"e_1_3_2_9_2","unstructured":"OpenAI. Introducing GPTs. (2023). https:\/\/openai.com\/index\/introducing-gpts\/ (accessed 12 October 2025)."},{"key":"e_1_3_2_10_2","article-title":"Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions","volume":"12","author":"Gorelik Y","year":"2024","unstructured":"Gorelik Y, Ghersin I, Arraf T, et al. Using a customized GPT to provide guideline-based recommendations for management of pancreatic cystic lesions. Endosc Int Open 2024; 12: E600\u2013E603.","journal-title":"Endosc Int Open"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1002\/ca.24178"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12903-025-06163-3"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.2147\/RMHP.S98099"},{"key":"e_1_3_2_14_2","unstructured":"Ministry of Health Labour and Welfare. Annual Health Labour and Welfare Report 2007-2008. (2008). https:\/\/www.mhlw.go.jp\/english\/wp\/wp-hw2\/ (accessed 12 October 2025)."},{"key":"e_1_3_2_15_2","unstructured":"Hokkaido Prefectural Government. Registered salesperson exam past questions. (2025). https:\/\/www.pref.hokkaido.lg.jp\/hf\/iyk\/iry\/yakuji\/tourokuhannbaishashikenmondai.html (accessed 15 July 2025)."},{"key":"e_1_3_2_16_2","unstructured":"Ibaraki Prefectural Government. Registered salesperson exam past questions. (2025). https:\/\/www.pref.ibaraki.jp\/hokenfukushi\/yakumu\/yakuji\/yakumu\/yakuji\/toroku\/26toroku.html (accessed 16 July 2025)."},{"key":"e_1_3_2_17_2","unstructured":"Tokyo Metropolitan Government. Registered salesperson exam past questions. (2025). https:\/\/www.hokeniryo.metro.tokyo.lg.jp\/anzen\/iyaku\/tourokushiken\/R6shiken (accessed 16 July 2025)."},{"key":"e_1_3_2_18_2","unstructured":"Toyama Prefectural Government. Registered salesperson exam past questions. (2025). https:\/\/www.pref.toyama.jp\/1208\/sangyou\/shikaku\/shiken\/kj00019694\/r6touhan.html (accessed 17 July 2025)."},{"key":"e_1_3_2_19_2","unstructured":"Union of Kansai Governments. Registered salesperson exam past questions. (2025). https:\/\/www.kouiki-kansai.jp\/koikirengo\/jisijimu\/shikakumenkyo\/touroku\/7607.html (accessed 17 July 2025)."},{"key":"e_1_3_2_20_2","unstructured":"Shimane Prefectural Government. Registered salesperson exam past questions. (2025). https:\/\/www.pref.shimane.lg.jp\/medical\/yakuji\/yakuji\/yakuji_info\/toroku_hanbaisha\/hanbaisha_shiken_monndai_seikai.html (accessed 18 July 2025)."},{"key":"e_1_3_2_21_2","unstructured":"Fukuoka Prefectural Government. Registered salesperson exam past questions. (2024). https:\/\/www.pref.fukuoka.lg.jp\/contents\/r06tourokuhanbaisyashikenmondai.html (accessed 20 July 2025)."},{"key":"e_1_3_2_22_2","unstructured":"OpenAI. Introducing GPT-4o and more tools to ChatGPT free users. (2024). https:\/\/openai.com\/index\/gpt-4o-and-more-tools-to-chatgpt-free\/ (accessed 25 January 2026)."},{"key":"e_1_3_2_23_2","unstructured":"Ministry of Health Labour and Welfare. Fiscal year 2024 edition guide about examination question making (2024 April). (2025). https:\/\/www.mhlw.go.jp\/stf\/seisakunitsuite\/bunya\/0000045312\/index_00001.html (accessed 15 July 2025)."},{"key":"e_1_3_2_24_2","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown T","year":"2020","unstructured":"Brown T, Mann B, Ryder N, et al. Language models are few-shot learners. Adv Neural Inf Process Syst 2020; 33: 1877\u20131901.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_2_25_2","unstructured":"Ministry of Health Labour and Welfare. About registered salesperson examination. (2025). https:\/\/www.mhlw.go.jp\/stf\/seisakunitsuite\/bunya\/0000082514.html (accessed 25 January 2026)."},{"key":"e_1_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.3390\/healthcare12171726"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1177\/20552076251323810"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10758-025-09891-1"},{"key":"e_1_3_2_29_2","article-title":"Performance evaluation of GPT-4o and o1-preview using the certification examination for the Japanese \u2018operations chief of radiography with X-rays\u2019","volume":"16","author":"Goto H","year":"2024","unstructured":"Goto H, Shiraishi Y, Okada S. Performance evaluation of GPT-4o and o1-preview using the certification examination for the Japanese \u2018operations chief of radiography with X-rays\u2019. Cureus 2024; 16: e74262.","journal-title":"Cureus"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1136\/bmjgast-2024-001496"},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsurg.2025.103442"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1111\/ipd.70029"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1111\/idh.12848"}],"container-title":["DIGITAL HEALTH"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261427504","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/20552076261427504","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/20552076261427504","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T17:56:12Z","timestamp":1777398972000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/20552076261427504"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":32,"alternative-id":["10.1177\/20552076261427504"],"URL":"https:\/\/doi.org\/10.1177\/20552076261427504","relation":{},"ISSN":["2055-2076","2055-2076"],"issn-type":[{"value":"2055-2076","type":"print"},{"value":"2055-2076","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]},"article-number":"20552076261427504"}}