{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T23:20:27Z","timestamp":1790032827204,"version":"4.0.1"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:00:00Z","timestamp":1781654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:00:00Z","timestamp":1787702400000},"content-version":"vor","delay-in-days":70,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Educ"],"DOI":"10.1186\/s12909-026-09671-0","type":"journal-article","created":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T00:18:04Z","timestamp":1781655484000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Psychometric performance and student perceptions of AI- versus student-generated multiple-choice questions: a single-center randomized controlled trial"],"prefix":"10.1186","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4223-3191","authenticated-orcid":false,"given":"Dheyaa","family":"Al-Najafi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Katherine D.","family":"Krause","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yundi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi Kang","family":"Zuo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4174-2919","authenticated-orcid":false,"given":"Maya E","family":"Koblanski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cameron J.","family":"Leong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Emma","family":"Schmidt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Muhammad","family":"Faran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vanay","family":"Verma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ravi","family":"Vyas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Campbell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jaehyun","family":"Hwang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiawen","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7881-4800","authenticated-orcid":false,"given":"Anita","family":"Palepu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,17]]},"reference":[{"key":"9671_CR1","doi-asserted-by":"publisher","first-page":"e59778","DOI":"10.7759\/cureus.59778","volume":"16","author":"P Parekh","year":"2024","unstructured":"Parekh P, Bahadoor V. The Utility of Multiple-Choice Assessment in Current Medical Education: A Critical Review. Cureus. 2024;16:e59778. https:\/\/doi.org\/10.7759\/cureus.59778.","journal-title":"Cureus"},{"key":"9671_CR2","doi-asserted-by":"publisher","first-page":"88","DOI":"10.33590\/emjinnov\/10313113","volume":"2","author":"KD Royal","year":"2018","unstructured":"Royal KD, Hedgpeth M-W, Jeon T, Colford CM. Automated Item Generation: The Future of Medical Education Assessment. EMJ Innov. 2018;2:88\u201393. https:\/\/doi.org\/10.33590\/emjinnov\/10313113.","journal-title":"EMJ Innov"},{"key":"9671_CR3","doi-asserted-by":"publisher","unstructured":"Case SM, Holtzman K, Ripkey DR, Supplement. S111\u20133. https:\/\/doi.org\/10.1097\/00001888-200110001-00037.","DOI":"10.1097\/00001888-200110001-00037"},{"key":"9671_CR4","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/978-0-387-85461-8_8","volume-title":"Elements of Adaptive Testing","author":"LM Rudner","year":"2009","unstructured":"Rudner LM. Implementing the Graduate Management Admission Test Computerized Adaptive Test. In: van der Linden WJ, Glas CAW, editors. Elements of Adaptive Testing. New York, NY: Springer; 2009. pp. 151\u201365."},{"key":"9671_CR5","doi-asserted-by":"publisher","first-page":"757","DOI":"10.1111\/j.1365-2923.2012.04289.x","volume":"46","author":"MJ Gierl","year":"2012","unstructured":"Gierl MJ, Lai H, Turner SR. Using automatic item generation to create multiple-choice test items. Med Educ. 2012;46:757\u201365. https:\/\/doi.org\/10.1111\/j.1365-2923.2012.04289.x.","journal-title":"Med Educ"},{"key":"9671_CR6","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1007\/s42452-024-06194-5","volume":"6","author":"D Brin","year":"2024","unstructured":"Brin D, Sorin V, Konen E, Nadkarni G, Glicksberg BS, Klang E. How GPT models perform on the United States medical licensing examination: A systematic review. Discov Appl Sci. 2024;6:500. https:\/\/doi.org\/10.1007\/s42452-024-06194-5.","journal-title":"Discov Appl Sci"},{"key":"9671_CR7","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1186\/s12909-024-05239-y","volume":"24","author":"Y Artsi","year":"2024","unstructured":"Artsi Y, Sorin V, Konen E, Glicksberg BS, Nadkarni G, Klang E. Large language models for generating medical examinations: systematic review. BMC Med Educ. 2024;24:354. https:\/\/doi.org\/10.1186\/s12909-024-05239-y.","journal-title":"BMC Med Educ"},{"key":"9671_CR8","doi-asserted-by":"publisher","first-page":"3872","DOI":"10.1016\/j.acra.2024.06.046","volume":"31","author":"NP Mistry","year":"2024","unstructured":"Mistry NP, Saeed H, Rafique S, Le T, Obaid H, Adams SJ. Large Language Models as Tools to Generate Radiology Board-Style Multiple-Choice Questions. Acad Radiol. 2024;31:3872\u20138. https:\/\/doi.org\/10.1016\/j.acra.2024.06.046.","journal-title":"Acad Radiol"},{"key":"9671_CR9","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1186\/s12909-025-06796-6","volume":"25","author":"AK Law","year":"2025","unstructured":"Law AK, So J, Lui CT, Choi YF, Cheung KH, Kei-ching Hung K, et al. AI versus human-generated multiple-choice questions for medical education: a cohort study in a high-stakes examination. BMC Med Educ. 2025;25:208. https:\/\/doi.org\/10.1186\/s12909-025-06796-6.","journal-title":"BMC Med Educ"},{"key":"9671_CR10","doi-asserted-by":"publisher","unstructured":"Cheung BHH, Lau GKK, Wong GTC, Lee EYP, Kulkarni D, Seow CS, ChatGPT versus human in generating medical graduate exam multiple choice questions\u2014A multinational prospective study (Hong, Kong SAR et al. Singapore, Ireland, and the United Kingdom). PLOS ONE. 2023;18:e0290691. https:\/\/doi.org\/10.1371\/journal.pone.0290691 ;","DOI":"10.1371\/journal.pone.0290691"},{"key":"9671_CR11","doi-asserted-by":"publisher","first-page":"2554678","DOI":"10.1080\/10872981.2025.2554678","volume":"30","author":"M Elzayyat","year":"2025","unstructured":"Elzayyat M, Mohammad JN, Zaqout S. Assessing LLM-generated vs. expert-created clinical anatomy MCQs: a student perception-based comparative study in medical education. Med Educ Online. 2025;30:2554678. https:\/\/doi.org\/10.1080\/10872981.2025.2554678.","journal-title":"Med Educ Online"},{"key":"9671_CR12","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1152\/advan.00197.2025","volume":"49","author":"AD Dhanvijay","year":"2025","unstructured":"Dhanvijay AD, Kumari A, Pinjar MJ, Kumari A, Ganguly A, Priya A, et al. Faculty versus artificial intelligence chatbot: a comparative analysis of multiple-choice question quality in physiology. Adv Physiol Educ. 2025;49:1045\u201351. https:\/\/doi.org\/10.1152\/advan.00197.2025.","journal-title":"Adv Physiol Educ"},{"key":"9671_CR13","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1152\/advan.00106.2024","volume":"49","author":"T Camarata","year":"2025","unstructured":"Camarata T, McCoy L, Rosenberg R, Temprine Grellinger KR, Brettschnieder K, Berman J. LLM-Generated multiple choice practice quizzes for preclinical medical students. Adv Physiol Educ. 2025;49:758\u201363. https:\/\/doi.org\/10.1152\/advan.00106.2024.","journal-title":"Adv Physiol Educ"},{"key":"9671_CR14","doi-asserted-by":"publisher","first-page":"1885","DOI":"10.1007\/s10439-023-03224-y","volume":"51","author":"S Biswas","year":"2023","unstructured":"Biswas S. Passing is Great: Can ChatGPT Conduct USMLE Exams? Ann Biomed Eng. 2023;51:1885\u20136. https:\/\/doi.org\/10.1007\/s10439-023-03224-y.","journal-title":"Ann Biomed Eng"},{"key":"9671_CR15","doi-asserted-by":"publisher","first-page":"1645","DOI":"10.1080\/0142159X.2025.2478872","volume":"47","author":"A Balu","year":"2025","unstructured":"Balu A, Prvulovic ST, Fernandez Perez C, Kim A, Donoho DA, Keating G. Evaluating the value of AI-generated questions for USMLE step 1 preparation: A study using ChatGPT-3.5. Med Teach. 2025;47:1645\u201353. https:\/\/doi.org\/10.1080\/0142159X.2025.2478872.","journal-title":"Med Teach"},{"key":"9671_CR16","doi-asserted-by":"publisher","first-page":"772","DOI":"10.1186\/s12909-023-04752-w","volume":"23","author":"E Klang","year":"2023","unstructured":"Klang E, Portugez S, Gross R, Kassif Lerner R, Brenner A, Gilboa M, et al. Advantages and pitfalls in utilizing artificial intelligence for crafting medical examinations: A medical education pilot study with GPT-4. BMC Med Educ. 2023;23:772. https:\/\/doi.org\/10.1186\/s12909-023-04752-w.","journal-title":"BMC Med Educ"},{"key":"9671_CR17","doi-asserted-by":"publisher","first-page":"e43717","DOI":"10.7759\/cureus.43717","volume":"15","author":"I Ayub","year":"2023","unstructured":"Ayub I, Hamann D, Hamann CR, Davis MJ. Exploring the Potential and Limitations of Chat Generative Pre-trained Transformer (ChatGPT) in Generating Board-Style Dermatology Questions: A Qualitative Analysis. Cureus. 2023;15:e43717. https:\/\/doi.org\/10.7759\/cureus.43717.","journal-title":"Cureus"},{"key":"9671_CR18","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/s10143-023-01998-2","volume":"46","author":"UT Sevgi","year":"2023","unstructured":"Sevgi UT, Erol G, Do\u011fruel Y, S\u00f6nmez OF, Tubbs RS, G\u00fcngor A. The role of an open artificial intelligence platform in modern neurosurgical education: A preliminary study. Neurosurg Rev. 2023;46:86. https:\/\/doi.org\/10.1007\/s10143-023-01998-2.","journal-title":"Neurosurg Rev"},{"key":"9671_CR19","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1080\/0142159X.2023.2271159","volume":"46","author":"Z Han","year":"2024","unstructured":"Han Z, Battaglia F, Udaiyar A, Fooks A, Terlecky SR. An explorative assessment of ChatGPT as an aid in medical education: Use it with caution. Med Teach. 2024;46:657\u201364. https:\/\/doi.org\/10.1080\/0142159X.2023.2271159.","journal-title":"Med Teach"},{"key":"9671_CR20","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1007\/BF00596229","volume":"1","author":"CPM Van Der Vleuten","year":"1996","unstructured":"Van Der Vleuten CPM. The assessment of professional competence: Developments, research and practical implications. Adv Health Sci Educ. 1996;1:41\u201367. https:\/\/doi.org\/10.1007\/BF00596229.","journal-title":"Adv Health Sci Educ"},{"key":"9671_CR21","doi-asserted-by":"publisher","first-page":"10588","DOI":"10.15766\/mep_2374-8265.10588","volume":"13","author":"JM Colbert-Getz","year":"2017","unstructured":"Colbert-Getz JM, Ryan M, Hennessey E, Lindeman B, Pitts B, Rutherford KA, et al. Measuring Assessment Quality With an Assessment Utility Rubric for Medical Education. MedEdPORTAL. 2017;13:10588. https:\/\/doi.org\/10.15766\/mep_2374-8265.10588.","journal-title":"MedEdPORTAL"},{"key":"9671_CR22","doi-asserted-by":"publisher","first-page":"1776","DOI":"10.1038\/s41591-025-03635-5","volume":"31","author":"S Hopewell","year":"2025","unstructured":"Hopewell S, Chan A-W, Collins GS, Hr\u00f3bjartsson A, Moher D, Schulz KF, et al. CONSORT 2025 statement: Updated guideline for reporting randomized trials. Nat Med. 2025;31:1776\u201383. https:\/\/doi.org\/10.1038\/s41591-025-03635-5.","journal-title":"Nat Med"},{"key":"9671_CR23","doi-asserted-by":"publisher","first-page":"103208","DOI":"10.1016\/j.jbi.2019.103208","volume":"95","author":"PA Harris","year":"2019","unstructured":"Harris PA, Taylor R, Minor BL, Elliott V, Fernandez M, O\u2019Neal L, et al. The REDCap consortium: Building an international community of software platform partners. J Biomed Inf. 2019;95:103208. https:\/\/doi.org\/10.1016\/j.jbi.2019.103208.","journal-title":"J Biomed Inf"},{"key":"9671_CR24","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1016\/j.jbi.2008.08.010","volume":"42","author":"PA Harris","year":"2009","unstructured":"Harris PA, Taylor R, Thielke R, Payne J, Gonzalez N, Conde JG. Research electronic data capture (REDCap)\u2014A metadata-driven methodology and workflow process for providing translational research informatics support. J Biomed Inf. 2009;42:377\u201381. https:\/\/doi.org\/10.1016\/j.jbi.2008.08.010.","journal-title":"J Biomed Inf"},{"key":"9671_CR25","doi-asserted-by":"publisher","first-page":"33267","DOI":"10.1525\/collabra.33267","volume":"8","author":"D Lakens","year":"2022","unstructured":"Lakens D. Sample Size Justification. Collabra Psychol. 2022;8:33267. https:\/\/doi.org\/10.1525\/collabra.33267.","journal-title":"Collabra Psychol"},{"key":"9671_CR26","doi-asserted-by":"publisher","first-page":"933","DOI":"10.4135\/9781506326139.n376","volume":"4","author":"J Chen","year":"2018","unstructured":"Chen J. KR-20. SAGE Encycl Educ Res Meas Eval. 2018;4:933\u20136. https:\/\/doi.org\/10.4135\/9781506326139.n376.","journal-title":"SAGE Encycl Educ Res Meas Eval"},{"key":"9671_CR27","unstructured":"Ebel RL, Frisbie DA. Evaluating Test and Item Characteristics. In: Essentials of Educational Measurement. 5th edition. Englewood Cliffs, NJ: Prentice-Hall Inc.; 1991;220\u201340."},{"key":"9671_CR28","first-page":"142","volume":"62","author":"MR Hingorjo","year":"2012","unstructured":"Hingorjo MR, Jaleel F. Analysis of One-Best MCQs: the Difficulty Index, Discrimination Index and Distractor Efficiency. J Pak Med Assoc. 2012;62:142\u20137.","journal-title":"J Pak Med Assoc"},{"key":"9671_CR29","doi-asserted-by":"publisher","first-page":"741","DOI":"10.1037\/0003-066X.50.9.741","volume":"50","author":"S Messick","year":"1995","unstructured":"Messick S. Validity of psychological assessment: Validation of inferences from persons\u2019 responses and performances as scientific inquiry into score meaning. Am Psychol. 1995;50:741\u20139. https:\/\/doi.org\/10.1037\/0003-066X.50.9.741.","journal-title":"Am Psychol"},{"key":"9671_CR30","doi-asserted-by":"publisher","first-page":"363","DOI":"10.1007\/BF02289364","volume":"34","author":"LS Feldt","year":"1969","unstructured":"Feldt LS. A Test of the Hypothesis that Cronbach\u2019s Alpha or Kuder-Richardson Coefficient Twenty is the Same for Two Tests. Psychometrika. 1969;34:363\u201373. https:\/\/doi.org\/10.1007\/BF02289364.","journal-title":"Psychometrika"},{"key":"9671_CR31","doi-asserted-by":"publisher","first-page":"e44049","DOI":"10.7759\/cureus.44049","volume":"15","author":"AKD Dhanvijay","year":"2023","unstructured":"Dhanvijay AKD, Dhokane N, Balgote S, Kumari A, Juhi A, Mondal H, et al. The Effect of a One-Day Workshop on the Quality of Framing Multiple Choice Questions in Physiology in a Medical College in India. Cureus. 2023;15:e44049. https:\/\/doi.org\/10.7759\/cureus.44049.","journal-title":"Cureus"},{"key":"9671_CR32","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1186\/s12909-024-05433-y","volume":"24","author":"AA Rezigalla","year":"2024","unstructured":"Rezigalla AA, Eleragi AMESA, Elhussein AB, Alfaifi J, ALGhamdi MA, Al Ameer AY, et al. Item analysis: the impact of distractor efficiency on the difficulty index and discrimination power of multiple-choice items. BMC Med Educ. 2024;24:445. https:\/\/doi.org\/10.1186\/s12909-024-05433-y.","journal-title":"BMC Med Educ"},{"key":"9671_CR33","doi-asserted-by":"publisher","first-page":"1224","DOI":"10.1080\/0142159X.2023.2249239","volume":"45","author":"M Zuckerman","year":"2023","unstructured":"Zuckerman M, Flood R, Tan RJB, Kelp N, Ecker DJ, Menke J, et al. ChatGPT for assessment writing. Med Teach. 2023;45:1224\u20137. https:\/\/doi.org\/10.1080\/0142159X.2023.2249239.","journal-title":"Med Teach"},{"key":"9671_CR34","doi-asserted-by":"publisher","first-page":"1961","DOI":"10.1080\/0142159X.2025.2505122","volume":"47","author":"H Wu","year":"2025","unstructured":"Wu H, Zerner T, Lee D, Court-Kowalski S, Devitt P, Palmer E. GPT-4 versus human authors in clinically complex MCQ creation: A blinded analysis of item quality. Med Teach. 2025;47:1961\u201374. https:\/\/doi.org\/10.1080\/0142159X.2025.2505122.","journal-title":"Med Teach"},{"key":"9671_CR35","doi-asserted-by":"publisher","first-page":"e48291","DOI":"10.2196\/48291","volume":"9","author":"A Abd-alrazaq","year":"2023","unstructured":"Abd-alrazaq A, AlSaad R, Alhuwail D, Ahmed A, Healy PM, Latifi S, et al. Large Language Models in Medical Education: Opportunities, Challenges, and Future Directions. JMIR Med Educ. 2023;9:e48291. https:\/\/doi.org\/10.2196\/48291.","journal-title":"JMIR Med Educ"}],"container-title":["BMC Medical Education"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12909-026-09671-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12909-026-09671-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12909-026-09671-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,26]],"date-time":"2026-08-26T00:25:17Z","timestamp":1787703917000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12909-026-09671-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,17]]},"references-count":35,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["9671"],"URL":"https:\/\/doi.org\/10.1186\/s12909-026-09671-0","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-9187684\/v1","asserted-by":"object"}]},"ISSN":["1472-6920"],"issn-type":[{"value":"1472-6920","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,17]]},"assertion":[{"value":"21 March 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was approved by the University of British Columbia Behavioral Research Ethics Board (Ethics ID: H16-00044) and was conducted in accordance with the ethical principles set forth in the World Medical Association Declaration of Helsinki. All participants provided written informed consent prior to enrollment. Participation was voluntary, uncompensated, and had no impact on academic standing.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"1376"}}