{"title":"利用生成式人工智能制作医学 MCQ:利用 ChatGPT 的操作指南。","authors":"Matthias Stadler, Anna Horrer, Martin R Fischer","doi":"10.3205/zma001675","DOIUrl":null,"url":null,"abstract":"<p><p>As medical educators grapple with the consistent demand for high-quality assessments, the integration of artificial intelligence presents a novel solution. This how-to article delves into the mechanics of employing ChatGPT for generating Multiple Choice Questions (MCQs) within the medical curriculum. Focusing on the intricacies of prompt engineering, we elucidate the steps and considerations imperative for achieving targeted, high-fidelity results. The article presents varying outcomes based on different prompt structures, highlighting the AI's adaptability in producing questions of distinct complexities. While emphasizing the transformative potential of ChatGPT, we also spotlight challenges, including the AI's occasional \"hallucination\", underscoring the importance of rigorous review. This guide aims to furnish educators with the know-how to integrate AI into their assessment creation process, heralding a new era in medical education tools.</p>","PeriodicalId":45850,"journal":{"name":"GMS Journal for Medical Education","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2024-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11106576/pdf/","citationCount":"0","resultStr":"{\"title\":\"Crafting medical MCQs with generative AI: A how-to guide on leveraging ChatGPT.\",\"authors\":\"Matthias Stadler, Anna Horrer, Martin R Fischer\",\"doi\":\"10.3205/zma001675\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>As medical educators grapple with the consistent demand for high-quality assessments, the integration of artificial intelligence presents a novel solution. This how-to article delves into the mechanics of employing ChatGPT for generating Multiple Choice Questions (MCQs) within the medical curriculum. Focusing on the intricacies of prompt engineering, we elucidate the steps and considerations imperative for achieving targeted, high-fidelity results. The article presents varying outcomes based on different prompt structures, highlighting the AI's adaptability in producing questions of distinct complexities. While emphasizing the transformative potential of ChatGPT, we also spotlight challenges, including the AI's occasional \\\"hallucination\\\", underscoring the importance of rigorous review. This guide aims to furnish educators with the know-how to integrate AI into their assessment creation process, heralding a new era in medical education tools.</p>\",\"PeriodicalId\":45850,\"journal\":{\"name\":\"GMS Journal for Medical Education\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.5000,\"publicationDate\":\"2024-04-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11106576/pdf/\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"GMS Journal for Medical Education\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3205/zma001675\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/1/1 0:00:00\",\"PubModel\":\"eCollection\",\"JCR\":\"Q2\",\"JCRName\":\"EDUCATION, SCIENTIFIC DISCIPLINES\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"GMS Journal for Medical Education","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3205/zma001675","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/1/1 0:00:00","PubModel":"eCollection","JCR":"Q2","JCRName":"EDUCATION, SCIENTIFIC DISCIPLINES","Score":null,"Total":0}
Crafting medical MCQs with generative AI: A how-to guide on leveraging ChatGPT.
As medical educators grapple with the consistent demand for high-quality assessments, the integration of artificial intelligence presents a novel solution. This how-to article delves into the mechanics of employing ChatGPT for generating Multiple Choice Questions (MCQs) within the medical curriculum. Focusing on the intricacies of prompt engineering, we elucidate the steps and considerations imperative for achieving targeted, high-fidelity results. The article presents varying outcomes based on different prompt structures, highlighting the AI's adaptability in producing questions of distinct complexities. While emphasizing the transformative potential of ChatGPT, we also spotlight challenges, including the AI's occasional "hallucination", underscoring the importance of rigorous review. This guide aims to furnish educators with the know-how to integrate AI into their assessment creation process, heralding a new era in medical education tools.
期刊介绍:
GMS Journal for Medical Education (GMS J Med Educ) – formerly GMS Zeitschrift für Medizinische Ausbildung – publishes scientific articles on all aspects of undergraduate and graduate education in medicine, dentistry, veterinary medicine, pharmacy and other health professions. Research and review articles, project reports, short communications as well as discussion papers and comments may be submitted. There is a special focus on empirical studies which are methodologically sound and lead to results that are relevant beyond the respective institution, profession or country. Please feel free to submit qualitative as well as quantitative studies. We especially welcome submissions by students. It is the mission of GMS Journal for Medical Education to contribute to furthering scientific knowledge in the German-speaking countries as well as internationally and thus to foster the improvement of teaching and learning and to build an evidence base for undergraduate and graduate education. To this end, the journal has set up an editorial board with international experts. All manuscripts submitted are subjected to a clearly structured peer review process. All articles are published bilingually in English and German and are available with unrestricted open access. Thus, GMS Journal for Medical Education is available to a broad international readership. GMS Journal for Medical Education is published as an unrestricted open access journal with at least four issues per year. In addition, special issues on current topics in medical education research are also published. Until 2015 the journal was published under its German name GMS Zeitschrift für Medizinische Ausbildung. By changing its name to GMS Journal for Medical Education, we wish to underline our international mission.