{"id":29071,"date":"2025-10-12T04:58:00","date_gmt":"2025-10-11T20:58:00","guid":{"rendered":"https:\/\/csccm.org.cn\/?p=29071"},"modified":"2025-10-12T08:16:58","modified_gmt":"2025-10-12T00:16:58","slug":"chest%e5%8f%91%e8%a1%a8%e8%ae%ba%e6%96%87%ef%bc%9a%e4%b8%93%e5%ae%b6%e4%b8%8e%e5%a4%a7%e8%af%ad%e8%a8%80%e6%a8%a1%e5%9e%8b%e6%9c%ba%e6%a2%b0%e9%80%9a%e6%b0%94%e9%a2%86%e5%9f%9f%e5%a4%9a%e9%80%89","status":"publish","type":"post","link":"https:\/\/csccm.org.cn\/?p=29071","title":{"rendered":"[Chest\u53d1\u8868\u8bba\u6587]\uff1a\u4e13\u5bb6\u4e0e\u5927\u8bed\u8a00\u6a21\u578b\u673a\u68b0\u901a\u6c14\u9886\u57df\u591a\u9009\u9898\u8d28\u91cf"},"content":{"rendered":"\n<p>Original Research<\/p>\n\n\n\n<h1 class=\"wp-block-heading\" id=\"screen-reader-main-title\">Quality of Human Expert versus Large Language Model Generated Multiple Choice Questions in the Field of Mechanical Ventilation<\/h1>\n\n\n\n<h3 class=\"wp-block-heading\">Sami\u00a0Safadi,\u00a0Roxana\u00a0Amirahmadi,\u00a0Abdulhakim\u00a0Tlimat, et al<\/h3>\n\n\n\n<h3 class=\"wp-block-heading\">Chest Available online 18 July 2025<\/h3>\n\n\n\n<h3 class=\"wp-block-heading\">https:\/\/doi.org\/10.1016\/j.chest.2025.07.005<\/h3>\n\n\n\n<h2 class=\"wp-block-heading\">Abstract<\/h2>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"sectitle0015\">Background<\/h3>\n\n\n\n<p>Mechanical ventilation (MV) is a critical competency in critical care training, yet standardized methods for assessing MV-related knowledge are lacking. Traditional multiple-choice question (MCQ) development is resource-intensive, and prior studies have suggested that generative AI tools could streamline question creation. However, the quality of AI-generated MCQs remains unclear.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"sectitle0020\">Research Question<\/h3>\n\n\n\n<p>Are MCQs generated by ChatGPT non-inferior to human-expert (HE) created questions in terms of quality and relevance for MV education.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"sectitle0025\">Study Design and Methods<\/h3>\n\n\n\n<p>Three key MV topics were selected: Equation of Motion &amp; Ohm\u2019s Law, Tau &amp; Auto PEEP, and Oxygenation. Fifteen learning objectives were used to generate 15 AI-written MCQs via a standardized prompt with ChatGPT (model o1-preview-2024-09-12). A group of 31 faculty experts, all of whom regularly teach MV, evaluated both AI-generated and HE-generated MCQs. Each MCQ was assessed based on its alignment with learning objectives, accuracy of chosen answer, clarity of stem, plausibility of distractors, and difficulty level. The faculty members were blinded to the provenance of the MCQ questions. The non-inferiority margin was predefined as 15% of the total possible score (-3.45).<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"sectitle0030\">Results<\/h3>\n\n\n\n<p>AI-generated MCQs were statistically non-inferior to expert-written MCQs (95% upper CI: [-1.15, \u221e]). Additionally, respondents were unable to reliably differentiate AI-generated from HE-written MCQs (p = 0.32).<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"sectitle0035\">Interpretation<\/h3>\n\n\n\n<p>AI-generated MCQs using ChatGPT o1 are comparable in quality to those written by human experts. Given the time and resource-intensive nature of human MCQ development, AI-assisted question generation may serve as an efficient and scalable alternative for medical education assessment, even in highly specialized domains such as mechanical ventilation.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\" id=\"sectitle0040\">Clinical Trial Registration<\/h3>\n\n\n\n<p>None<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Original Research Quality of Human Expert versus Large  [&hellip;]<\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":[],"categories":[32,23],"tags":[],"_links":{"self":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/29071"}],"collection":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=29071"}],"version-history":[{"count":1,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/29071\/revisions"}],"predecessor-version":[{"id":29072,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=\/wp\/v2\/posts\/29071\/revisions\/29072"}],"wp:attachment":[{"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=29071"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=29071"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/csccm.org.cn\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=29071"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}