Mashaal Sabqat, Rehan Ahmed Khan, Masood Jawaid, Madiha Sajjad
{"title":"Artificial Intelligence Meets Item Analysis (AI meets IA): A Study of Chatbot Training and Performance in detecting and correcting MCQ Flaws.","authors":"Mashaal Sabqat, Rehan Ahmed Khan, Masood Jawaid, Madiha Sajjad","doi":"10.12669/pjms.41.3.11224","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>To explore the potential of AI-powered chatbots, specifically ChatGPT, in identifying and correcting flaws in MCQs.</p><p><strong>Methods: </strong>A three-phase-Interventional study was conducted from February to August 2023 at Riphah International University, Islamabad. In Phase-1, flawed MCQs were selected from the NBME guide and fed into ChatGPT. ChatGPT identified item flaws and suggested corrections. In Phase-2, ChatGPT was trained to detect flaws in MCQs with text data from the NBME item writing guide. In Phase-3, ChatGPT was again tested to detect flaws and correct MCQs. Data were analyzed using SPSS, Version 26 and presented using percentages and McNemar's test with exact conditional method.</p><p><strong>Results: </strong>ChatGPT could identify and correct flaws such as use of \"None of the above,\" \"Grammatical cues,\" \"absolute terms,\" and \"inconsistently presented numerical data.\" However, it struggled with flaws related to \"complicated stems,\" \"long or complex options,\" and \"vague frequency terms.\" After training, ChatGPT became better at identifying and correcting flaws related to complicated stems and absolute terms. It also struggled with recognizing \"nonparallel options,\" \"convergence,\" and \"word repetition,\" both before and after training. ChatGPT's performance deteriorated during peak hours. The test of significance showed no measurable increase in ChatGPT's efficiency in detecting item flaws (p = 1.00) and correcting them (p = 0.125).</p><p><strong>Conclusion: </strong>AI is revolutionizing industries and improving efficiency, but limitations exist in complex conversations, analysis, accuracy, and error prevention. Ongoing research is vital to unlocking AI's potential, especially in education.</p>","PeriodicalId":19958,"journal":{"name":"Pakistan Journal of Medical Sciences","volume":"41 3","pages":"652-656"},"PeriodicalIF":1.2000,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11911725/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Pakistan Journal of Medical Sciences","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.12669/pjms.41.3.11224","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0
Abstract
Objective: To explore the potential of AI-powered chatbots, specifically ChatGPT, in identifying and correcting flaws in MCQs.
Methods: A three-phase-Interventional study was conducted from February to August 2023 at Riphah International University, Islamabad. In Phase-1, flawed MCQs were selected from the NBME guide and fed into ChatGPT. ChatGPT identified item flaws and suggested corrections. In Phase-2, ChatGPT was trained to detect flaws in MCQs with text data from the NBME item writing guide. In Phase-3, ChatGPT was again tested to detect flaws and correct MCQs. Data were analyzed using SPSS, Version 26 and presented using percentages and McNemar's test with exact conditional method.
Results: ChatGPT could identify and correct flaws such as use of "None of the above," "Grammatical cues," "absolute terms," and "inconsistently presented numerical data." However, it struggled with flaws related to "complicated stems," "long or complex options," and "vague frequency terms." After training, ChatGPT became better at identifying and correcting flaws related to complicated stems and absolute terms. It also struggled with recognizing "nonparallel options," "convergence," and "word repetition," both before and after training. ChatGPT's performance deteriorated during peak hours. The test of significance showed no measurable increase in ChatGPT's efficiency in detecting item flaws (p = 1.00) and correcting them (p = 0.125).
Conclusion: AI is revolutionizing industries and improving efficiency, but limitations exist in complex conversations, analysis, accuracy, and error prevention. Ongoing research is vital to unlocking AI's potential, especially in education.
期刊介绍：
It is a peer reviewed medical journal published regularly since 1984. It was previously known as quarterly "SPECIALIST" till December 31st 1999. It publishes original research articles, review articles, current practices, short communications & case reports. It attracts manuscripts not only from within Pakistan but also from over fifty countries from abroad.
Copies of PJMS are sent to all the import medical libraries all over Pakistan and overseas particularly in South East Asia and Asia Pacific besides WHO EMRO Region countries. Eminent members of the medical profession at home and abroad regularly contribute their write-ups, manuscripts in our publications. We pursue an independent editorial policy, which allows an opportunity to the healthcare professionals to express their views without any fear or favour. That is why many opinion makers among the medical and pharmaceutical profession use this publication to communicate their viewpoint.
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号
