[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-436196-105":59,"doc-detail-436196-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","using-machine-learning-to-identify-key-subject-categories-predicting-the-pre-clerkship-and-clerkship-performance-8-year-cohort-study","Using machine learning to identify key subject categories predicting the pre-clerkship and clerkship performance: 8-year cohort study","","Medical students require a strong knowledge foundation, and clerkship serves as a pivotal transition where performance forecasts further development. This 8-year cohort study builds machine-learning prediction models to identify academic subjects that influence both pre-clerkship and clerkship performance. Data from students graduating between 2011 and 2019 were preprocessed, then models were trained and validated using 10-fold cross-validation. Results link multiple subject categories to higher clerkship outcomes and achieve strong predictive performance, including a random-forest model with high accuracy and AUC.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/using-machine-learning-to-identify-key-subject-categories-predicting-the-pre-clerkship-and-clerkship-performance-8-year-cohort-study/436196/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/using-machine-learning-to-identify-key-subject-categories-predicting-the-pre-clerkship-and-clerkship-performance-8-year-cohort-study/436196.png","ImageObject",300,407,{"name":92,"@type":93},"Miles","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-30","2026-09-29",true,{"@type":102,"interactionType":103,"userInteractionCount":14},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What was the purpose of this study?","Question",{"text":112,"@type":113},"To identify subjects that could predict pre-clerkship and clerkship performance, helping medical students learn more efficiently to achieve strong clerkship outcomes.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How were prediction models developed and validated?",{"text":117,"@type":113},"A cohort dataset (2011–2019 graduates) was used to train machine-learning models, with data preprocessing and 10-fold cross-validation for validation.",{"name":119,"@type":110,"acceptedAnswer":120},"Which subject categories showed predictive ability for clerkship performance?",{"text":121,"@type":113},"For social science topics, medical humanities and sociology; for basic science, chemistry and physician scientist-related training; and within basic medical science, pharmacology, immunology-microbiology, and histology showed predictive ability above the top tertile.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},436196,1790767257,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":14,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":29,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":143,"read_time":144},13056703019404,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","J Chin MedAssoc  \nOriginal article  \nUsing machine learning to identify key subject categories predicting the pre-clerkship and clerkship performance: 8-year cohort study  \nShiau-Shian Huanga,b, Yu-Fan Lina, Anna YuQing Huangc, Ji-Yang Linc, Ying-Ying Yanga,b,*,  \nSheng-Min Lina, Wen-Yu Lina, Pin-Hsiang Huanga, Tzu-Yao Chenc, Stephen J. H. Yangc,*, Jiing-Feng Lirnga,b, Chen-Huan Chena,b  \naDepartment of Medical Education, Clinical Innovation Center, Taipei Veterans General Hospital, Taipei, Taiwan, ROC; bDepartment of Medicine, College of Medicine, National Yang Ming Chiao Tung University, Taipei, Taiwan, ROC; cDepartment of Computer Science and Information Engineering, National Central University, Taoyuan, Taiwan, ROC  \nAbstract  \nBackground: Medical students need to build a solid foundation of knowledge to become physicians. Clerkship is often considered the first transition point, and clerkship performance is essential for their development. We hope to identify subjects that could predict the clerkship performance, thus helping medical students learn more efficiently to achieve high clerkship performance. Methods: This cohort study collected background and academic data from medical students who graduated between 2011 and 2019. Prediction models were developed by machine learning techniques to identify the affecting features in predicting the pre-clerkship performance and clerkship performance. Following serial processes of data collection, data preprocessing before machine learning, and techniques and performance of machine learning, different machine learning models were trained and validated using the 10-fold cross-validation method.  \nResults: Thirteen subjects from the pre-med stage and 10 subjects from the basic medical science stage with an area under the ROC curve (AUC) >0 .7 for either pre-clerkship performance or clerkship performance were found. In each subject category, medical humanities and sociology in social science, chemistry, and physician scientist-related training in basic science, and pharmacology, immunology-microbiology, and histology in basic medical science have predictive abilities for clerkship performance above the top tertile. Using a machine learning technique based on random forest, the prediction model predicted clerkship performance with 95% accuracy and 88% AUC.  \nConclusion: Clerkship performance was predicted by selected subjects or combination of different subject categories in the premed and basic medical science stages. The demonstrated predictive ability of subjects or categories in the medical program may facilitate students’ understanding of how these subjects or categories of the medical program relate to their performance in the clerkship to enhance their preparedness for the clerkship.  \nKeywords: Area under the ROC curve; Cohort study; Machine learning; Medical students; Random forest  \n1. INTRODUCTION  \nTo become physicians, medical students must undergo a maturation process that is long and complicated; over this course, the pathway is paved with grit.1,2 A broad knowledge base in premed, basic medical science, and clinical medicine is necessary for the ideal doctor to provide effective patient care.3–5 To build  \n* Address correspondence. Prof. Ying-Ying Yang, Department of Medical Education, Taipei Veterans General Hospital, 201, Section 2, Shi-Pai Road, Taipei 112, Taiwan, [ROC. E-mail address: yangyy@vghtpe.gov.tw](ROC. E-mail address: yangyy@vghtpe.gov.tw) (Y.-Y. Yang); Prof. Stephen J. H. Yang, Department of Computer Science and Information Engineering, National, Central University, 300, Zhongda Road, Taoyuan 320, Taiwan, [ROC. E-mail address: jhyang@csie.ncu.edu.tw](ROC. E-mail address: jhyang@csie.ncu.edu.tw) (S. J. -H. Yang). Conflicts of interest: The authors declare that they have no conflicts of interest related to the subject matter or materials discussed in this article.  \nJournal of Chinese Medical Association. (2024) 87: 609-614.  \nReceived May 30, 2023; accept","cbCaik58LIKWYPXm","https://ap.wps.com/l/cbCaik58LIKWYPXm","pdf",534792,"English","# Abstract\n# Introduction\n# Methods\n# Results\n# Conclusion","[{\"question\":\"What was the purpose of this study?\",\"answer\":\"To identify subjects that could predict pre-clerkship and clerkship performance, helping medical students learn more efficiently to achieve strong clerkship outcomes.\"},{\"question\":\"How were prediction models developed and validated?\",\"answer\":\"A cohort dataset (2011–2019 graduates) was used to train machine-learning models, with data preprocessing and 10-fold cross-validation for validation.\"},{\"question\":\"Which subject categories showed predictive ability for clerkship performance?\",\"answer\":\"For social science topics, medical humanities and sociology; for basic science, chemistry and physician scientist-related training; and within basic medical science, pharmacology, immunology-microbiology, and histology showed predictive ability above the top tertile.\"}]","Using machine learning to identify key subject categories predicting the pre-clerkship and clerkship performance: 8-year cohort study | PDF",1790677107,15]