[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122478-en":3,"doc-seo-122478-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122478,1374391974585,"Genevieve","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning and Deep Learning Models for Automated Protocoling of Emergency Brain MRI Using Text from Clinical Referrals","Machine learning and deep learning models are developed and evaluated to automate protocol selection for emergency brain MRI using free-text from clinical referral letters. A retrospective single-institution cohort of 1953 emergency brain MRI referrals (2016–2019) is used, with neuroradiologists labeling imaging protocol and contrast-agent use as the reference standard. Naive Bayes, SVM, and XGBoost, alongside pretrained BERT and GPT-3.5, are trained on datasets of varying sizes and assessed on a test set, showing strong predictive accuracy, particularly with GPT-3.5.","Machine Learning and Deep Learning Models for Automated Protocoling of Emergency Brain MRI Using Text from Clinical Referrals  \nHeidi J. Huhtanen, MD1 • Mikko J. Nyman, MD, PhD1 • Antti Karlsson, PhD2 • Jussi Hirvonen, MD, PhD1  \nAuthor affiliations, funding, and conflicts of interest are listed at the end of this article. See also commentary by Strotzer in this issue. Radiology: Artificial Intelligence 2025; 7(3):e230620 • [https://doi.org/10.1148/ryai.230620](https://doi.org/10.1148/ryai.230620) • Content codes:   \nPurpose: To develop and evaluate machine learning and deep learning–based models for automated protocoling of emergency brain MRI scans based on clinical referral text.  \nMaterials and Methods: In this single-institution, retrospective study of 1953 emergency brain MRI referrals from January 2016 to January 2019, two neuroradiologists labeled the imaging protocol and use of contrast agent as the reference standard. Three machine learning algorithms (naive Bayes, support vector machine, and XGBoost) and two pretrained deep learning models (Finnish bidirectional encoder representations from transformers [BERT] and generative pretrained transformer [GPT]–3.5 [GPT-3.5 Turbo; Open AI]) were developed to predict the MRI protocol and need for a contrast agent. Each model was trained with three datasets (100% of training data, 50% of training data, and 50% plus augmented training data) . Prediction accuracy was assessed with a test set.  \nResults: The GPT-3.5 models trained with 100% of the training data performed best in both tasks, achieving an accuracy of 84%(95% CI: 80, 88) for the correct protocol and 91%(95% CI: 88, 94) for the contrast agent. BERT had an accuracy of 78%(95% CI: 74, 82) for the protocol and 89%(95% CI: 86, 92) for the contrast agent. The best machine learning model in the protocol task was XGBoost (accuracy, 78%; 95% CI: 73, 82), and the best machine learning models in the contrast agent task were support vector machine and XGBoost (accuracy, 88%; 95% CI: 84, 91 for both) . The accuracies of two nonneuroradiologists were 80%–83% in the protocol task and 89%–91% in the contrast medium task.  \nConclusion: Machine learning and deep learning models demonstrated high performance in automatic protocoling of emergency brain MRI scans based on text from clinical referrals.  \nSupplemental material is available for this article.  \nPublished under a CC BY 4.0 license.  \nPr3ot5oc%o–li6ng2o%foifncomradinloggiis’agtiingme s(tu1,d2esIisn estiememrgated to takency radioleogy, protocoling is a frequent cause of interruptions, which may increase cognitive workload and risk of errors (3,4) . However, careful protocoling is essential for answering the clinical question. Errors are common in protocoling (5,6), which is often done by less experienced residents or nonsubspecialist radiologists in an emergency setting. During the last decade, advancements in artificial intelligence and natural language processing (NLP) (7) have opened new possibilities for streamlining the protocoling process.  \nAlthough most NLP research in radiology has focused on analyzing radiology reports and communicating critical findings (8,9), there is growing interest in applying NLP for automatic protocol selection (10–21) . Promising results have been shown with traditional machine learning (ML) algorithms such as support vector machine (SVM), random forest, and XGBoost (10–13) . Deep learning (DL)–based large pretrained language models, such as bidirectional encoder representations from transformers (BERT) (22), have also demonstrated good performance in protocoling (14,15) . Specific versions of BERT tailored for radiology might further enhance the results (15,23), although these have been limited to English language. Larger language models, such as the generative pretrained transformer (GPT) (24) from OpenAI, have recently gained attention for their ability to learn complex tasks with limited data and achieve humanlike performance in tasks s","cbCaiumrXjxnORL4","https://ap.wps.com/l/cbCaiumrXjxnORL4","pdf",1501295,1,9,"English","en",105,"# Purpose\n# Materials and Methods\n## Data and reference standard\n## Models and training\n## Evaluation metrics\n# Results\n# Conclusion\n# Abbreviations\n# Summary","[{\"question\":\"What problem does the study address in emergency brain MRI workflows?\",\"answer\":\"It targets automated protocoling for emergency brain MRI by predicting the appropriate imaging protocol and whether a contrast agent is needed from clinical referral text.\"},{\"question\":\"Which machine learning and deep learning models were evaluated?\",\"answer\":\"The study evaluates naive Bayes, support vector machine, and XGBoost, plus pretrained deep learning models including BERT and GPT-3.5.\"},{\"question\":\"How were model predictions trained and evaluated?\",\"answer\":\"Models were trained using different dataset-size setups (full training data, 50% training data, and augmented 50% plus additional data) and accuracy was measured on a test set.\"}]","Machine Learning and Deep Learning Models for Automated Protocoling of Emergency Brain MRI Using Text from Clinical Referrals | PDF",1785810862,23,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"machine-learning-and-deep-learning-models-for-automated-protocoling-of-emergency-brain-mri-using-text-from-clinical-referrals","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/machine-learning-and-deep-learning-models-for-automated-protocoling-of-emergency-brain-mri-using-text-from-clinical-referrals/122478/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in emergency brain MRI workflows?","Question",{"text":75,"@type":76},"It targets automated protocoling for emergency brain MRI by predicting the appropriate imaging protocol and whether a contrast agent is needed from clinical referral text.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning and deep learning models were evaluated?",{"text":80,"@type":76},"The study evaluates naive Bayes, support vector machine, and XGBoost, plus pretrained deep learning models including BERT and GPT-3.5.",{"name":82,"@type":73,"acceptedAnswer":83},"How were model predictions trained and evaluated?",{"text":84,"@type":76},"Models were trained using different dataset-size setups (full training data, 50% training data, and augmented 50% plus additional data) and accuracy was measured on a test set.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]