[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118715-en":3,"doc-seo-118715-105":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},118715,1099513958607,"Jiven","https://ap-avatar.wpscdn.com/avatar/100002390cf8733938c?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778829742770036399",8,"Research & Report","Explainable Machine Learning for Real-Time Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations - Research Article","Continuous glucose monitoring (CGM) provides real-time glucose readings that can support proactive diabetes self-management, especially as young adults with type 1 diabetes take greater responsibility for their care. This study applies explainable machine learning to predict hypoglycemia (\u003C70 mg/dL) and hyperglycemia (>270 mg/dL) up to 60 minutes ahead using CGM data summarized into short-, medium-, and long-term glucose control features plus demographics. XGBoost achieves strong AUROC and precision versus baseline models, while SHAP identifies user-specific features driving risk predictions to inform more timely, individualized control.","Duckworth, C. , Guy, M. J. , Kumaran, A. , O'Kane, A. A. , Ayobi, A. , Chapman, A. , Marshall, P. , & Boniface, M. (2022) . Explainable Machine Learning for Real-Time Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations. Journal of Diabetes Science and Technology , 1-11. [https://doi.org/10.1177/19322968221103561](https://doi.org/10.1177/19322968221103561)  \nPublisher's PDF, also known as Version of record  \nLicense (if available): CC BY  \nLink to published version (if available):  \n10.1177/19322968221103561  \nLink to publication record in Explore Bristol Research  \nPDF-document  \nThis is the final published version of the article (version of record) . It first appeared online via Sage at  \n[https://doi.org/10.1177/19322968221103561 .Please](https://doi.org/10.1177/19322968221103561 .Please) refer to any applicable terms of use of the publisher.  \nUniversity of Bristol-Explore Bristol Research  \nGeneral rights  \nThis document is made available in accordance with publisher policies. Please cite only the published version using the reference above. Full terms of use are available: [http://www.bristol.ac.uk/red/research-policy/pure/user-guides/ebr-terms/](http://www.bristol.ac.uk/red/research-policy/pure/user-guides/ebr-terms/)  \nOriginal Article  \nExplainable Machine Learning for RealTime Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations  \nJournal of Diabetes Science and Technology 1–11  \n© 2022 Diabetes Technology Society  \nArticle reuse guidelines: [sagepub.com/journals-permissions](sagepub.com/journals-permissions)[ ](sagepub.com/journals-permissions)[DOI: 10.1177/19322968221103561](DOI: 10.1177/19322968221103561)[ ](DOI: 10.1177/19322968221103561)[journals.sagepub.com/home/dst](journals.sagepub.com/home/dst)  \nChristopher Duckworth, PhD 1, Matthew J. Guy, PhD2,4,  \nAnitha Kumaran, MRCPCH, PhD3, Aisling Ann O’Kane, PhD4,5, Amid Ayobi, PhD4, Adriane Chapman, PhD6, Paul Marshall, DPhil4,5,  \nand Michael Boniface, CEng MIET 1  \nAbstract  \nBackground: The occurrences of acute complications arising from hypoglycemia and hyperglycemia peak as young adults with type 1 diabetes (T1D) take control of their own care. Continuous glucose monitoring (CGM) devices provide real-time glucose readings enabling users to manage their control proactively. Machine learning algorithms can use CGM data to make ahead-of-time risk predictions and provide insight into an individual’s longer term control.  \nMethods: We introduce explainable machine learning to make predictions of hypoglycemia (\u003C70 mg/dL) and hyperglycemia ( >270 mg/dL) up to 60 minutes ahead of time. We train our models using CGM data from 153 people living with T1D in the CITY (CGM Intervention in Teens and Young Adults With Type 1 Diabetes)survey totaling more than 28 000 days of usage, which we summarize into (short-term, medium-term, and long-term) glucose control features along with demographic information. We use machine learning explanations (SHAP [SHapley Additive exPlanations]) to identify which features have been most important in predicting risk per user.  \nResults: Machine learning models (XGBoost) show excellent performance at predicting hypoglycemia (area under the receiver operating curve [AUROC]: 0.998, average precision: 0.953) and hyperglycemia (AUROC: 0.989, average precision: 0.931) in comparison with a baseline heuristic and logistic regression model.  \nConclusions: Maximizing model performance for glucose risk prediction and management is crucial to reduce the burden of alarm fatigue on CGM users. Machine learning enables more precise and timely predictions in comparison with baseline models. SHAP helps identify what about a CGM user’s glucose control has led to predictions of risk which can be used to reduce their long-term risk of complications.  \nKeywords  \ncontinuous glucose monitoring, explainable and trustworthy AI, feature extraction, hypoglycemia prediction, hyperglycemia prediction, machine le","cbCaiuKPoak4BGHB","https://ap.wps.com/l/cbCaiuKPoak4BGHB","pdf",1569606,1,12,"English","en",105,"# Abstract\n# Introduction\n# Background and Motivation\n# Methods\n## Prediction Targets and Time Horizon\n## Training Data and Feature Construction\n## Explainability with SHAP\n# Results\n## Model Performance\n# Conclusions","[{\"question\":\"What conditions and prediction horizon does the explainable model address?\",\"answer\":\"The model predicts hypoglycemia (\\u003c70 mg/dL) and hyperglycemia (\\u003e270 mg/dL) up to 60 minutes ahead using CGM-derived features.\"},{\"question\":\"How were the models trained and what data was used?\",\"answer\":\"Models were trained on CGM data from 153 people with type 1 diabetes from the CITY survey, covering more than 28,000 days, summarized into short-, medium-, and long-term glucose control features with demographic information.\"},{\"question\":\"How does the study ensure interpretability and personalization of risk?\",\"answer\":\"SHAP (SHapley Additive exPlanations) is used to identify which features are most important for predicting risk for each individual user, supporting tailored control recommendations.\"}]","Explainable Machine Learning for Real-Time Hypoglycemia and Hyperglycemia Prediction and Personalized Control Recommendations - Research Article | PDF",1785719887,30,{"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},"explainable-machine-learning-for-real-time-hypoglycemia-and-hyperglycemia-prediction-and-personalized-control-recommendations-research-article","",{"@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/explainable-machine-learning-for-real-time-hypoglycemia-and-hyperglycemia-prediction-and-personalized-control-recommendations-research-article/118715/",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","2026-08-03",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 conditions and prediction horizon does the explainable model address?","Question",{"text":75,"@type":76},"The model predicts hypoglycemia (\u003C70 mg/dL) and hyperglycemia (>270 mg/dL) up to 60 minutes ahead using CGM-derived features.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How were the models trained and what data was used?",{"text":80,"@type":76},"Models were trained on CGM data from 153 people with type 1 diabetes from the CITY survey, covering more than 28,000 days, summarized into short-, medium-, and long-term glucose control features with demographic information.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the study ensure interpretability and personalization of risk?",{"text":84,"@type":76},"SHAP (SHapley Additive exPlanations) is used to identify which features are most important for predicting risk for each individual user, supporting tailored control recommendations.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"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"]