[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120093-en":3,"doc-seo-120093-105":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},120093,8796095462418,"Noah","https://ap-avatar.wpscdn.com/avatar/80000253c1241d02b47?x-image-process=image/resize,m_fixed,w_180,h_180&k=1778826106357471780",8,"Research & Report","Predicting Individual Patient and Hospital-Level Discharge Using Machine Learning","Accurately forecasting hospital discharge events can improve patient flow and the efficiency of healthcare delivery, yet machine learning approaches using diverse electronic health record data are not fully established. Using Oxfordshire, UK EHR data from February 2017 to January 2020, the study predicts discharges within 24 hours for elective and emergency admissions. Separate extreme gradient boosting models evaluate individual- and hospital-level performance, feature importance, subgroup robustness, and effects of training size, recency, and prediction timing.","[https://doi.org/10.1038/s43856-024-00673-x](https://doi.org/10.1038/s43856-024-00673-x)  \n\n| Predicting individual patient and hospitallevel discharge using machine learning\u003Cbr> Check for updates |  |  |\n| --- | --- | --- |\n| Jia Wei 1, Jiandong Zhou 1, Zizheng Zhang2, Kevin Yuan 2, Qingze Gu1, Augustine Luk1, Andrew J. Brent1,3, David A. Clifton 4,5, A. Sarah Walker1,6,7 & David W. Eyre 2,3,6,7  |  |  |\n| Abstract |  | Plain language summary |\n| Background Accurately predicting hospital discharge events could help improve patient flow and the efficiency of healthcare delivery. However, using machine learning and diverse electronic health record (EHR) data for this task remains incompletely explored.\u003Cbr>Methods We used EHR data from February-2017 to January-2020 from Oxfordshire, UK to predict hospital discharges in the next 24 h. We fitted separate extreme gradient boosting models for elective and emergency admissions, trained on the first two years of data and tested on the final year of data. We examined individual-level and hospital-level model performance and evaluated the impact of training data size and recency, prediction time, and performance in subgroups.\u003Cbr>Results Our models achieve AUROCs of 0 .87 and 0 .86, AUPRCs of 0 .66 and 0 .64, and F1 scores of 0.61 and 0.59 for elective and emergency admissions, respectively. These models outperform a logistic regression model using the same features and are substantially better than a baseline logistic regression model with more limited features. Notably, the relative performance increase from adding additional features is greaterthan the increase from using a sophisticated model. Aggregating individual probabilities, daily total discharge estimates are accurate with mean absolute errors of 8.9%(elective) and 4.9%(emergency) . The most informative predictors include antibiotic prescriptions, medications, and hospital capacity factors. Performance remains robust across patient subgroups and different training strategies, but is lower in patients with longer admissions and those who died in hospital. Conclusions Our findings highlight the potential of machine learning in optimising hospital patient flow and facilitating patient care and recovery. |  | Predicting when hospital patients are ready tobe discharged could help hospitals run more smoothly and improve patient care. In this study, we used three years of patient records from Oxfordshire, UK, to build a machine learning model that predicts discharges within the next 24 h. Our model includes both planned and emergency admissions. The model performs well at accurately predicting the probability, or chance, that an individual patient will be discharged and also estimating the total number of discharges each day. Important information for making the predictions includes whether patients are taking antibiotics and other medications, and whether the hospital is crowded. Overall, we show that machine learning could help hospitals manage patient flow and improve patient care. |\n| Increasing demand for healthcare, driven by changing population demographics, a rise in the prevalence of chronic diseases, societal changes, and technological advances, places significant strain on hospital resources1. In the United Kingdom (UK), the National Health Service (NHS) has faced escalating demand pressures in recent years, with an increasing number of admissions, prolonged waiting times in Emergency Departments, and financial challenges2,3. This has been exacerbated by the COVID-19 pandemic, resulting in substantial backlogs in both urgent and routine care4. With healthcare resources being inherently limited, there is a pressing need | to enhance the efficiency of healthcare services and improve hospital capacity management. A critical component is patientflowwithin hospitals, referring to the movement of patients from admission to discharge while ensuring they receive appropriate care and resources5. Optimising this could improve patient experience","cbCaicbFfQHYx5ml","https://ap.wps.com/l/cbCaicbFfQHYx5ml","pdf",1358468,1,14,"English","en",105,"# Background\n## Patient flow and discharge prediction needs\n# Methods\n## Data source and time window\n## Model design and training/testing strategy\n## Evaluation at individual and hospital levels\n# Results\n## Predictive performance and comparisons\n## Feature importance\n## Robustness across subgroups and training strategies\n# Conclusions\n## Implications for optimizing patient flow","[{\"question\":\"How did the study predict discharges, and for which admission types?\",\"answer\":\"It used EHR data from Oxfordshire, UK to predict discharges within the next 24 hours. Separate models were trained for elective and emergency admissions.\"},{\"question\":\"What evaluation metrics were used for individual and hospital-level prediction performance?\",\"answer\":\"Model performance was assessed using AUROC, AUPRC, and F1 scores for both elective and emergency admissions, along with aggregated daily discharge estimates with mean absolute errors.\"},{\"question\":\"Which factors were most informative for discharge prediction?\",\"answer\":\"The most informative predictors included antibiotic prescriptions, medications, and hospital capacity factors.\"}]","Predicting Individual Patient and Hospital-Level Discharge Using Machine Learning | PDF",1785728125,35,{"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},"predicting-individual-patient-and-hospital-level-discharge-using-machine-learning","",{"@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/predicting-individual-patient-and-hospital-level-discharge-using-machine-learning/120093/",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},"How did the study predict discharges, and for which admission types?","Question",{"text":75,"@type":76},"It used EHR data from Oxfordshire, UK to predict discharges within the next 24 hours. Separate models were trained for elective and emergency admissions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What evaluation metrics were used for individual and hospital-level prediction performance?",{"text":80,"@type":76},"Model performance was assessed using AUROC, AUPRC, and F1 scores for both elective and emergency admissions, along with aggregated daily discharge estimates with mean absolute errors.",{"name":82,"@type":73,"acceptedAnswer":83},"Which factors were most informative for discharge prediction?",{"text":84,"@type":76},"The most informative predictors included antibiotic prescriptions, medications, and hospital capacity factors.","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},[93,97,101,105,110,115,120,123,128,131,135],{"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":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]