[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122305-en":3,"doc-seo-122305-105":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":20,"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},122305,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Delirium Detection Using Wearable Sensors and Machine Learning in Patients with Intracerebral Hemorrhage","Delirium is linked to poorer outcomes in stroke and neurocritical patients, yet daily screening remains difficult with existing bedside tools. A prospective observational cohort study evaluated machine learning models to detect post-stroke delirium episodes using wearable activity-monitor data combined with stroke-related clinical features. Thirty-nine patients with acute intracerebral hemorrhage and hemiparesis were followed over one year. Adding wrist actigraphy to clinical information significantly improved day-to-day prediction accuracy and F1 score, with nighttime activity features proving especially informative. Results support actigraphy-assisted, clinically actionable delirium prediction.","1 Delirium Detection Using Wearable Sensors and Machine Learning in Patients with  \n2 Intracerebral Hemorrhage  \n3  \n4 Abdullah Ahmed1* , Augusto Garcia-Agundez, PhD1 ,2* , Ivana Petrovic, PhD1 , Fatemeh Radaei, MS1 , James  \n5 Fife BS1 , John Zhou1 , Hunter Karas1 , Scott Moody, BS3 , Jonathan Drake, MD3 , Richard N. Jones, ScD4 , 6 Carsten Eickhoff, PhD1†, Michael E. Reznik, MD3†  \n7  \n8 Author affiliations:  \n9 1 Brown Center for Biomedical Informatics, Brown University, Providence, RI, United States  \n10 2 IMDEA Networks Institute, Madrid, Spain  \n11 3 Department of Neurology, Brown University, Providence, RI, United States  \n12 4 Department of Psychiatry, Brown University, Providence, RI, United States  \n13 * Equally collaborating authors  \n14 †Equally collaborating senior authors 15  \n16 Corresponding authors:  \n17 Michael Reznik  \n18 Division of Neurocritical Care, Rhode Island Hospital  \n19 593 Eddy Street, APC 712  \n20 Providence, RI 02903  \n21 [Email: ](Email: Michael_Reznik@brown.edu)[Michael_Reznik@brown.edu](Email: Michael_Reznik@brown.edu)[ ](Email: Michael_Reznik@brown.edu)22  \n23 Carsten Eickhoff  \n24 233 Richmond St , Room 209  \n25 Providence, RI, 02912  \n26 [Email: ](Email: Carsten@brown.edu)[Carsten@brown.edu](Email: Carsten@brown.edu)[ ](Email: Carsten@brown.edu)27  \n28 Keywords: Delirium, Neurocritical Care, Stroke, Intracerebral Hemorrhage, Actigraphy, Machine  \n29 Learning, Wearable Electronic Devices 30  \n31 Abstract word count: 300  \n32 Manuscript word count: 2877  \n33 Figures: 3  \n34 Tables: 2 35  \n36 Author Contributions: 37  \n38 • Conceptualization and methodology: MER, CE, RNJ  \n39 • Funding acquisition: MER, CE  \n40 • Investigation and analysis of data: AA, AGA, IP, FR, JF, JZ, HK, SM, JD, CE, MER  \n41 • Supervision: MER, CE  \n42 • Drafting and/or revising significant portions of the manuscript: AA, AGA, CE, MER 43  \n44  \n45  \n46  \n47 ABSTRACT  \n48 Objective. Delirium is associated with worse outcomes in patients with stroke and neurocritical illness, but  \n49 delirium detection in these patients can be challenging with existing screening tools. To address this gap, 50 we aimed to develop and evaluate machine learning models that detect episodes of post-stroke delirium  \n51 based on data from wearable activity monitors in conjunction with stroke-related clinical features.  \n52 Design. Prospective observational cohort study.  \n53 Setting. Neurocritical Care and Stroke Units at an academic medical center.  \n54 Patients. We recruited 39 patients with moderate-to-severe acute intracerebral hemorrhage (ICH) and  \n55 hemiparesis over a 1-year period (mean [SD] age 71.3 [12 .20], 54% male, median [IQR] initial NIHSS 14.5 56 [6], median [IQR] ICH score 2 [1]) .  \n57 Measurements & Main Results. Each patient received daily assessments for delirium by an attending  \n58 neurologist, while activity data were recorded throughout each patient’s hospitalization using wrist-worn  \n59 actigraph devices (on both paretic and non-paretic arms) . We compared the predictive accuracy of Random  \n60 Forest, SVM and XGBoost machine learning methods in classifying daily delirium status using clinical  \n61 information alone and combined with actigraph data. Among our study cohort, 85% of patients (n=33) had  \n62 at least one delirium episode, while 71% of monitoring days (n=209) were rated as days with delirium.  \n63 Clinical information alone had a low accuracy in detecting delirium on a day-to-day basis (Accuracy mean 64 [SD] 62%[18%], F1 score mean [SD] 50%[17%]) . Prediction performance improved significantly (p\u003C0 .001)  \n65 with the addition of actigraph data (Accuracy mean [SD] 74%[10%], F1 score 65%[10%]) . Among  \n66 actigraphy features, night-time actigraph data were especially relevant for classification accuracy.  \n67 Conclusions. We found that actigraphy in conjunction with machine learning models improves clinical  \n68 detection of delirium in patients with stroke, thus paving the way to make actigraph-assisted","cbCailoOv55rR1W7","https://ap.wps.com/l/cbCailoOv55rR1W7","pdf",390779,1,19,"English","en",105,"# Abstract\n## Objective\n## Design and Setting\n## Patients and Measurements\n## Main Results\n## Conclusions\n# Introduction","[{\"question\":\"Why is delirium detection challenging in patients with stroke and neurocritical illness?\",\"answer\":\"Existing screening tools can be unreliable in stroke, neurocritical illness, and dementia. Bedside diagnosis is also labor intensive, making automated identification important.\"},{\"question\":\"What data sources were used to predict delirium in the study?\",\"answer\":\"Daily delirium status was assessed by a neurologist, while wrist-worn actigraph devices continuously recorded activity data on both paretic and non-paretic arms.\"},{\"question\":\"Which machine learning approach performed best and what improved prediction?\",\"answer\":\"The study compared Random Forest, SVM, and XGBoost models. Prediction accuracy improved significantly when actigraphy data were added to clinical information, with nighttime actigraphy features especially relevant.\"}]","Delirium Detection Using Wearable Sensors and Machine Learning in Patients with Intracerebral Hemorrhage | PDF",1785809912,48,{"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},"delirium-detection-using-wearable-sensors-and-machine-learning-in-patients-with-intracerebral-hemorrhage","",{"@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/delirium-detection-using-wearable-sensors-and-machine-learning-in-patients-with-intracerebral-hemorrhage/122305/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"Why is delirium detection challenging in patients with stroke and neurocritical illness?","Question",{"text":75,"@type":76},"Existing screening tools can be unreliable in stroke, neurocritical illness, and dementia. Bedside diagnosis is also labor intensive, making automated identification important.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What data sources were used to predict delirium in the study?",{"text":80,"@type":76},"Daily delirium status was assessed by a neurologist, while wrist-worn actigraph devices continuously recorded activity data on both paretic and non-paretic arms.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning approach performed best and what improved prediction?",{"text":84,"@type":76},"The study compared Random Forest, SVM, and XGBoost models. Prediction accuracy improved significantly when actigraphy data were added to clinical information, with nighttime actigraphy features especially relevant.","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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]