[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-438969-105":59,"doc-detail-438969-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","identifying-health-conditions-in-older-adults-in-textual-health-records-using-deep-learning-based-natural-language-processing","Identifying health conditions in older adults in textual health records using deep learning-based natural language processing","","Many clinically significant health conditions in older adults remain underreported or only appear in unstructured entries in electronic health records. This study used 10.6 million free-text records from 102,525 patients aged 50–80 in Finland (2010–2022) to identify falls, incontinence, loneliness, and mobility limitations. A deep learning-based natural language processing model performed named entity recognition and was assessed using precision, recall, and F1 scores. Cox regression tested prognostic relevance for all-cause mortality and compared findings with diagnostic codes.",{"@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/identifying-health-conditions-in-older-adults-in-textual-health-records-using-deep-learning-based-natural-language-processing/438969/",{"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/identifying-health-conditions-in-older-adults-in-textual-health-records-using-deep-learning-based-natural-language-processing/438969.png","ImageObject",300,407,{"name":92,"@type":93},"Miles","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-01","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},"Which health conditions were identified from older adults’ free-text electronic health records?","Question",{"text":112,"@type":113},"Falls, incontinence, loneliness, and mobility limitations were identified using a named entity recognition approach over free-text entries.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How large was the dataset and what time period was it drawn from?",{"text":117,"@type":113},"The study used 10.6 million free-text entries from 102,525 patients aged 50–80, covering care settings in Finland from 2010 to 2022.",{"name":119,"@type":110,"acceptedAnswer":120},"How was model performance evaluated and how were results compared with diagnostic codes?",{"text":121,"@type":113},"Performance was measured using precision, recall, and F1 scores, and diagnostic-code data for incontinence and falls were collected for comparisons.","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},438969,1790885353,{"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":34,"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","Computational and Structural Biotechnology Journal 28 (2025) 341–347  \nContents lists available at ScienceDirect  \nComputational and Structural Biotechnology Journal  \njournal [homepage:](homepage: www.elsevier.com/locate/csbj)[ www.elsevier.com/locate/csbj](homepage: www.elsevier.com/locate/csbj)  \n| Research Article\u003Cbr>Identifying health conditions in older adults in textual health records using deep learning-based natural language processing |  |  | |\n| --- | --- | --- | --- |\n| Jake Lina,b , Anna Kuukka a, Tomi Korpia , Anna Tirkkonenc, Antti Kariluotod, Juho Kaijansinkkoa, Maija Satamoa , Hanna Pajulammie , Markus J. Haapanen b,f,g, Sergei H¨ayrynen h, Eetu Pursiainenh,i , Daniel Ciovicah, Mikaela B. von Bonsdorffc,g , Juulia Jylh¨av¨a a,b,j,* \u003Cbr>a Faculty of Medicine and Health Technology, Tampere University, Tampere, Finland b Department of Medical Epidemiology and Biostatistics, Karolinska Institutet, Sweden\u003Cbr>c Faculty of Sport and Health Sciences and Gerontology Research Center, University of Jyv¨askyl¨a, Finland d Faculty of Information Technology, University of Jyv¨askyl¨a, Jyv¨askyl¨a, Finland\u003Cbr>e Department of Geriatric Medicine, Central Finland Hospital Nova, Wellbeing Services County of Central Finland, Finland f Department of General Practice and Primary Health Care, University of Helsinki and Helsinki University Hospital, Helsinki, Finland g Folkh¨alsan Research Center, Helsinki, Finland\u003Cbr>h Veracell Oy, Tampere, Finland i Pursi AI Oy, Helsinki, Finland\u003Cbr>j Tampere Institute for Advanced Study, Tampere, Finland |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Natural language processing Electronic health records Falls\u003Cbr>Incontinence Loneliness Mobility limitations |  | Many clinically significant health conditions in older adults are underreported or only recorded in unstructured health records. These records, however, contain valuable information for patient care and prognosis. This study utilized 10.6 million free-text entries from the electronic health records of 102,525 patients aged 50–80 across various care settings in Finland from 2010 to 2022. A deep learning-based natural language processing model was employed to perform named entity recognition (NER) to identify falls, incontinence, loneliness, and mobility limitations from the free-text entries. The performance of the NER models was evaluated by precision, recall and F1 scores. Diagnostic codes for incontinence and falls were collected for comparisons. Cox regression models were used to assess the predictive value of the identified conditions for all-cause mortality. The NER models demonstrated excellent performance with recall, precision and F1 scores greater than 0.80 across the health conditions. Compared to diagnostic codes, NER identified greater numbers of falls (31987 vs 4090) and incontinence (7059 vs 3873) onsets and yielded greater hazard ratios for all-cause mortality: 1.31 vs 1.04 for falls and 1.99 vs 0.65 for incontinence. Deep learning-based NER models present new opportunities to identify vulnerable patients in free text health records. |  |\n\n1. Introduction  \nMany clinically significant conditions in older patients, such as incontinence, falls, mobility limitations and loneliness are frequently underreported, underdiagnosed or recorded only in unstructured data within electronic health records (EHRs) [1–3]. Data on these conditions nevertheless provide relevant information on individual’s health and functioning beyond diagnostic disease codes and hold significant value for more detailed patient assessment, care planning and prognostic  \npurposes. Until recently, identifying and extracting such information from the free-text EHRs has been inaccessible on a larger scale as traditional methods, such as manual abstraction are insufficient for processing unstructured text efficiently. Modern techniques, such as artificial intelligence (AI) -guided natural language processing (NLP) have been developed to ","cbCaijhFkT5ex5Pb","https://ap.wps.com/l/cbCaijhFkT5ex5Pb","pdf",1525901,"English","# Introduction\n## Motivation: underreporting in unstructured EHRs\n## NLP and named entity recognition background\n## Study objective and challenges\n## Methods overview (deep learning NER)\n# Abstract content","[{\"question\":\"Which health conditions were identified from older adults’ free-text electronic health records?\",\"answer\":\"Falls, incontinence, loneliness, and mobility limitations were identified using a named entity recognition approach over free-text entries.\"},{\"question\":\"How large was the dataset and what time period was it drawn from?\",\"answer\":\"The study used 10.6 million free-text entries from 102,525 patients aged 50–80, covering care settings in Finland from 2010 to 2022.\"},{\"question\":\"How was model performance evaluated and how were results compared with diagnostic codes?\",\"answer\":\"Performance was measured using precision, recall, and F1 scores, and diagnostic-code data for incontinence and falls were collected for comparisons.\"}]","Identifying health conditions in older adults in textual health records using deep learning-based natural language processing | PDF",1790687048,18]