[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-426068-105":59,"doc-detail-426068-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","a-classification-approach-to-determine-cognitive-impairment-stage-from-metabolomic-data-poster-abstract","A Classification Approach to Determine Cognitive Impairment Stage from Metabolomic Data - Poster Abstract","","Alzheimer’s Disease (AD) is a neurodegenerative disorder where metabolic changes may appear years before clinical onset. This study applies machine learning to classify serum-derived metabolites that distinguish early mild cognitive impairment (EMCI) from late mild cognitive impairment (LMCI). Using publicly available ADNI baseline data from 643 participants, a two-stage feature selection framework (univariate ANOVA F-testing then recursive feature elimination) identifies diagnostic metabolites. A Random Forest model with balanced weighting produces a consistent five-metabolite panel with validation accuracy around 76% and development accuracy near 78%, highlighting gut–liver and energy metabolism disruptions.",{"@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/a-classification-approach-to-determine-cognitive-impairment-stage-from-metabolomic-data-poster-abstract/426068/",{"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/a-classification-approach-to-determine-cognitive-impairment-stage-from-metabolomic-data-poster-abstract/426068.png","ImageObject",300,407,{"name":92,"@type":93},"Rizky","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-25","2026-09-28",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What cognitive impairment stages were distinguished in this study?","Question",{"text":112,"@type":113},"The study differentiates early mild cognitive impairment (EMCI) from late mild cognitive impairment (LMCI).","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How were important metabolites selected?",{"text":117,"@type":113},"A two-stage feature selection pipeline was used: univariate ANOVA F-testing to shortlist the top 30 features, followed by multivariate recursive feature elimination to finalize 15 features. The selection was repeated across multiple training/testing splits to improve reliability.",{"name":119,"@type":110,"acceptedAnswer":120},"Which metabolite panel emerged as most consistent, and how accurate was it?",{"text":121,"@type":113},"Across repetitions, a five-metabolite panel (glyceric acid, hyocholic acid, hyodeoxycholic acid, tauro-muricholic acid, and succinic acid) appeared consistently. It achieved about 76% ± 3% accuracy on unseen validation data and about 78% ± 6% on development data.","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},426068,1791282776,{"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":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":8,"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":81},962085564807,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","1044 Innovation in Aging, 2025, Vol. 9, No. S2  \nSESSION 8000 (POSTER)   \nLATE BREAKING POSTER SESSION I  \nAbstract citation ID: igaf122.3516  \nA CLASSIFICATION APPROACH TO DETERMINE  \nCOGNITIVE IMPAIRMENT STAGE FROM  \nMETABOLOMIC DATA  \nAraya Cserepy, and Joshua Chuah, Union College, Schenectady, New York, United States  \nAlzheimer’s Disease (AD) is a neurodegenerative disorder often marked by amyloid beta and tau accumulation, but metabolic changes can precede clinical onset by several years. Metabolites in particular have been implicated as early indicators of brain dysfunction. As such, this study applied machine learning to identify serum-derived metabolites distinguishing early (EMCI) from late mild cognitive impairment (LMCI). Using publicly available metabolite data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI), we analyzed baseline profiles from 643 participants (222 EMCI, 421 LMCI) across 104 features. A two-stage feature selection framework combined univariate ANOVA F-testing (top 30 features) with multivariate recursive feature elimination (final 15 features) to find the most important metabolites for diagnosis. This feature selection framework was repeated across different training/ testing set splits to ensure the reliability of the features selected.  \nRandom Forest classification with balanced weighting addressed dataset imbalance. Across all repetitions, a core panel of five metabolites emerged consistently across validation runs: glyceric acid, hyocholic acid (HCA), hyodeoxycholic acid (HDCA), tauro-muricholic acid (TAMCA), and succinic acid. These metabolites achieved 76% ± 3% accuracy on unseen validation data and 78% ± 6% on development data. Notably, the panel included bile acid metabolites (HCA, HDCA, TAMCA) and energy-related metabolites (glyceric acid, succinic acid), pointing to disruptionsin the gut–liver axis and cellular metabolism during disease progression. Overall, this work highlights metabolic alterations that accompany the transition from EMCI to LMCI and demonstrates the potential of machine learning–based metabolomics for early detection and diagnosis in AD.","cbCaiuiGess1hzHo","https://ap.wps.com/l/cbCaiuiGess1hzHo","pdf",929985,"English","# Late Breaking Poster Session I\n## Objective and background\n## Data and participants\n## Feature selection approach\n## Classification model and results\n## Interpretation and significance","[{\"question\":\"What cognitive impairment stages were distinguished in this study?\",\"answer\":\"The study differentiates early mild cognitive impairment (EMCI) from late mild cognitive impairment (LMCI).\"},{\"question\":\"How were important metabolites selected?\",\"answer\":\"A two-stage feature selection pipeline was used: univariate ANOVA F-testing to shortlist the top 30 features, followed by multivariate recursive feature elimination to finalize 15 features. The selection was repeated across multiple training/testing splits to improve reliability.\"},{\"question\":\"Which metabolite panel emerged as most consistent, and how accurate was it?\",\"answer\":\"Across repetitions, a five-metabolite panel (glyceric acid, hyocholic acid, hyodeoxycholic acid, tauro-muricholic acid, and succinic acid) appeared consistently. It achieved about 76% ± 3% accuracy on unseen validation data and about 78% ± 6% on development data.\"}]","A Classification Approach to Determine Cognitive Impairment Stage from Metabolomic Data - Poster Abstract | PDF",1790639275]