[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127453-en":3,"doc-seo-127453-105":30,"detail-sidebar-cat-0-en-105":92},{"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},127453,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","Converse or reverse? Machine-learning modeling for disease progression - A study based on Alzheimer’s disease continuum cohort","Longitudinal changes from healthy aging to mild cognitive impairment and Alzheimer’s disease follow complex mechanisms. A five-model evaluation compared Random Forest, SVM, RBF networks, backpropagation networks, and convolutional neural networks to determine the importance of predictive markers across the health-to-dementia continuum. Using the ADNI cohort spanning ADNI1, ADNIGO, ADNI2, and ADNI3 phases, groups with stable, convertible, and reverse progression trajectories were analyzed. Results showed Random Forest superiority with strong sensitivity and specificity, highlighting visuospatial and memory cognitive dysfunction, amyloid-related neuroimaging biomarkers, and plasma APOE4 and neurofilament light chain as predictors.","NeuroImage 327 (2026) 121754  \nContents lists available at ScienceDirect  \nNeuroImage  \njournal [homepage:](homepage: www.elsevier.com/locate/ynimg)[ www.elsevier.com/locate/ynimg](homepage: www.elsevier.com/locate/ynimg)  \n| Converse or reverse? Machine-learning modeling for disease progression: A study based on Alzheimer’s disease continuum cohort\u003Cbr>Yujing Huang (黄玉晶)a,g,h,1,*, Hao Zhang (张灏)a,1, Buqing Ma (马步青)a, Zhe Yu (俞哲)a, Shenyi Dai (戴珅懿)e, Lu Cheng (程璐)f, Li Su (苏里)c,d, Alzheimer’s Disease Neuroimaging Initiative (ADNI), Gaoyi Yang (杨高怡)a,*, Qingguo Ma (马庆国)b,**\u003Cbr>a Affiliated Hangzhou First People’s Hospital, School of Medicine, Westlake University, Hangzhou 310024 Zhejiang Province, China\u003Cbr>b Laboratory of Neuromanagement, Zhejiang University, Hangzhou 310024 Zhejiang Province, China c Sheffield Institute of Translational Neuroscience, University of Sheffield, Sheffield S102TN, United Kingdom d Department of Psychiatry, University of Cambridge, Cambridge CB20SZ, United Kingdom\u003Cbr>e China Jiliang University, Hangzhou 310024 Zhejiang Province, China f Hangzhou Dianzi University, Hangzhou 310024 Zhejiang Province, China\u003Cbr>g Zhejiang Key Laboratory of Multi-Omics in Infection and Immunity, Center for Infectious Disease Research, School of Medicine, Westlake University, Hangzhou 310024 Zhejiang Province, China\u003Cbr>h Westlake University Research Center for Industries of the Future, Westlake University, Hangzhou 310024 Zhejiang Province, China |  |  |\n| --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |\n| Keywords: Machine learning Random Forest\u003Cbr>Healthy-MCI-AD continuum ADNI |  | Introduction: Longitudinal trajectories from healthy aging to Mild Cognitive Impairment and Alzheimer’s Disease involve complex mechanisms.\u003Cbr>Methods: We evaluated five machine learning approaches (Random Forest, Support Vector Machines, Radial Basis Function Networks, Backpropagation Networks, Convolutional Neural Network) to assess the importance of potential predictive markers across the health-to-dementia continuum. Using the ADNI cohort across four phases (ADNI1, ADNIGO, ADNI2, ADNI3), we analyzed participants with distinct trajectories: stable, convertible, and reverse progression.\u003Cbr>Results: Random Forest outperformed other models across key effectiveness metrics and achieved a macroaveraged sensitivity of 70.8 % and specificity of 96.8 % across all participant groups. Random Forest identified visuospatial and memory-related cognitive dysfunction as key predictive clinical features and several amyloid-related neuroimaging biomarkers — including temporal variations of amyloid uptake within inferior lateral ventricles, para-hippocampus—for classifying participant groups. Additionally, plasma APOE4 and long neurofilament light chain levels emerged as promising predictors for tracking progression.\u003Cbr>Conclusion: These findings highlight the potential of machine learning in classifying disease trajectories. |\n\n1. Introduction  \nThe transition from normal cognitive function to mild cognitive impairment (MCI) or Alzheimer’s disease (AD) involves a complex pathological process. Patients with MCI may progress to dementia, remain stable for years, or even revert to normal cognition (Ahlskoget al., 2011; Huey, 2013; Hu et al., 2017). Studies indicates that over 20 % of MCI exhibit a reverse to normal cognition (Malek-Ahmadi, 2016; Makino et al., 2021; Tsujimoto et al., 2022). Thus, the heterogeneity and  \nvariability of MCI and AD present significant challenges for accurate prediction and prevention in patients.  \nThe Alzheimer’s Disease Neuroimaging Initiative (ADNI) is a longitudinal, multi-center study spanning the United States and Canada. The original goal of ADNI was to test whether serial magnetic resonance imaging (MRI), positron emission tomography (PET), other biological markers, and clinical and neuropsychological assessment can be combined to measure the progression of MCI and early AD. Based on the ADNI cohort, a sys","cbCaioknWHOYDLCG","https://ap.wps.com/l/cbCaioknWHOYDLCG","pdf",12741242,1,18,"English","en",105,"# Introduction\n## ADNI overview and disease continuum context\n# Methods\n## Machine-learning approaches and marker evaluation\n# Results\n## Model performance and key predictive features\n# Conclusion","[{\"question\":\"Why is predicting progression along the health-to-dementia continuum challenging?\",\"answer\":\"Normal cognition can shift to MCI or Alzheimer’s through complex pathological processes. MCI and AD show heterogeneity, with patients progressing, remaining stable, or even reverting, making accurate prediction difficult.\"},{\"question\":\"Which machine-learning model performed best and what metrics were reported?\",\"answer\":\"Random Forest outperformed other models across key effectiveness metrics. It achieved a macroaveraged sensitivity of 70.8% and specificity of 96.8% across all participant groups.\"},{\"question\":\"What biomarkers and features helped classify stable, convertible, and reverse trajectories?\",\"answer\":\"Random Forest identified visuospatial and memory-related cognitive dysfunction as key clinical features and several amyloid-related neuroimaging biomarkers. Plasma APOE4 and long neurofilament light chain levels also emerged as promising predictors for tracking progression.\"}]","Converse or reverse? Machine-learning modeling for disease progression - A study based on Alzheimer’s disease continuum cohort | PDF",1785938955,45,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"converse-or-reverse-machine-learning-modeling-for-disease-progression-a-study-based-on-alzheimers-disease-continuum-cohort","",{"@graph":36,"@context":86},[37,54,69],{"@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/converse-or-reverse-machine-learning-modeling-for-disease-progression-a-study-based-on-alzheimers-disease-continuum-cohort/127453/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is predicting progression along the health-to-dementia continuum challenging?","Question",{"text":76,"@type":77},"Normal cognition can shift to MCI or Alzheimer’s through complex pathological processes. MCI and AD show heterogeneity, with patients progressing, remaining stable, or even reverting, making accurate prediction difficult.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"Which machine-learning model performed best and what metrics were reported?",{"text":81,"@type":77},"Random Forest outperformed other models across key effectiveness metrics. It achieved a macroaveraged sensitivity of 70.8% and specificity of 96.8% across all participant groups.",{"name":83,"@type":74,"acceptedAnswer":84},"What biomarkers and features helped classify stable, convertible, and reverse trajectories?",{"text":85,"@type":77},"Random Forest identified visuospatial and memory-related cognitive dysfunction as key clinical features and several amyloid-related neuroimaging biomarkers. Plasma APOE4 and long neurofilament light chain levels also emerged as promising predictors for tracking progression.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]