[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120975-en":3,"doc-seo-120975-105":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},120975,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Dimensional Neuroimaging Endophenotypes - Neurobiological Representations of Disease Heterogeneity Through Machine Learning","Machine learning is increasingly leveraged to extract individualized neuroimaging signatures that support disease diagnosis, prognosis, and treatment response across neuropsychiatric and neurodegenerative disorders. By distinguishing disease subtypes with distinct brain phenotypic patterns, it advances understanding of disease heterogeneity. This review surveys multimodal MRI studies, consolidates key machine learning methodologies, and introduces dimensional neuroimaging endophenotype (DNE) as a low-dimensional quantitative intermediate phenotype reflecting underlying genetics and etiology. Clinical and future research implications are discussed.","Dimensional Neuroimaging Endophenotypes: Neurobiological Representations of Disease Heterogeneity  \nThrough Machine Learning  \nJunhao Wen 1*, Mathilde Antoniades2, Zhijian Yang2, Gyujoon Hwang3, Ioanna Skampardoni2,  \nRongguang Wang2, Christos Davatzikos2,*  \n1Laboratory of AI and Biomedical Science (LABS), Stevens Neuroimaging and Informatics Institute, Keck School of Medicine of USC, University of Southern California, Los Angeles, CA, USA 2Artificial Intelligence in Biomedical Imaging Laboratory (AIBIL), Center for AI and Data Science for Integrated Diagnostics (AI2D), Perelman School of Medicine, University of Pennsylvania, Philadelphia, PA, USA  \n3Psychiatry and Behavioral Medicine, Medical College of Wisconsin, Watertown Plank Rd, Milwaukee, WI, USA  \n*Corresponding authors:  \nJunhao Wen, Ph.D.–[junhaowe@usc.edu](junhaowe@usc.edu)  \n2025 Zonal Ave, Los Angeles, CA 90033, United States  \nChristos Davatzikos, [Ph.D. -](Ph.D. -christos.davatzikos@pennmedicine.upenn.edu)[christos.davatzikos@pennmedicine.upenn.edu](Ph.D. -christos.davatzikos@pennmedicine.upenn.edu)[ ](Ph.D. -christos.davatzikos@pennmedicine.upenn.edu)3700 Hamilton Walk, 7th Floor, Philadelphia, PA 19104, USA  \nAbstract  \nMachine learning has been increasingly used to obtain individualized neuroimaging signatures for disease diagnosis, prognosis, and response to treatment in neuropsychiatric and neurodegenerative disorders. Therefore, it has contributed to a better understanding of disease heterogeneity by identifying disease subtypes that present significant differences in various brain phenotypic measures. In this review, we first present a systematic literature overview of studies using machine learning and multimodal MRI to unravel disease heterogeneity in various neuropsychiatric and neurodegenerative disorders, including Alzheimer’s disease, schizophrenia, major depressive disorder, autism spectrum disorder, multiple sclerosis, as well as their potential in transdiagnostic settings. Subsequently, we summarize relevant machine learning methodologies and discuss an emerging paradigm which we call dimensional neuroimaging endophenotype (DNE) . DNE dissects the neurobiological heterogeneity of neuropsychiatric and neurodegenerative disorders into a low-dimensional yet informative, quantitative brain phenotypic representation, serving as a robust intermediate phenotype (i.e., endophenotype) largely reflecting underlying genetics and etiology. Finally, we discuss the potential clinical implications of the current findings and envision future research avenues.  \nKeywords: Disese heterogeneity, Machine learning, Neurodegenerative disease, Neuropsychiatric disorder  \n1. Main  \nOver the past two decades, magnetic resonance imaging (MRI) and machine learning have emerged as foundational tools and techniques for studying human brain aging and disease1. Researchers have proposed an array of individual-level imaging signatures2–10,10–12 to quantify disease and aging effects using state-of-the-art machine learning techniques. However, disease heterogeneity poses a major obstacle to their potential clinical implementation. Disease heterogeneity can manifest in various aspects such as neuroanatomy and function 13–16, clinical symptoms 17, and genetics 18. Critically, case-control studies largely overlooked such heterogeneity, leading to limited applicability due to the inability to capture diverse, multifaceted underlying biological processes that collectively give rise to the ultimate manifestation of clinical symptoms. Furthermore, it is anticipated that the heterogeneity in the underlying etiology and clinical manifestations thereof will also give rise to variability in response to experimental pharmacotherapeutics 19. Therefore, the effectiveness of the drugs developed and tested in the ‘1-for-all’ unitary group of patients, such as Alzheimer's disease (AD), may be hindered since the study population may represent a mixture of multiple pathological processes.  \nThe re","cbCaiimTKtNbXxqz","https://ap.wps.com/l/cbCaiimTKtNbXxqz","pdf",1528002,1,35,"English","en",105,"# Background and Motivation\n## Imaging signatures and case-control limitations\n## Disease heterogeneity and variable drug response\n# Machine Learning Approaches to Disease Subtyping\n## Clustering methods and fixed-resolution “subtypes”\n## Limitations of singular patterns and static thresholds\n# Dimensional Neuroimaging Endophenotype (DNE) Framework\n## Concept and role as an intermediate phenotype\n## Bridging genetics and clinical symptoms\n## Co-expression of multiple imaging patterns\n# Systematic Review Scope and Objectives\n## Bibliometric search across multiple disorders\n# Implications and Future Directions","[{\"question\":\"Why does disease heterogeneity hinder clinical adoption of imaging signatures?\",\"answer\":\"Disease heterogeneity affects neuroanatomy/function, symptoms, and genetics, and case-control designs often miss these diverse biological processes. As a result, models and therapies trained on “unitary” groups may underperform when multiple underlying pathological processes co-occur.\"},{\"question\":\"How do clustering-based approaches to brain MRI subtypes fall short?\",\"answer\":\"Clustering defines subtypes using fixed thresholds that may ignore how disease manifestations evolve along a spectrum. It also assumes singular imaging patterns per patient, potentially overlooking multiple presentations or longitudinal changes.\"},{\"question\":\"What is dimensional neuroimaging endophenotype (DNE) and what is its purpose?\",\"answer\":\"DNE models neurobiological heterogeneity as a low-dimensional, quantitative representation that acts as a robust intermediate phenotype. It supports co-expression of multiple imaging patterns in the same patient, bridging underlying genetics and eventual clinical symptoms.\"}]","Dimensional Neuroimaging Endophenotypes - Neurobiological Representations of Disease Heterogeneity Through Machine Learning | PDF",1785733145,88,{"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},"dimensional-neuroimaging-endophenotypes-neurobiological-representations-of-disease-heterogeneity-through-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/dimensional-neuroimaging-endophenotypes-neurobiological-representations-of-disease-heterogeneity-through-machine-learning/120975/",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},"Why does disease heterogeneity hinder clinical adoption of imaging signatures?","Question",{"text":75,"@type":76},"Disease heterogeneity affects neuroanatomy/function, symptoms, and genetics, and case-control designs often miss these diverse biological processes. As a result, models and therapies trained on “unitary” groups may underperform when multiple underlying pathological processes co-occur.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do clustering-based approaches to brain MRI subtypes fall short?",{"text":80,"@type":76},"Clustering defines subtypes using fixed thresholds that may ignore how disease manifestations evolve along a spectrum. It also assumes singular imaging patterns per patient, potentially overlooking multiple presentations or longitudinal changes.",{"name":82,"@type":73,"acceptedAnswer":83},"What is dimensional neuroimaging endophenotype (DNE) and what is its purpose?",{"text":84,"@type":76},"DNE models neurobiological heterogeneity as a low-dimensional, quantitative representation that acts as a robust intermediate phenotype. It supports co-expression of multiple imaging patterns in the same patient, bridging underlying genetics and eventual clinical symptoms.","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"]