[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124072-en":3,"doc-seo-124072-105":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},124072,687197207639,"Asher","https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd",8,"Research & Report","Network-level enrichment provides a framework for biological interpretation of machine learning results","Machine learning algorithms are increasingly used to identify brain connectivity biomarkers related to behavioral and clinical outcomes, yet prediction-focused workflows often sacrifice biological interpretability and can impair reliability when methods are implemented inconsistently. This work proposes a network-level enrichment approach that combines brain system organization with connectome-wide statistical analysis to expose network-level links between connectivity and behavior. Linear support vector regression is used with resting-state functional connectivity networks to test effects of shared family variance handling and feature selection, and compares raw versus forward/inverse derived associations for alignment with significant brain systems.","Washington University School of Medicine  \nDigital Commons@Becker  \n\n| 2020-Current year OA Pubs | Open Access Publications |\n| --- | --- |\n| 10-1-2024\u003Cbr>Network-level enrichment provides a framework for biological interpretation of machine learning results\u003Cbr>Jiaqi Li\u003Cbr>Washington University in St. Louis Ari Segel\u003Cbr>Washington University School of Medicine in St. Louis Xinyang Feng\u003Cbr>Washington University in St. Louis Jiaxin Cindy Tu\u003Cbr>Washington University School of Medicine in St. Louis Andy Eck\u003Cbr>Washington University School of Medicine in St. Louis\u003Cbr>See next page for additional authors\u003Cbr>Follow this and additional works at: [https://digitalcommons.wustl.edu/oa_4](https://digitalcommons.wustl.edu/oa_4)\u003Cbr> Part of the Medicine and Health Sciences Commons\u003Cbr>Please let us know how this document benefits you. |  |\n\nRecommended Citation  \nLi, Jiaqi; Segel, Ari; Feng, Xinyang; Tu, Jiaxin Cindy; Eck, Andy; King, Kelsey T; Adeyemo, Babatunde; Karcher, Nicole R; Chen, Likai; Eggebrecht, Adam T; and Wheelock, Muriah D, \"Network-level enrichment provides a framework for biological interpretation of machine learning results.\" Network Neuroscience. 8, 3. 762-790. (2024) .  \n[https://digitalcommons.wustl.edu/oa_4/4279](https://digitalcommons.wustl.edu/oa_4/4279)  \nThis Open Access Publication is brought to you for free and open access by the Open Access Publications at Digital Commons@Becker. It has been accepted for inclusion in 2020-Current year OA Pubs by an authorized administrator of Digital Commons@Becker. For more information, please [contact vanam@wustl.edu](contact vanam@wustl.edu).  \nAuthors  \nJiaqi Li, Ari Segel, Xinyang Feng, Jiaxin Cindy Tu, Andy Eck, Kelsey T King, Babatunde Adeyemo, Nicole RKarcher, Likai Chen, Adam T Eggebrecht, and Muriah D Wheelock  \nThis open access publication is available at Digital Commons@Becker: [https://digitalcommons.wustl.edu/oa_4/4279](https://digitalcommons.wustl.edu/oa_4/4279)  \n\n|  |  |  |  |  |  |\n| --- | --- | --- | --- | --- | --- |\n|  |  |  |  |  |  |\n| an open access  journal\u003Cbr>\u003Cbr>Citation: Li, J., Segel, A., Feng, X., Tu, J. C., Eck, A., King, K. T., Adeyemo, B., Karcher, N. R., Chen, L., Eggebrecht, A. T., & Wheelock, M. D. (2024). Networklevel enrichment provides a framework for biological interpretation of machine learning results. Network Neuroscience, 8(3), 762–790. [https://doi.org/10.1162](https://doi.org/10.1162)[ ](https://doi.org/10.1162)[/netn_a_00383](/netn_a_00383)\u003Cbr>DOI:\u003Cbr>[https://doi.org/10.1162/netn_a_00383](https://doi.org/10.1162/netn_a_00383)\u003Cbr>Supporting Information:\u003Cbr>[https://doi.org/10.1162/netn_a_00383](https://doi.org/10.1162/netn_a_00383)\u003Cbr>Received: 12 October 2023\u003Cbr>Accepted: 15 May 2024\u003Cbr>Competing Interests: The authors have declared that no competing interests exist.\u003Cbr>Corresponding Author:\u003Cbr>Muriah D. Wheelock\u003Cbr>[mdwheelock@wustl.edu](mdwheelock@wustl.edu)\u003Cbr>Handling Editor: Andrew Zalesky |  |  |  |  |  |\n| Copyright: © 2024\u003Cbr>Massachusetts Institute of Technology Published under a Creative Commons Attribution 4.0 International (CC BY 4.0) license\u003Cbr> The MIT Press |  |  |  |  |  |\n\nMETHODS  \nNetwork-level enrichment provides a framework for biological interpretation of machine learning results  \nJiaqi Li1, Ari Segel2, Xinyang Feng1, Jiaxin Cindy Tu2, Andy Eck2, Kelsey T. King2, Babatunde Adeyemo3, Nicole R. Karcher4, Likai Chen1, Adam T. Eggebrecht2, and Muriah D. Wheelock2  \n1Department of Statistics and Data Science, Washington University in St. Louis, MO, USA 2Mallinckrodt Institute of Radiology, Washington University in St. Louis, MO, USA 3Department of Neurology, Washington University in St. Louis, MO, USA  \n4Department of Psychiatry, Washington University in St. Louis, MO, USA  \nKeywords: Functional connectivity, Machine learning, Twins, Feature selection, Brain networks, HCP  \nABSTRACT  \nMachine learning algorithms are increasingly being utilized to identify brain connectivity biomarkers linked to behavioral and clini","cbCainzt8unWwZHS","https://ap.wps.com/l/cbCainzt8unWwZHS","pdf",2382101,1,31,"English","en",105,"# Methods\n# Keywords\n# Abstract\n# Introduction","[{\"question\":\"What problem does the network-level enrichment approach address?\",\"answer\":\"It addresses the gap between high prediction accuracy and biological interpretability in machine learning studies of brain connectivity, including inconsistencies that can reduce model accuracy.\"},{\"question\":\"How do the authors evaluate the approach in this paper?\",\"answer\":\"They use linear support vector regression to examine relationships between resting-state functional connectivity networks and chronological age, comparing network-level associations from different model weight constructions.\"},{\"question\":\"What do the results show about feature selection and model weighting?\",\"answer\":\"Not accounting for shared family variance inflates performance, k-best feature selection via Pearson correlation reduces accuracy and reliability, and raw LSVR model weights can produce associations that deviate from significant brain systems identified by forward and inverse models.\"}]","Network-level enrichment provides a framework for biological interpretation of machine learning results | PDF",1785820198,78,{"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},"network-level-enrichment-provides-a-framework-for-biological-interpretation-of-machine-learning-results","",{"@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/network-level-enrichment-provides-a-framework-for-biological-interpretation-of-machine-learning-results/124072/",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":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the network-level enrichment approach address?","Question",{"text":75,"@type":76},"It addresses the gap between high prediction accuracy and biological interpretability in machine learning studies of brain connectivity, including inconsistencies that can reduce model accuracy.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the authors evaluate the approach in this paper?",{"text":80,"@type":76},"They use linear support vector regression to examine relationships between resting-state functional connectivity networks and chronological age, comparing network-level associations from different model weight constructions.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the results show about feature selection and model weighting?",{"text":84,"@type":76},"Not accounting for shared family variance inflates performance, k-best feature selection via Pearson correlation reduces accuracy and reliability, and raw LSVR model weights can produce associations that deviate from significant brain systems identified by forward and inverse models.","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"]