[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128408-en":3,"doc-seo-128408-105":31,"detail-sidebar-cat-0-en-105":96},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128408,8796095027276,"Valentina","https://avatar.qwps.com/avatar/d3BzX2FwX3Rlc3RfMjUxMTI2XzAxODA=",8,"Research & Report","Explainable machine learning on weighted connectivity networks across frequencies for outcome prediction in comatose patients","Accurate early prediction of neurological outcomes in comatose patients after cardiac arrest is essential for guiding therapeutic decisions and individualized care. This work introduces an explainable machine learning framework using weighted EEG functional connectivity and multi-frequency topological network features computed from 1–40 Hz dwPLI. Interpretable models are built with SHAP to identify key predictors distinguishing favorable vs unfavorable long-term outcomes, highlighting delta-band topology differences. Results reach up to 95% accuracy, with limitations including moderate cohort size and expert-guided artifact rejection.","medRxiv preprint doi: [https://doi.org/10.1101/2025.11.21.25340725](https://doi.org/10.1101/2025.11.21.25340725); this version posted November 23, 2025. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity.  \nIt is made available under a CC-BY-NC-ND 4.0 International license .  \nExplainable machine learning on weighted connectivity networks across frequencies for outcome prediction in comatose patients  \nArthur Verdeyme 1 , Jake P. Grainger 1 , Marzia De Lucia2 ,3 Y, Sofia C. Olhede 1 Y,  \n1 Institute of Mathematics, Ecole Polytechnique F´ed´erale de Lausanne, Lausanne, Switzerland.  \n2 Brain-Body and Consciousness Laboratory, Department of Clinical Neuroscience, Lausanne University Hospital, University of Lausanne, Lausanne 1011,Switzerland  \n3 Center for Biomedical Imaging, Lausanne 1011, Switzerland  \nYThese authors contributed equally to this work.  \n‡These authors also contributed equally to this work.  \n¤Current Address: Dept/Program/Center, Institution Name, City, State, Country †Deceased  \n¶Membership list can be found in the Acknowledgments section.  \n* [correspondingauthor@institute.edu](correspondingauthor@institute.edu)  \nAbstract  \nBackground: Accurate early prediction of neurological outcomes in comatose patients after cardiac arrest is critical for guiding therapeutic decisions and improving individualized care. Current electroencephalographic (EEG) approaches typically rely on threshold-based or binarized measures of functional connectivity, which may overlook key subtleties of brain dynamics and limit clinical interpretability. We aimed to develop an explainable machine learning framework using weighted EEG connectivity and topological network features to improve early outcome prediction after cardiac arrest.  \nMethods and Findings: We analyzed EEG recordings from comatose patients within the first 24 hours after cardiac arrest, recruited from multiple intensive care units across Switzerland. Weighted functional connectivity networks were computed using the debiased weighted phase-lag index (dwPLI) across 1–40 Hz. We extracted  \nmulti-frequency topological metrics describing global integration and local segregation, and used these as features in an explainable machine learning classifier to predict long-term neurological outcome. Model interpretation was performed using Shapley additive explanations (SHAP) . The classifier achieved up to 95% accuracy in distinguishing patients with favourable versus unfavourable outcomes, matching or surpassing existing approaches. SHAP analyses identified delta-band features, particularly path length and clustering coefficient, as the most informative predictors, highlighting differences in large-scale integration and local segregation between outcome groups. Main limitations include the moderate cohort size and the dependency on expert-guided artefact rejection during EEG preprocessing.  \nConclusions: Our findings demonstrate that weighted network topology and multifrequency EEG analysis provide valuable, interpretable biomarkers of coma outcome. The proposed explainable AI framework offers a transparent, quantitative, and clinically meaningful approach for early neurological prognostication after cardiac arrest and may inform the design of future decision-support tools in critical care neurology.  \nNovember 20, 2025 1/23  \nNOTE: This preprint reports new research that has not been certified by peer review and should not be used to guide clinical practice.  \nmedRxiv preprint doi: [https://doi.org/10.1101/2025.11.21.25340725](https://doi.org/10.1101/2025.11.21.25340725); this version posted November 23, 2025. The copyright holder for this preprint (which was not certified by peer review) is the author/funder, who has granted medRxiv a license to display the preprint in perpetuity.  \nIt is made available under a CC-BY-NC-ND 4.0 International license .  \nAuth","cbCainjQunLcMyiW","https://ap.wps.com/l/cbCainjQunLcMyiW","pdf",14227507,2,1,27,"English","en",105,"# Abstract\n## Background\n## Methods and Findings\n## Conclusions\n# Author summary\n# Introduction","[{\"question\":\"What problem does this study address in comatose patients after cardiac arrest?\",\"answer\":\"It targets early, accurate prediction of long-term neurological outcomes to support therapeutic decisions and individualized care.\"},{\"question\":\"How are EEG connectivity features computed and used for prediction?\",\"answer\":\"Weighted functional connectivity networks are computed using dwPLI across 1–40 Hz, and multi-frequency topological metrics are extracted as classifier features.\"},{\"question\":\"How does the study explain what drives the model predictions?\",\"answer\":\"It uses Shapley additive explanations (SHAP) to quantify which frequency-band features most influence each patient’s predicted outcome.\"},{\"question\":\"What are the main limitations reported by the authors?\",\"answer\":\"The cohort size is moderate, and EEG preprocessing depends on expert-guided artifact rejection.\"}]","Explainable machine learning on weighted connectivity networks across frequencies for outcome prediction in comatose patients | PDF",1785947348,68,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":91,"head_meta":93,"extra_data":95,"updated_unix":29},"explainable-machine-learning-on-weighted-connectivity-networks-across-frequencies-for-outcome-prediction-in-comatose-patients","",{"@graph":37,"@context":90},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/explainable-machine-learning-on-weighted-connectivity-networks-across-frequencies-for-outcome-prediction-in-comatose-patients/128408/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-27","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82,86],{"name":73,"@type":74,"acceptedAnswer":75},"What problem does this study address in comatose patients after cardiac arrest?","Question",{"text":76,"@type":77},"It targets early, accurate prediction of long-term neurological outcomes to support therapeutic decisions and individualized care.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How are EEG connectivity features computed and used for prediction?",{"text":81,"@type":77},"Weighted functional connectivity networks are computed using dwPLI across 1–40 Hz, and multi-frequency topological metrics are extracted as classifier features.",{"name":83,"@type":74,"acceptedAnswer":84},"How does the study explain what drives the model predictions?",{"text":85,"@type":77},"It uses Shapley additive explanations (SHAP) to quantify which frequency-band features most influence each patient’s predicted outcome.",{"name":87,"@type":74,"acceptedAnswer":88},"What are the main limitations reported by the authors?",{"text":89,"@type":77},"The cohort size is moderate, and EEG preprocessing depends on expert-guided artifact rejection.","https://schema.org",{"og:url":52,"og:type":92,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":94,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":97},[98,102,106,110,115,120,125,128,133,136,140],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":107,"show_sort_weight":108,"slug":109},"Exam",70,"exam",{"id":111,"doc_module":4,"doc_module_name":47,"category_name":112,"show_sort_weight":113,"slug":114},5,"Comic",60,"comic",{"id":116,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},6,"Technology",50,"technology",{"id":121,"doc_module":4,"doc_module_name":47,"category_name":122,"show_sort_weight":123,"slug":124},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":126,"slug":127},30,"research-report",{"id":129,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":131,"slug":132},9,"Religion & Spirituality",20,"religion-spirituality",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":131,"slug":135},"World Cup","world-cup",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":137,"slug":139},10,"Lifestyle","lifestyle",{"id":141,"doc_module":4,"doc_module_name":47,"category_name":142,"show_sort_weight":111,"slug":143},19,"General","general"]