[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-458917-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-458917-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","a-machine-learning-model-for-predicting-oligoclonal-band-positivity-using-routine-cerebrospinal-fluid-and-serum-biochemical-markers","A machine learning model for predicting oligoclonal band positivity using routine cerebrospinal fluid and serum biochemical markers","","Objective: develop and validate an ensemble machine learning model to predict oligoclonal band (OCB) positivity using routine cerebrospinal fluid (CSF) and serum biochemical markers, aiming to improve diagnostic accuracy and workflow efficiency for assessing intrathecal immunoglobulin G (IgG) synthesis. Methods: retrospective study (n=1709) with 8 refined CSF/serum parameters; CatBoost, XGBoost, and LightGBM combined in a 2-phase workflow including 5-fold cross-validation plus internal (n=342) and external (n=49) validation. Results: ROC-AUC 0.902 internal vs IgG index 0.795, with accuracy 0.830, sensitivity 0.714, specificity 0.916; external accuracy 90% and sensitivity 96%. Conclusions: the model predicts OCB positivity accurately using routine laboratory data and outperforms the IgG index, supporting AI-enabled laboratory decision support; prospective multicenter validation is needed.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/a-machine-learning-model-for-predicting-oligoclonal-band-positivity-using-routine-cerebrospinal-fluid-and-serum-biochemical-markers/458917/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/a-machine-learning-model-for-predicting-oligoclonal-band-positivity-using-routine-cerebrospinal-fluid-and-serum-biochemical-markers/458917.png","ImageObject",300,407,{"name":42,"@type":43},"Mafia Boss","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-31","2026-09-30",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",7,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"What is the main objective of the study?","Question",{"text":63,"@type":64},"To develop and validate a machine learning model that predicts oligoclonal band (OCB) positivity using routine CSF and serum biochemical markers, improving diagnostic accuracy and efficiency for intrathecal IgG synthesis assessment.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"How was the machine learning model developed and evaluated?",{"text":68,"@type":64},"An ensemble model was built from 8 refined CSF and serum parameters and combines CatBoost, XGBoost, and LightGBM. It was evaluated using 5-fold cross-validation plus internal (n=342) and external (n=49) validation cohorts.",{"name":70,"@type":61,"acceptedAnswer":71},"How does the model perform compared with the conventional IgG index?",{"text":72,"@type":64},"On the internal test set, the ensemble achieved ROC-AUC 0.902 versus 0.795 for the conventional IgG index. At the optimal threshold it showed accuracy 0.830 with sensitivity 0.714 and specificity 0.916, and the external cohort reached 90% accuracy with 96% sensitivity.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},458917,1790945439,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,109,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":107,"slug":108},40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":25,"category_name":111,"show_sort_weight":112,"slug":113},8,"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":97,"slug":129},19,"General","general",{"code":4,"msg":82,"data":131},{"doc_id":79,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":55,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":139,"language":140,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":12,"update_tm":144,"read_time":145,"preview_page_count":4},962090760730,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","A machine learning model for predicting oligoclonal band positivity using routine cerebrospinal fluid and serum biochemical markers  \nHazar Gözgöz, MD 1, , Oğuzhan Orhan, BSc2, , Başak Akan Konuk, MSc3, , PınarAkan, MD 1, *,   \n1Faculty of Medicine, Department of Clinical Biochemistry, Dokuz Eylul University, Izmir, Turkey; 2Engineering Faculty, Computer Engineering, Izmir Institute of Technology, Izmir, Turkey; 3Computation, Information and Technology (CIT), Technical University of Munich, Munich, Germany  \nabstract  \nObjective: To develop and validate a machine learning model for predicting oligoclonal band (OCB) positivity using routine cerebrospinal fluid (CSF) and serum biochemical markers to improve the diagnostic accuracy and efficiency of assessing intrathecal immunoglobulin G (IgG) synthesis.  \nMethods: In this retrospective study (n = 1709), an ensemble model was developed using 8 refined CSF and serum parameters. Combining optimized CatBoost, XGBoost, and LightGBMclassifiers, the model was trained and evaluated using a 2-phase workflow, including 5-fold cross-validation and validation on independent internal (n = 342) and external (n = 49) cohorts.  \nResults: The developed ensemble model achieved a receiver operating characteristic– area under the curve (ROC-AUC) of 0.902 on the internal test set, significantly outperforming the conventional IgG index (ROC-AUC, 0.795). At its optimal threshold, the model demonstrated an accuracy of 0.830, with a sensitivity of 0.714 and a specificity of 0.916. On the external validation cohort, it achieved 90% accuracy and 96% sensitivity.  \nConclusions: A novel machine learning ensemble model accurately predicts OCBpositivity using routine laboratory data and demonstrates superior performance compared with the IgG index. This approach represents a significant step in applying artificial intelligence in laboratory medicine, with the potential to enhance diagnostic efficiency. Prospective, multicenter validation is essential for broader clinical implementation.  \nintrODUctiOn  \nCerebrospinal fluid (CSF) analysis is a cornerstone in the diagnosis of neurologic diseases, providing critical insights into the pathologic processes of the central nervous system (CNS).1 A key finding from this analysis is the presence of 2 or more CSF-restricted oligoclonal bands (OCBs), which indicates intrathecal immunoglobulin G (IgG) synthesis and is considered the most sensitive and reliable laboratory marker for multiple sclerosis (MS),2 a chronic autoimmune disease characterized by demyelination and axonal injury and the most common nontraumatic cause of neurologic disability in young adults.3,4 Analysis of CSF remains vital for  \n© The Author(s) 2025. This is an Open Access article distributed under the terms of the Creative Commons Attribution License ([https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)), which permits unrestricted reuse, distribution, and reproduction in any medium, provided the original work is properly cited.  \n|  \nOriginal article  \nKeY POintS  \n• This study addresses the need fora more objective tool to supplement oligoclonal band (OCB) analysis in cerebrospinal fluid.  \n• A novel machine learning model using routine laboratory data accurately predicts OCB positivity, outperforming the conventional immunoglobulin G index.  \n• This model can serve as a decision support tool to enhance diagnostic efficiency and workflow in clinical laboratories.  \nKey words  \noligoclonal bands; cerebrospinal fluid; machine learning; multiple sclerosis; diagnostic prediction model  \nAm J Clin Pathol December 2025;  \n164:933-945  \ndoi:10.1093/ajcp/aqaf119  \nReceived: August 13, 2025.  \nAccepted: September 25, 2025  \n*Corresponding author: Pınar Akan ([pinar.akan@deu.edu.tr](pinar.akan@deu.edu.tr))  \nAm J Clin Pathol 2025;164:933-945 933  \ndoi:10.1093/ajcp/aqaf119  \n | American Journal of Clinical Pathology, 2025, Vol. 164, No. 6  \nMS diagnosis, especially i","cbCaipPc0ssAxEdu","https://ap.wps.com/l/cbCaipPc0ssAxEdu","pdf",2452484,14,"English","# Objective\n# Methods\n# Results\n# Conclusions\n# Introduction\n## Current diagnostic approaches and limitations\n## Need for novel analytical tools","[{\"question\":\"What is the main objective of the study?\",\"answer\":\"To develop and validate a machine learning model that predicts oligoclonal band (OCB) positivity using routine CSF and serum biochemical markers, improving diagnostic accuracy and efficiency for intrathecal IgG synthesis assessment.\"},{\"question\":\"How was the machine learning model developed and evaluated?\",\"answer\":\"An ensemble model was built from 8 refined CSF and serum parameters and combines CatBoost, XGBoost, and LightGBM. It was evaluated using 5-fold cross-validation plus internal (n=342) and external (n=49) validation cohorts.\"},{\"question\":\"How does the model perform compared with the conventional IgG index?\",\"answer\":\"On the internal test set, the ensemble achieved ROC-AUC 0.902 versus 0.795 for the conventional IgG index. At the optimal threshold it showed accuracy 0.830 with sensitivity 0.714 and specificity 0.916, and the external cohort reached 90% accuracy with 96% sensitivity.\"}]","A machine learning model for predicting oligoclonal band positivity using routine cerebrospinal fluid and serum biochemical markers | PDF",1790754756,35]