[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-329589-105":59,"doc-detail-329589-en":134},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","metabolomics-based-machine-learning-models-accurately-predict-breast-cancer-estrogen-receptor-status","Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status","","Breast cancer remains a global cause of death, and early, accurate diagnosis is essential for effective management. Estrogen receptor (ER) status underpins prognosis and treatment selection, so this work develops a non-invasive approach using metabolomics from plasma to find metabolite biomarkers that differentiate ER-positive from ER-negative disease. A dataset covers 188 breast cancer patients and 73 healthy controls. Recursive Feature Elimination with Random Forest selects 30 features (including 29 biomarkers and age) for best AUC, while Gaussian-noise augmentation and ADASYN address class imbalance. Random Forest is the top model with AUC 0.95 and 93% accuracy. Results indicate ML can identify metabolites linked to ER expression, supporting improved breast cancer subtyping and a potential analytical tool to reduce current ER-status identification challenges.",{"@graph":69,"@context":126},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/metabolomics-based-machine-learning-models-accurately-predict-breast-cancer-estrogen-receptor-status/329589/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/metabolomics-based-machine-learning-models-accurately-predict-breast-cancer-estrogen-receptor-status/329589.png","ImageObject",300,407,{"name":92,"@type":93},"Clementine","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-23","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"What is the study’s goal regarding breast cancer ER status?","Question",{"text":112,"@type":113},"To use plasma metabolomics data and machine learning to identify metabolite biomarkers that distinguish ER-positive from ER-negative breast cancer in a non-invasive way.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How were features selected and what subset was chosen?",{"text":117,"@type":113},"Recursive Feature Elimination (RFE) with a Random Forest classifier selected an optimal subset of 30 features, including 29 biomarkers and age.",{"name":119,"@type":110,"acceptedAnswer":120},"How did the study handle class imbalance during model training?",{"text":121,"@type":113},"Gaussian noise-based augmentation and Adaptive Synthetic Oversampling (ADASYN) were applied to ensure balanced representation.",{"name":123,"@type":110,"acceptedAnswer":124},"Which machine learning algorithm performed best and what results were achieved?",{"text":125,"@type":113},"Random Forest performed best, reaching an AUC of 0.95 and 93% accuracy based on grid search evaluation.","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},329589,1790196732,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":143,"language":144,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":145,"faqs":146,"seo_title":147,"seo_description":67,"update_tm":148,"read_time":149,"preview_page_count":4},1374391974564,"https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002","Article  \nMetabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status  \nKamala K. Arumalla 1, Jean-François Haince 2, Rashid A. Bux 3, Guoyu Huang 2,3, Paramjit S. Tappia 4, Bram Ramjiawan 4,5, W. Randolph Ford 1 and Maria Vaida 1, *  \nCitation: Arumalla, K.K.; Haince, J.-F.; Bux, R.A.; Huang, G.; Tappia, P.S.; Ramjiawan, B.; Ford, W.R.; Vaida, M. Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status. Int. J. Mol. Sci. 2024, 25, 13029 . [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)ijms252313029  \nAcademic Editors: Hung-Yu Lin and Pei-Yi Chu  \nReceived: 19 October 2024  \nRevised: 27 November 2024  \nAccepted: 29 November 2024  \nPublished: 4 December 2024  \nCopyright: © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) .  \n1 Department of Analytics, Harrisburg University of Science and Technology, Harrisburg, PA 17101, USA; [karumalla@alumni.harrisburgu.edu](karumalla@alumni.harrisburgu.edu) (K.K.A.); [marriotts2010@gmail.com](marriotts2010@gmail.com) (W.R.F.)  \n2 BioMark Diagnostic Solutions Inc., Quebec, QC G1K 3G5, Canada; [jhaince@biomarkdiagnostics.com](jhaince@biomarkdiagnostics.com) (J.-F.H.); [ghuang@biomarkdiagnostics.com](ghuang@biomarkdiagnostics.com) (G.H.)  \n3 BioMark Diagnostics Inc., Richmond, BC V6X 2W2, Canada; [rahmed@biomarkdiagnostics.com](rahmed@biomarkdiagnostics.com)  \n[4](4 Asper Clinical Research Institute)[ Asper Clinical Research Institute](4 Asper Clinical Research Institute), [Winnipeg](Winnipeg), [MB R2H2A6](MB R2H2A6), [Canada](Canada); [ptappia@sbrc.ca](ptappia@sbrc.ca) ([P.S.T](P.S.T).); [bramjiawan@sbrc.ca](bramjiawan@sbrc.ca) (B.R.)  \n5 Department of Pharmacology & Therapeutics, Max Rady College of Medicine, University of Manitoba, Winnipeg, MB R3E 0T6, Canada  \n* [Correspondence: mvaida@harrisburgu.edu](Correspondence: mvaida@harrisburgu.edu)  \nAbstract: Breast cancer is a global concern as a leading cause of death for women. Early and precise diagnosis can be vital in handling the disease efficiently. Breast cancer subtyping based on estrogen receptor (ER) status is crucial for determining prognosis and treatment. This study uses metabolomics data from plasma samples to detect metabolite biomarkers that could distinguish ERpositive from ER-negative breast cancers in a non-invasive manner. The dataset includes demographic information, ER status, and metabolite levels from 188 breast cancer patients and 73 healthy controls. Recursive Feature Elimination (RFE) with a Random Forest (RF) classifier identified an optimal subset of 30 features—29 biomarkers and age—that achieved the highest area under the curve (AUC) . To address the class imbalance, Gaussian noise-based augmentation and Adaptive Synthetic Oversampling (ADASYN) were applied, ensuring balanced representation during training. Four machine learning (ML) algorithms—Random Forest, Support Vector Classifier (SVC), XGBoost, and Logistic Regression (LR)—were evaluated using grid search. The Random Forest classifier emerged as the top performer, achieving an AUC of 0.95 and an accuracy of 93% . These results suggest that ML has great promise for identifying specific metabolites linked to ER expression, paving the development of a novel analytical tool that can minimize current challenges in identifying ER status, and improve the precision of breast cancer subtyping.  \nKeywords: estrogen receptors; breast cancer; metabolomics; machine learning models  \n1. Introduction  \nEvery breast cancer subtype can be characterized by histological and molecular features, and their intrinsic heterogeneity leads to an array of clinical presentations ","cbCaiep1VLBfCknF","https://ap.wps.com/l/cbCaiep1VLBfCknF","pdf",2286380,14,"English","# Introduction\n## Breast cancer subtypes and receptor-based classification\n## Importance of estrogen receptor status in prognosis and therapy","[{\"question\":\"What is the study’s goal regarding breast cancer ER status?\",\"answer\":\"To use plasma metabolomics data and machine learning to identify metabolite biomarkers that distinguish ER-positive from ER-negative breast cancer in a non-invasive way.\"},{\"question\":\"How were features selected and what subset was chosen?\",\"answer\":\"Recursive Feature Elimination (RFE) with a Random Forest classifier selected an optimal subset of 30 features, including 29 biomarkers and age.\"},{\"question\":\"How did the study handle class imbalance during model training?\",\"answer\":\"Gaussian noise-based augmentation and Adaptive Synthetic Oversampling (ADASYN) were applied to ensure balanced representation.\"},{\"question\":\"Which machine learning algorithm performed best and what results were achieved?\",\"answer\":\"Random Forest performed best, reaching an AUC of 0.95 and 93% accuracy based on grid search evaluation.\"}]","Metabolomics-Based Machine Learning Models Accurately Predict Breast Cancer Estrogen Receptor Status | PDF",1789984674,35]