[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-340439-105":59,"doc-detail-340439-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","improving-platelet-rna-based-diagnostics-a-comparative-analysis-of-machine-learning-models-for-cancer-detection-and-multiclass-classification","Improving platelet-RNA-based diagnostics: a comparative analysis of machine learning models for cancer detection and multiclass classiﬁcation","","Liquid biopsy enables minimally invasive, cost-effective cancer detection and monitoring, but its RNA-based data present significant complexity. This study performs a large-scale comparative evaluation of machine-learning methods for pan-cancer detection and multiclass cancer classification using platelet RNA samples from 1397 cancer patients across 17 cancer types and 354 asymptomatic donors. After dataset quality filtering and transcript feature selection, results indicate simple logistic regression achieves the best performance, with 68% detection at 99% specificity and 79.38% multiclass accuracy.",{"@graph":69,"@context":123},[70,84,106],{"@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/improving-platelet-rna-based-diagnostics-a-comparative-analysis-of-machine-learning-models-for-cancer-detection-and-multiclass-classification/340439/",{"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/improving-platelet-rna-based-diagnostics-a-comparative-analysis-of-machine-learning-models-for-cancer-detection-and-multiclass-classification/340439.png","ImageObject",300,407,{"name":92,"@type":93},"Quinn","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-09-22",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What data did the study use for platelet-RNA-based cancer detection?","Question",{"text":113,"@type":114},"The study used platelet RNA samples from 1397 cancer patients covering 17 cancer types and 354 asymptomatic, presumed healthy donors.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which machine-learning approach performed best in pan-cancer detection?",{"text":118,"@type":114},"Simple logistic regression performed best, reaching a 68% cancer detection rate at a 99% specificity level.",{"name":120,"@type":111,"acceptedAnswer":121},"How accurate was the multiclass classification between cancer types?",{"text":122,"@type":114},"Multiclass classification achieved 79.38% accuracy when distinguishing among five cancer types.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},340439,1790370835,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":105,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":41,"preview_page_count":19,"preview_urls":145},962075114765,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Improving platelet-RNA-based diagnostics: a comparative analysis of machine learning models for cancer detection and multiclass classiﬁcation  \nMaksym _A. Jopek 1,2 , Krzysztof Pastuszak 1,2,3 , Michał Sieczczy ski 1,2, Sebastian Cygert4,5, Anna J. Zaczek 1, Matthew T. Rondina6,7,8,9 and Anna Supernat 1,2   \n1 Laboratory of Translational Oncology, Intercollegiate Faculty of Biotechnology of the University of Gdask and the Medical University of Gdask, Poland  \n2 Centre of Biostatistics and Bioinformatics, Medical University of Gdask, Poland  \n3 Department of Algorithms and Systems Modelling, Faculty of Electronics, Telecommunications and Informatics, Gdask University of Technology, Poland  \n4 Department of Multimedia Systems, Faculty of Electronics, Telecommunications and Informatics, Gdask University of Technology, Poland  \n5 Ideas, NCBR, Warsaw, Poland  \n6 Molecular Medicine Program, University of Utah, Salt Lake City, UT, USA  \n7 George E. Wahlen Veterans Affairs Medical Center Department of Internal Medicine and the Geriatric Research Education and Clinical Center (GRECC), Salt Lake City, UT, USA  \n8 Department of Pathology, University of Utah, Salt Lake City, UT, USA  \n9 Division of General Internal Medicine, Department of Internal Medicine, University of Utah, Salt Lake City, UT, USA  \nKeywords  \ngene expression; liquid biopsy; machine learning; platelets  \nCorrespondence  \nA. Supernat, Laboratory of Translational Oncology, Intercollegiate Faculty of Biotechnology of the University of Gdask and the Medical University of Gdask, Debinki 1, 80-211, Gdask, Poland  \nE-mail: [anna.supernat@gumed.edu.pl](anna.supernat@gumed.edu.pl)  \n(Received 29 December 2023, revised 15 May 2024, accepted 5 June 2024, available online 17 June 2024)  \ndoi:10 . 1002/1878-0261 .13689  \nLiquid biopsy demonstrates excellent potential in patient management by providing a minimally invasive and cost-effective approach to detecting and monitoring cancer, even at its early stages. Due to the complexity of liquid biopsy data, machine-learning techniques are increasingly gaining attention in sample analysis, especially for multidimensional data such as RNA expression proﬁles. Yet, there is no agreement in the community on which methods are the most effective or how to process the data. To circumvent this, we performed a large-scale study using various machine-learning techniques. First, we took a closer look at existing datasets and ﬁltered out some patients to assert data collection quality. The ﬁnal data collection included platelet RNA samples acquired from 1397 cancer patients (17 types of cancer) and 354 asymptomatic, presumed healthy, donors. Then, we assessed an array of different machine-learning models and techniques (e.g., feature selection of RNA transcripts) in pan-cancer detection and multiclass classiﬁcation. Our results show that simple logistic regression performs the best, reaching a 68% cancer detection rate at a 99% speciﬁcity level, and multiclass classiﬁcation accuracy of 79. 38% when distinguishing between ﬁve cancer types. In summary, by revisiting classical machine-learning models, we have exceeded the previously used method by 5% and 9.65% in cancer detection and multiclass  \nAbbreviations  \nAC, asymptomatic controls; AUC, area under curve; BalancedRF, balanced random forest; BRCA, breast cancer; cfDNA, circulating free DNA; cfRNA, circulating free RNA; CHOL, cholangiocarcinoma; CRC, colorectal cancer; CTCs, circulating tumor cells; DL, deep learning; ENDO, endometrial cancer; ESO, esophageal cancer; GLIO, glioma; HCC, hepatocellular carcinoma; HNSCC, head and neck squamous cell carcinoma; LogReg, logistic regression; LYM, lymphoma; MELA, melanoma; ML, machine learning; MM, multiple myeloma; NSCLC, non-small cell lung cancer; OVCAR, ovarian cancer; PDAC, pancreatic ductal adenocarcinoma; PRCA, prostate cancer; PSO-SVM, particleswarm optimized support vector machine; RCC, renal cell carcinoma; RF, random forest; ROC, receiver oper","cbCaisjLNNEtc5Ug","https://ap.wps.com/l/cbCaisjLNNEtc5Ug","pdf",601006,"English","# Introduction\n## Cancer diagnosis challenges\n## Rationale for liquid biopsy and RNA-based biomarkers\n# Methods\n## Dataset collection and quality filtering\n## Machine-learning model comparison and feature selection\n# Results\n## Pan-cancer detection performance\n## Multiclass classification performance\n# Discussion\n## Why classical models outperform prior baselines\n## Open-source code and data pipelines","[{\"question\":\"What data did the study use for platelet-RNA-based cancer detection?\",\"answer\":\"The study used platelet RNA samples from 1397 cancer patients covering 17 cancer types and 354 asymptomatic, presumed healthy donors.\"},{\"question\":\"Which machine-learning approach performed best in pan-cancer detection?\",\"answer\":\"Simple logistic regression performed best, reaching a 68% cancer detection rate at a 99% specificity level.\"},{\"question\":\"How accurate was the multiclass classification between cancer types?\",\"answer\":\"Multiclass classification achieved 79.38% accuracy when distinguishing among five cancer types.\"}]","Improving platelet-RNA-based diagnostics: a comparative analysis of machine learning models for cancer detection and multiclass classiﬁcation | PDF",1790036510,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/fe54a442cb69865cf9da999564321404.webp",983,1291,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/36b0582d0c491917d91663fcc9303047.webp",982,1290,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/28faa470d755db1d8f57bb4ca001779f.webp",981,1289,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/fea24e1a7ea278a35ebf47723ee7e894.webp",980,1287]