[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124389-en":3,"doc-seo-124389-105":29,"detail-sidebar-cat-0-en-105":90},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},124389,1374391974564,"Clementine","https://ap-avatar.wpscdn.com/avatar/14000253aa45c000a9e?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779874745381141002",8,"Research & Report","Advances in machine learning for tumour classification in cancer of unknown primary: A mini-review","Cancers of unknown primary (CUP) represent a heterogeneous group of aggressive metastatic cancers in which standard diagnostic workflows cannot determine the organ of origin, leading to poor prognosis and reduced responsiveness to treatment. Large-scale sequencing now enables tumour-specific mutational signatures, including from liquid biopsy samples such as blood, supporting more affordable diagnostic options. This mini-review surveys recent advances in machine learning for CUP tumour classification, weighing strengths and weaknesses and outlining challenges for multiomics integration. It emphasizes how higher-dimensional data can reduce predictive accuracy and robustness when sample size is limited, and discusses strategies that bridge theory with clinical practice.","Cancer Letters 611 (2025) 217348  \nContents lists available at ScienceDirect  \nCancer Letters  \njournal [homepage: www.elsevier.com/locate/canlet](homepage: www.elsevier.com/locate/canlet)  \n| Advances in machine learning for tumour classification in cancer of unknown primary: A mini-review |  |  |  |\n| --- | --- | --- | --- |\n| Karen Or´osticaa,**, Felipe Mardonesa, Yanara A. Bernalb, Samuel Molina c, Marcos Orchard c, Ricardo A. Verdugo a,d, Daniel Carvajal-Hausdorfe, Katherine Marcelaind,f, Seba Contreras g,*, Ricardo Armisenb,***\u003Cbr>a Facultad de Medicina, Universidad de Talca, Talca, Chile\u003Cbr>b Centro de Gen´etica y Gen´omica, Instituto de Ciencias e Innovaci´on en Medicina, Facultad de Medicina Clínica Alemana Universidad del Desarrollo, Santiago, Chile c Department of Electrical Engineering, Faculty of Physical and Mathematical Sciences, University of Chile, Av. Tupper 2007, Casilla 412-3, Santiago, 8370451, Chile d Departamento de Oncología B´asico Clínica, Facultad de Medicina, Universidad de Chile, Santiago, Chile\u003Cbr>e Anatomia Patol´ogica, Clinica Alemana, Facultad de Medicina Universidad del Desarrollo, Santiago, Chile\u003Cbr>f Centro Para La Prevenci´on y el Control del Ca´ncer, Universidad de Chile, Santiago, Chile g Max Planck Institute for Dynamics and Self-Organization, G¨ottingen, Germany |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Cancers of unknown primary (CUP) Machine learning (ML)\u003Cbr>Mutational signatures Somatic mutations Diagnostic methods Tumour classification |  | Cancers of unknown primary (CUP) are a heterogeneous group of aggressive metastatic cancers where standardised diagnostic techniques fail to identify the organ where it originated, resulting in a poor prognosis and resistance to treatment. Recent advances in large-scale sequencing techniques have enabled the identification of mutational signatures specific to particular tumour subtypes, even from liquid biopsy samples such as blood. This breakthrough paves the way for the development of new cost-effective diagnostic strategies. This mini-review explores recent advancements in Machine Learning (ML) and its application to tumour classification methods for CUP patients, identifying its weaknesses and strengths when classifying the tumour type. In the era of multiomics, integrating several sources of information (e.g., imaging, molecular biomarkers, and family history) requires important theoretical advancements: increasing the dimensionality of the problem can result in lowering the predictive accuracy and robustness when data is scarce. Here, we review and discuss different architecturesand strategies for incorporating cutting-edge machine learning into CUP diagnosis, aiming to bridge the gap between theory and clinical practice. |  |\n\n1. Background  \nCancer is a complex group of diseases characterised by abnormal and uncontrolled cell growth with the potential to invade other organs and systems. It arises from the combined effects of multiple genomic and epigenetic factors and is, to date, the second cause of death worldwide, with more than 8 million deaths per year [1]. The leading cause of death in cancer patients with solid tumours, metastasis, begins when circulating cancer cells start to colonise distant organs and compromise their function [2,3]. Knowing where metastasis originated (i.e., its primary origin) substantially increases the chances of survival, as practitioners have specialised therapeutic alternatives to treat each type of cancer.  \nHowever, identifying the source is technologically and economically challenging.  \nCancers of unknown primary (CUP) are those metastatic cancers where the metastasis’s origin is unclear. These cancers are characterised by an aggressive course of the disease and a resistance to conventional chemotherapy, resulting in a poor prognosis for the patients [4]. CUP comprises a heterogeneous group of aggressive metastatic tumours with distinct clinicopathological features wh","cbCaieeIusVozDZh","https://ap.wps.com/l/cbCaieeIusVozDZh","pdf",2545401,1,"English","en",105,"# Background\n## Cancer biology and mortality context\n## Cancers of unknown primary (CUP): definition, features, and challenges\n## Impact of resource limitations and need for new diagnostic approaches\n# Machine learning and multiomics direction\n## Sequencing, mutational signatures, and liquid biopsy opportunities\n## ML architectures and strategies for CUP diagnosis","[{\"question\":\"What makes cancers of unknown primary (CUP) clinically challenging?\",\"answer\":\"CUP involves metastatic cancers whose primary origin cannot be identified using standardized diagnostic techniques. This leads to an aggressive disease course, resistance to conventional chemotherapy, and a poor prognosis.\"},{\"question\":\"How can large-scale sequencing improve diagnosis in CUP?\",\"answer\":\"Large-scale sequencing enables detection of mutational signatures linked to specific tumour subtypes. These signals can be obtained even from liquid biopsy materials such as blood, enabling new cost-effective diagnostic strategies.\"},{\"question\":\"Why does multiomics integration pose difficulties for machine learning in CUP?\",\"answer\":\"Integrating multiple information sources (e.g., imaging, molecular biomarkers, family history) increases the dimensionality of the prediction problem. When data are scarce, this can lower predictive accuracy and robustness, requiring theoretical advances and careful model design.\"}]","Advances in machine learning for tumour classification in cancer of unknown primary: A mini-review | PDF",1785821946,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"advances-in-machine-learning-for-tumour-classification-in-cancer-of-unknown-primary-a-mini-review","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/advances-in-machine-learning-for-tumour-classification-in-cancer-of-unknown-primary-a-mini-review/124389/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What makes cancers of unknown primary (CUP) clinically challenging?","Question",{"text":74,"@type":75},"CUP involves metastatic cancers whose primary origin cannot be identified using standardized diagnostic techniques. This leads to an aggressive disease course, resistance to conventional chemotherapy, and a poor prognosis.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"How can large-scale sequencing improve diagnosis in CUP?",{"text":79,"@type":75},"Large-scale sequencing enables detection of mutational signatures linked to specific tumour subtypes. These signals can be obtained even from liquid biopsy materials such as blood, enabling new cost-effective diagnostic strategies.",{"name":81,"@type":72,"acceptedAnswer":82},"Why does multiomics integration pose difficulties for machine learning in CUP?",{"text":83,"@type":75},"Integrating multiple information sources (e.g., imaging, molecular biomarkers, family history) increases the dimensionality of the prediction problem. When data are scarce, this can lower predictive accuracy and robustness, requiring theoretical advances and careful model design.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]