[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118113-en":3,"doc-seo-118113-105":30,"detail-sidebar-cat-0-en-105":91},{"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":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},118113,5909877438554,"Maeve","https://ap-avatar.wpscdn.com/avatar/5600025385ad2bf12a7?_k=1778553567797529272",8,"Research & Report","Knowledge-Informed Machine Learning for Cancer Diagnosis and Prognosis - A review","Cancer remains one of the most challenging diseases to treat, and machine learning is increasingly used to analyze multi-omics profiles and medical imaging for cancer diagnosis and prognosis. However, limited labeled samples, complex high-dimensional data interactions, patient and intratumoral heterogeneity, and the need for interpretability and consistency with biomedical knowledge constrain model performance. This review summarizes knowledge-informed machine learning approaches that fuse biomedical knowledge with data, covering key clinical, imaging, molecular, and treatment data types. It compares knowledge representation and integration strategies and discusses future directions to advance cancer research.","Knowledge-Informed Machine Learning for Cancer Diagnosis and Prognosis:  \nA review  \nLingchao Mao1Ù, Hairong Wang1Ù, Leland S. Hu3, 4, 5, 6, Nhan L Tran5, 6, Peter D Canoll7, Kristin R Swanson2, 5, Jing  \nLi1*  \n1 H. Milton Stewart School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, 30332, USA.  \n2 Mathematical NeuroOncology Lab, Precision Neurotherapeutics Innovation Program, Mayo Clinic Arizona, 5777 East Mayo Blvd, Support Services Building Suite 2-700, Phoenix, AZ, 85054, USA.  \n3 Department of Radiology, Mayo Clinic Arizona, 5777 E. Mayo Blvd, Phoenix, AZ, 85054, USA.  \n4 School of Computing, Informatics, and Decision Systems Engineering, Arizona State University, 699 S Mill Ave, Tempe, AZ, 85281, USA.  \n5 Department of Neurosurgery, Mayo Clinic Arizona, 5777 E. Mayo Blvd, Phoenix, AZ, 85054, USA.  \n6 Department of Cancer Biology, Mayo Clinic Arizona, 5777 E. Mayo Blvd, Phoenix, AZ, 85054, USA.  \n7 Department of Pathology and Cell Biology, Columbia University Medical Center, 630 West 168th Street, New York, NY, 10032, USA.  \nÙCo-first author  \n*To whom correspondence should be addressed: [j](jli3175@gatech.edu)[li3175@gatech.edu](jli3175@gatech.edu)  \nAbstract  \nCancer remains one of the most challenging diseases to treat in the medical field. Machine learning has enabled in-depth analysis of rich multi-omics profiles and medical imaging for cancer diagnosis and prognosis. Despite these advancements, machine learning models face challenges stemming from limited labeled sample sizes, the intricate interplay of high-dimensionality data types, the inherent heterogeneity observed among patients and within tumors, and concerns about interpretability and consistency with existing biomedical knowledge. One approach to surmount these challenges is to integrate biomedical knowledge into data-driven models, which has proven potential to improve the accuracy, robustness, and interpretability of model results. Here, we review the state-of-the-art machine learning studies that adopted the fusion of biomedical knowledge and data, termed knowledge-informed machine learning, for cancer diagnosis and prognosis. Emphasizing the properties inherent in four primary data types including clinical, imaging, molecular, and treatment data, we highlight modeling considerations relevant to these contexts. We provide an overview of diverse forms of knowledge representation and current strategies of knowledge integration into machine learning pipelines with concrete examples. We conclude the review article by discussing future directions to advance cancer research through knowledge-informed machine learning.  \nIntroduction  \nCancer stands as a predominant cause of human death worldwide, with its incidence escalating alongside the increasing global life expectancy2. Despite its widespread occurrence, cancer remains one of the most formidable challenges in the medical field because the genetic and pathogenic mechanisms of tumors are still too complex to be fully resolved. In recent decades, machine learning (ML) has positioned itself as promising tool for analyzing complex patterns from large datasets. The computational power and versatility of ML models allow for the discrimination of subtle differences in multimodal images, analysis of vast arrays of digital histopathology slides, and interpretation of complex genetic and molecular profiles. ML has demonstrated success in numerous cancer applications and has promising potential to automate medical  \ndata analyses, improve diagnosis and prognosis capabilities, and support better clinical decision-making in cancer treatment3,4 .  \nA leading cause of the limited effectiveness of conventional therapies is the pronounced heterogeneity inherent in tumors5–8. At the individual-level, no two patients, even within the same subtype of tumor, behave clinically the same, with or without treatment, suggesting that conventional one-model-fits-all approaches are not sufficien","cbCaiviPkYad6l76","https://ap.wps.com/l/cbCaiviPkYad6l76","pdf",1183138,1,41,"English","en",105,"# Abstract\n# Introduction\n## Tumor heterogeneity and limits of conventional therapies\n## Data scarcity and generalization constraints\n## Multimodal high-dimensional modeling challenges\n## Radiogenomics and invasive diagnosis considerations","[{\"question\":\"What challenges limit machine learning models for cancer diagnosis and prognosis?\",\"answer\":\"Key challenges include limited labeled sample sizes, the complexity of high-dimensional multimodal data, strong heterogeneity among patients and within tumors, and concerns about interpretability and alignment with existing biomedical knowledge.\"},{\"question\":\"What does knowledge-informed machine learning aim to do?\",\"answer\":\"It integrates biomedical knowledge into data-driven models to improve accuracy, robustness, and interpretability of results.\"},{\"question\":\"Which primary data types does the review emphasize for modeling?\",\"answer\":\"The review highlights clinical, imaging, molecular, and treatment data, and explains how knowledge integration can be applied within these contexts.\"}]","Knowledge-Informed Machine Learning for Cancer Diagnosis and Prognosis - A review | PDF",1785681680,103,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"knowledge-informed-machine-learning-for-cancer-diagnosis-and-prognosis-a-review","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/knowledge-informed-machine-learning-for-cancer-diagnosis-and-prognosis-a-review/118113/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What challenges limit machine learning models for cancer diagnosis and prognosis?","Question",{"text":75,"@type":76},"Key challenges include limited labeled sample sizes, the complexity of high-dimensional multimodal data, strong heterogeneity among patients and within tumors, and concerns about interpretability and alignment with existing biomedical knowledge.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What does knowledge-informed machine learning aim to do?",{"text":80,"@type":76},"It integrates biomedical knowledge into data-driven models to improve accuracy, robustness, and interpretability of results.",{"name":82,"@type":73,"acceptedAnswer":83},"Which primary data types does the review emphasize for modeling?",{"text":84,"@type":76},"The review highlights clinical, imaging, molecular, and treatment data, and explains how knowledge integration can be applied within these contexts.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]