[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-361511-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-361511-en":131},{"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","multimodal-oral-cancer-detection-with-embedding-level-oversampling-of-fused-image-and-clinical-data","Multimodal oral cancer detection with embedding-level oversampling of fused image and clinical data","","Oral cancer is often detected too late, with limited screening because real-world datasets contain few confirmed cases and visual assessment can be subjective. A multimodal method was developed to combine photographic features with basic clinical information to improve early identification of malignant lesions while addressing class imbalance. Annotated oral image data paired with patient metadata were used to train multiple machine learning models, enhanced via synthetic oversampling techniques. The best configuration improved macro F1 and ROC-AUC over image-only baselines, indicating stronger minority-class sensitivity. The key contribution is embedding-level oversampling in a fused image–metadata space. The study uses a tightly controlled single-center protocol, so results are best viewed as exploratory methodology evidence supporting clinician-assisted earlier recognition under the evaluated setting.",{"@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/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/multimodal-oral-cancer-detection-with-embedding-level-oversampling-of-fused-image-and-clinical-data/361511/",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/multimodal-oral-cancer-detection-with-embedding-level-oversampling-of-fused-image-and-clinical-data/361511.png","ImageObject",300,407,{"name":42,"@type":43},"pixelkiddo","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-11","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",12,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Why is early oral cancer detection difficult in real-world settings?","Question",{"text":63,"@type":64},"Screening is limited by subjective visual assessment and by a scarcity of confirmed cancer cases, which leads to strong class imbalance in datasets.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What modalities are combined in the proposed approach?",{"text":68,"@type":64},"The approach fuses photographic visual features with basic clinical information (patient metadata) to provide contextual risk information alongside lesion appearance.",{"name":70,"@type":61,"acceptedAnswer":71},"How does embedding-level oversampling address class imbalance?",{"text":72,"@type":64},"It performs synthetic sample generation within a fused image–metadata embedding space, preserving latent semantics while improving sensitivity to minority cancer cases.","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},361511,1790471530,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"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":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":145,"read_time":146,"preview_page_count":33,"preview_urls":147},962090883892,"https://ap-avatar.wpscdn.com/avatar/e00115db34f3e0f11b?x-image-process=image/resize,m_fixed,w_180,h_180&k=1790152879550218658","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nMultimodal oral cancer detection with embedding-level oversampling offused image and clinical data  \nPablo Ormeñ o-Arriagada1,2,5,8􀀍, Carla Taramasco2,5,8, Carlos Toro3,8,  \nGastó n Má rquez2,4, David Araya2,5,6,8, Valentina Z u n ˜ iga5, Diego Mellado2,5,8, Diego Alcocer6,7,8 & David Ruete5,8  \nOral cancer is a highly aggressive disease that is often detected too late, resulting in poor survival outcomes. Screening methods are limited by subjective assessment and by the scarcity of confirmed cancer cases in real-world datasets. We developed a multimodal approach that combines photographic features with basic clinical information to improve early identification of malignant lesions while addressing the strong imbalance typically found in medical datasets. Multiple machine learning models were trained on a dataset of annotated oral images paired with patient metadata, using synthetic sample generation techniques to improve representation of cancer cases. Our best configuration achieved good macro F1 and Area Under Receiver Operating Characteristic, outperforming imageonly baselines. The improvements indicate that integrating contextual patient information was associated with improved class-balanced performance under the evaluated protocol. These findings reflect performance differences under the evaluated multimodal protocol and imbalance learning for assisting clinicians in earlier recognition of oral cancer. Our key contribution lies in embedding-level oversampling within a fused image–metadata space, which preserves latent semantics while improving minority-class sensitivity. These results arise from a tightly controlled, single-center experimental setup and are best understood as exploratory insights into the methodology, rather than as evidence that can be readily extended to broader clinical contexts. These findings reflect performance differences within the evaluated experimental setting. Metadata integration is treated as a structural component of multimodal representation within a constrained experimental framework.  \nKeywords Oral cancer detection, Multimodal learning, Class imbalance, SMOTE, ADASYN, XGBoost  \nOral Cancer (OCA) represents a significant global health challenge, characterised by high incidence and mortality rates1. The World Health Organization reports that this disease causes approximately 200,000 deaths annually2. It is among the most prevalent head and neck malignancies worldwide, with late-stage detection strongly affecting prognosis and survival. Traditional diagnosis relies on visual inspection and biopsy confirmation, which are resource-intensive and prone to inter-observer variability3. This disease represents a significant global health burden, ranking among the most common cancers in low and middle income countries4. Early detection is critical because the 5-year survival rate drops drastically, from over 80% in early stages to less than 30% in advanced stages5. Despite being accessible to visual and tactile examination, oral cancers are frequently diagnosed late due to subtle early-stage symptoms and limited screening programs6. Early identification not only enhances survival but also reduces treatment-related morbidity and healthcare costs7. Integrating Artificial Intelligence (AI) driven diagnostic tools into clinical workflows has the potential to assist clinicians in identifying malignant  \n1Facultad de Ingenier´ıa, Ingenier´ıa Civil Informá tica, Negocios y Ciencias Agroambientales, Universidad Viñ adel Mar, Viñ a del Mar, Chile. 2Centro para la Prevenció n y Control del Cancer, CECAN, Santiago, Chile. 3Facultadde Ingenier´ıa, Universidad André s Bello, Talcahuano, Chile. 4Departamento de Ciencias de la Computació n y Tecnolog´ıas de la Informació n, Universidad del B´ıo-B´ıo, Chillá n, Chile. 5Facultad de Ingenier´ıa, Instituto de Tecnolog´ıa para la Innovació n en Salud y Bienestar, Universidad André s Bell","cbCaioV7Xz6TFbZy","https://ap.wps.com/l/cbCaioV7Xz6TFbZy","pdf",2019660,17,"English","# Introduction\n## Clinical challenge and need for early detection\n## Limitations of imaging-only diagnosis\n# Multimodal data integration\n## Complementary strengths of imaging and metadata\n# Method overview\n## Dataset and annotation paired with patient metadata\n## Imbalance learning via synthetic sampling\n# Results and contribution\n## Performance improvements over image-only baselines\n## Embedding-level oversampling in fused space","[{\"question\":\"Why is early oral cancer detection difficult in real-world settings?\",\"answer\":\"Screening is limited by subjective visual assessment and by a scarcity of confirmed cancer cases, which leads to strong class imbalance in datasets.\"},{\"question\":\"What modalities are combined in the proposed approach?\",\"answer\":\"The approach fuses photographic visual features with basic clinical information (patient metadata) to provide contextual risk information alongside lesion appearance.\"},{\"question\":\"How does embedding-level oversampling address class imbalance?\",\"answer\":\"It performs synthetic sample generation within a fused image–metadata embedding space, preserving latent semantics while improving sensitivity to minority cancer cases.\"}]","Multimodal oral cancer detection with embedding-level oversampling of fused image and clinical data | PDF",1790144659,43,[148,152,156,160],{"page_no":22,"url":149,"width":150,"height":151},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/cb0ee6e188165f133850162fbcad01cf.webp",983,1291,{"page_no":26,"url":153,"width":154,"height":155},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9e16d40b1e2a6b2a26542f6ca98cb0df.webp",982,1290,{"page_no":30,"url":157,"width":158,"height":159},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/9ad94f4ef768cb78ce217442650bbd75.webp",981,1289,{"page_no":33,"url":161,"width":162,"height":163},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/52dc41157159ea74cc16c41524c09302.webp",980,1287]