[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-365283-105":3,"detail-sidebar-cat-0-en-105":85,"doc-detail-365283-en":134},{"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":78,"head_meta":80,"extra_data":82,"updated_unix":84},105,"en","incorporation-of-explainable-artificial-intelligence-in-ensemble-machine-learning-driven-pancreatic-cancer-diagnosis","Incorporation of Explainable Artificial Intelligence in Ensemble Machine Learning-driven Pancreatic Cancer Diagnosis","","Pancreatic cancer remains a high-fatality disease with late diagnosis and poor prognosis, driving the need for creative clinical decision-support. This study builds and evaluates six machine learning algorithms and an ensemble voting classifier using a public dataset of 590 patient urine samples. Hybrid models are formed from top single models and interpreted with SHAP to identify influential diagnostic features. The ensemble voting classifier achieves 96.61% accuracy and 98.72% precision, with strong AUC performance across hybrids, supporting accurate early detection potential.",{"@graph":14,"@context":77},[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/incorporation-of-explainable-artificial-intelligence-in-ensemble-machine-learning-driven-pancreatic-cancer-diagnosis/365283/",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/incorporation-of-explainable-artificial-intelligence-in-ensemble-machine-learning-driven-pancreatic-cancer-diagnosis/365283.png","ImageObject",300,407,{"name":42,"@type":43},"Rhys","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-29","2026-09-23",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",9,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69,73],{"name":60,"@type":61,"acceptedAnswer":62},"What is the main goal of this research?","Question",{"text":63,"@type":64},"To develop and analyze machine learning and ensemble models for early pancreatic cancer detection using clinical characteristics from urine samples, and to interpret model performance using SHAP.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What data source and input were used for training?",{"text":68,"@type":64},"A publicly available dataset containing 590 patient urine samples, used to classify cancerous versus non-cancerous pancreatic cases based on selected attributes.",{"name":70,"@type":61,"acceptedAnswer":71},"How did the ensemble voting classifier perform compared with standalone models?",{"text":72,"@type":64},"It outperformed all standalone models, reaching 96.61% accuracy and 98.72% precision.",{"name":74,"@type":61,"acceptedAnswer":75},"How is explainability handled in the study?",{"text":76,"@type":64},"SHAP (Shapley Additive Explanations) is used to provide interpretation and highlight the most influential features with the greatest positive SHAP values for pancreatic cancer diagnosis.","https://schema.org",{"og:url":32,"og:type":79,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":81,"canonical":32},"index,follow",{"doc_id":83,"site_id":7},365283,1790644117,{"code":4,"msg":86,"data":87},"success",[88,92,96,100,105,110,115,119,123,126,130],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},"Exam",70,"exam",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},5,"Comic",60,"comic",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":107,"show_sort_weight":108,"slug":109},6,"Technology",50,"technology",{"id":111,"doc_module":4,"doc_module_name":25,"category_name":112,"show_sort_weight":113,"slug":114},7,"Healthcare",40,"healthcare",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":117,"slug":118},8,30,"research-report",{"id":55,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":121,"slug":122},"Religion & Spirituality",20,"religion-spirituality",{"id":121,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":121,"slug":125},"World Cup","world-cup",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":127,"slug":129},10,"Lifestyle","lifestyle",{"id":131,"doc_module":4,"doc_module_name":25,"category_name":132,"show_sort_weight":101,"slug":133},19,"General","general",{"code":4,"msg":86,"data":135},{"doc_id":83,"user_id":136,"nickname":42,"user_avatar":137,"doc_module":4,"category_id":116,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":143,"language":144,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":145,"faqs":146,"seo_title":147,"seo_description":12,"update_tm":148,"read_time":149,"preview_page_count":33,"preview_urls":150},687207024643,"https://ap-avatar.wpscdn.com/davatar_3d24733baf745e90a7e4bdd5f77d97b2","[www. nature.com/scientificreports](www. nature.com/scientificreports)  \nOPEN  \nIncorporation of explainable artificial intelligence in ensemble machine learning-driven pancreatic cancer diagnosis  \nFaisal Abdulaziz Almisned1􀀍, Natacha Usanase2,3􀀍, Dilber Uzun Ozsahin2,4,5 & Ilker Ozsahin2  \nDespite the strides made in medical science, pancreatic cancer continues to be a threat, highlighting the urgent need for creative strategies to address this concern. Recently, a potential approach that has attracted significant attention is using machine learning in clinical decision-making. This research aims to analyze six machine learning algorithms, and an ensemble voting classifier, develop hybrid models for the early detection of pancreatic cancer based on several clinical characteristics and interpret their performance with Shapley Additive Explanations (SHAP). A publicly available dataset composed of 590 patient urine samples was utilized to develop six conventional models for the classification of cancerous from non-cancerous pancreatic cases through the analysis of specific attributes. An ensemble voting classifier was developed from the best-performed single models, which were later hybridized to form six novel hybrid models. The ensemble voting classifier outperformed all standalone models with an accuracy of 96.61% and a precision of 98.72%. The six novel hybrid models exhibited higher performance than single models with voting classifier random forest hybridized model outperforming others with anAUC of 99.05%(95% confidence interval (CI): 0.93-1.00) and an interpretation was given by SHAP showing top influential features in pancreatic cancer diagnosis that exhibited the greatest positive SHAP values. Employing rapid sophisticated models with high accuracy and precision holds significant promise in facilitating the effective detection of various diseases, including pancreatic cancer.  \nKeywords Biomarkers, Cancer, Diagnosis, Ensemble model, SHAP, Voting classifier  \nOver 400,000 men and women die from pancreatic cancer annually, representing a worldwide chronic disease1. The five-year survival rate for this disease is below 10% 1. Globally, this particular cancer ranks eighth among women and seventh among men in terms of cancer-related fatalities2. Consequently, by 2030, pancreatic cancer is predicted to replace lung cancer as the leading source of cancer death1. Before diagnosis, patients may have significant symptoms like pain, weakness, nausea, vomiting, and weight loss which may also indicate other health conditions1. As a result, it is a difficult oncology case because of its late-stage diagnosis and poor prognosis; however, early identification is critical for improving patient outcomes.  \nThere is presently no viable, safe screening technology, whether molecular or imaging-based, that allows for detecting pancreatic cancer in asymptomatic individuals in its early stages. Traditional methods for identifying microscopic premalignant lesions; including endoscopic ultrasonography (EUS), positron emission tomography (PET), computed tomography (CT), and magnetic resonance imaging (MRI), are characterized by their high cost and restricted sensitivity and specificity3. Furthermore, the identification of small-localized lesions during a routine abdominal examination is challenging due to the deep anatomic position of the pancreas4. As a result, identifying pancreatic cancer biomarkers in physiological fluids (e.g., serum, plasma, urine, or saliva) is feasible at a reasonable cost, and requires minimal invasiveness, as a result, this enables earlier detection and diagnosis and consequently can facilitate prompt therapy planning5. Urine is a potentially useful substitute biological fluid to blood; which has historically been the primary source of biomarkers. Although lacking in dynamic  \n1Department of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi Arabia. 2Operational Resea","cbCaij7k5K6Cs9aq","https://ap.wps.com/l/cbCaij7k5K6Cs9aq","pdf",2083989,15,"English","# Objectives and Approach\n# Dataset and Model Development\n# Ensemble and Hybrid Modeling Results\n# Interpretability via SHAP\n# Clinical Relevance and Implications","[{\"question\":\"What is the main goal of this research?\",\"answer\":\"To develop and analyze machine learning and ensemble models for early pancreatic cancer detection using clinical characteristics from urine samples, and to interpret model performance using SHAP.\"},{\"question\":\"What data source and input were used for training?\",\"answer\":\"A publicly available dataset containing 590 patient urine samples, used to classify cancerous versus non-cancerous pancreatic cases based on selected attributes.\"},{\"question\":\"How did the ensemble voting classifier perform compared with standalone models?\",\"answer\":\"It outperformed all standalone models, reaching 96.61% accuracy and 98.72% precision.\"},{\"question\":\"How is explainability handled in the study?\",\"answer\":\"SHAP (Shapley Additive Explanations) is used to provide interpretation and highlight the most influential features with the greatest positive SHAP values for pancreatic cancer diagnosis.\"}]","Incorporation of Explainable Artificial Intelligence in Ensemble Machine Learning-driven Pancreatic Cancer Diagnosis | PDF",1790160540,38,[151,155,159,163],{"page_no":22,"url":152,"width":153,"height":154},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/d7381a7112916ee44ebfc6b454758007.webp",983,1291,{"page_no":26,"url":156,"width":157,"height":158},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/01ecb00f8f6b055c8f3d886fdb63dd25.webp",982,1290,{"page_no":30,"url":160,"width":161,"height":162},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/587fe26165e0ee6147084a742679101b.webp",981,1289,{"page_no":33,"url":164,"width":165,"height":166},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-16/5341f226fa1a57d885f3d0198570968b.webp",980,1287]