[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127647-en":3,"doc-seo-127647-105":31,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127647,962084925502,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",7,"Healthcare","Understanding Machine Learning Explainability Models in the context of Pancreatic Cancer Treatment","Increasing use of machine learning in medicine requires models whose decisions can be understood and trusted by end users. This work studies explainability for a pancreatic cancer diagnosis setting, using a public dataset and multiple ML approaches to decide whether chemotherapy should be prescribed. Decision Tree, Random Forest, and model-agnostic ad-hoc explainability methods are evaluated and compared against a standard rule-based pancreatic cancer treatment framework, focusing on diagnostic validation and decision transparency.","Understanding Machine Learning Explainability Models in the context of Pancreatic Cancer Treatment  \nJos Bobes-Bascarn, ngel Fernndez Leal, Eduardo Mosqueira-Rey, David Alonso-Ros, Elena Hernndez-Pereira, Vicente Moret-Bonillo Centro de Investigaci´on CITIC, University of Coru~na, Spain Correspondence: jose .bobes@udc .es  \nDOI: [https://doi.org/10.17979/spudc.000024.28](https://doi.org/10.17979/spudc.000024.28)  \nAbstract: The increasing adoption of artificial intelligent systems at sensitive domains where humans are particularly, such as medicine, has provided the context to deeply explore ways of making machine learning models (ML) understandable for their final users. The success of such systems require the trust of their users, and thus there is a need to design and provide methods to understand the decisions made by such systems. We start from a public Pancreatic Cancer dataset and experiment with different ML models on a diagnosis scenario with the goal to decide whether a patient should be prescribed with a chemotherapy treatment. To validate the diagnosis results we explore different explainability approaches: Decision Tree, Random Forest, and model agnostic ad-hoc models, and compare them against a standard Pancreatic Cancer treatment set of rules. The increasing adoption of artificial intelligent systems at sensitive domains where humans are particularly, such as medicine, has provided the context to deeply explore ways of making machine learning models (ML) understandable for their final users. The success of such systems require the trust of their users, and thus thereis a need to design and provide methods to understand the decisions made by such systems. We start from a public Pancreatic Cancer dataset and experiment with different ML models. To validate the diagnostic results we explore different explainability approaches: Decision Tree based approach, Random Forest based approach, and different model agnostic ad-hoc approaches, and we compare them against a standard Pancreatic Cancer treatment set of rules.  \n1 Introduction  \nWhen creating Machine Learning (ML) models there is normally a trade of between interpretability and accuracy. While the former aims to create models that can be understand by their end-users, the search for accuracy often require complex models that are not easy to interpret.  \nIn recent years ML models are being deployed covering a wide range of scenarios were it is of crucial importance the ability to understand how those models behave and reach a certain conclusion. It is equally important to reach a certain level of accuracy so that the models could be trust in real scenarios.  \nIn this research, we continued from our previous work on AL Bobes-Bascarn et al. (2021) Bobes-Bascarn et al. (2023), where we first experimented with generated synthetic data and an Active Learning approach, and then followed with a real dataset introducing medical doctors in the loop of a therapy selection model for pancreatic cancer. On our previous work the goal was to overcame the scarcity of data available on the Pancreatic Cancer context by incorporating humans into the ML loop Mosqueira-Rey et al. (2022b) . The focus is now on applying several explainability techniques to get useful insight about the underlining models.  \n176 Proceedings XoveTIC 2023  \nWe found two different concepts in the literature that refer to the quality of a system to be understood by its end-users: Explainability and Interpretability.  \nExplainability is the ability to describe how a model could reach a certain prediction or classification result so that it can be understand by its end-users.  \nInterpretability is intrinsic to the model itself and refers to the fact that end-users could interpret the relationship between the model inputs and its outputs.  \nOn the one hand, we found that better interpretability and understandability leads to better trust and eases the adoption of AI systems. On the other hand, better accuracy re","cbCaijdjv2u0IFlJ","https://ap.wps.com/l/cbCaijdjv2u0IFlJ","pdf",402532,2,1,8,"English","en",105,"# Introduction\n## Explainability vs. interpretability\n## Trade-off between interpretability and accuracy\n## eXplainable AI (XAI) goals\n# Dataset\n## Source and patient cohort\n## Chemotherapy indication setup","[{\"question\":\"Why is explainability important in pancreatic cancer treatment models?\",\"answer\":\"Medical deployment requires user trust, and explainability enables end users to understand how a model reaches diagnostic or treatment-related decisions.\"},{\"question\":\"What explainability approaches are compared in this work?\",\"answer\":\"The study evaluates Decision Tree and Random Forest explainability approaches, along with model-agnostic ad-hoc explainability methods.\"},{\"question\":\"How is the evaluation framework for diagnosis results organized?\",\"answer\":\"Diagnosis results produced by the ML models are validated by comparing explainability outputs against a standard pancreatic cancer treatment set of rules.\"}]","Understanding Machine Learning Explainability Models in the context of Pancreatic Cancer Treatment | PDF",1785940491,20,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"understanding-machine-learning-explainability-models-in-the-context-of-pancreatic-cancer-treatment","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/healthcare/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/understanding-machine-learning-explainability-models-in-the-context-of-pancreatic-cancer-treatment/127647/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why is explainability important in pancreatic cancer treatment models?","Question",{"text":76,"@type":77},"Medical deployment requires user trust, and explainability enables end users to understand how a model reaches diagnostic or treatment-related decisions.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What explainability approaches are compared in this work?",{"text":81,"@type":77},"The study evaluates Decision Tree and Random Forest explainability approaches, along with model-agnostic ad-hoc explainability methods.",{"name":83,"@type":74,"acceptedAnswer":84},"How is the evaluation framework for diagnosis results organized?",{"text":85,"@type":77},"Diagnosis results produced by the ML models are validated by comparing explainability outputs against a standard pancreatic cancer treatment set of rules.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,119,123,127,130,134],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":117,"slug":118},40,"healthcare",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":120,"show_sort_weight":121,"slug":122},"Research & Report",30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":30,"slug":126},9,"Religion & Spirituality","religion-spirituality",{"id":30,"doc_module":4,"doc_module_name":47,"category_name":128,"show_sort_weight":30,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":47,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":47,"category_name":136,"show_sort_weight":107,"slug":137},19,"General","general"]