[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118656-en":3,"doc-seo-118656-105":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},118656,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","Machine Learning in Differentiated Thyroid Cancer Recurrence and Risk Prediction - A 383-Patient Study Using Feature Selection","Differentiated thyroid cancer (DTC) creates complex management needs because recurrence risk varies widely across patients. This study builds and validates machine learning models using a dataset of 383 patients with clinical, pathological, and treatment variables, combined with multiple feature selection strategies. Models spanning light gradient boosting machine, random forest, k-nearest neighbor, logistic regression, stochastic gradient descent, and a tabular deep learner (Gandalf) were assessed. Feature selection supports recurrence prediction accuracy of 94.8–95.9% under two validation methods, using tumor response status, advanced stage, and patient age, and also enables analysis of American Thyroid Association (ATA) risk scores.","Article  \nMachine Learning in Differentiated Thyroid Cancer Recurrence and Risk Prediction  \nMatthew A. Penner 1,2,3, Derek Berger 1, Xuchen Guo 1 and Jacob Levman 1,4, *  \nAcademic Editor: Giorgio De Nunzio  \nReceived: 8 May 2025  \nRevised: 30 July 2025  \nAccepted: 23 August 2025  \nPublished: 27 August 2025  \nCitation: Penner, M.A.; Berger, D.; Guo, X.; Levman, J. Machine Learning in Differentiated Thyroid Cancer Recurrence and Risk Prediction. Appl. Sci. 2025, 15, 9397. [https://doi.org/](https://doi.org/)[ ](https://doi.org/)[10.3390/app15179397](10.3390/app15179397)  \nCopyright: © 2025 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)) .  \n1 Department of Computer Science, St. Francis Xavier University, Antigonish, NS B2G 2W5, Canada;  \n[matthew.penner@mail.utoronto.ca](matthew.penner@mail.utoronto.ca) (M.A.P.); [dberger@stfx.ca](dberger@stfx.ca) (D.B.); [x2023diy@stfx.ca](x2023diy@stfx.ca) (X.G.)  \n2 Department of Physics, St. Francis Xavier University, Antigonish, NS B2G 2W5, Canada  \n3 Department of Physics, University of Toronto, Toronto, ON M5S 1A7, Canada  \n4 Nova Scotia Health Authority, Halifax, NS B3H 1V8, Canada  \n* [Correspondence: jlevman@stfx.ca](Correspondence: jlevman@stfx.ca)  \nAbstract  \nDifferentiated thyroid cancer (DTC) poses significant management challenges due to the variable risk of recurrence. This study uses a dataset comprising clinical, pathological, and treatment data from 383 patients to develop and validate machine learning models, combined with feature selection algorithms, for predicting differentiated thyroid cancer recurrence. We evaluated models based on a variety of machine learning technologies (light gradient boosting machine, random forest, k-nearest neighbor, logistic regression, stochastic gradient descent, and an emerging deep learner optimized for tabular data: Gandalf) combined with several feature selection methods. Our feature selection technologies include an emerging redundancy-aware wrapper-based feature selection technique, achieving thyroid cancer recurrence prediction accuracy of 94.8 to 95.9% across two validation methods, based only on whether the patient’s tumor’s response was structurally incomplete, whether their tumor’s stage was advanced (III, IVA, or IVB), and the patient’sage. The results underline the potential for machine learning to enhance the precision of recurrence prediction in DTC while developing technologies whose predictive capacity is more easily explained. Using the same dataset, machine learning and feature selection techniques, this study also provides an analysis on predicting American Thyroid Association (ATA) risk scores. The technologies developed as part of this study have potential for improving the personalization of healthcare through the creation of models based on detailed patient-specific clinical attributes.  \nKeywords: machine learning; differentiated thyroid cancer; cancer recurrence; thyroid cancer; predictive modeling; risk prediction; artificial intelligence  \n1. Introduction  \n1.1. Overview  \nThyroid cancer is the fifth most common cancer in women in 2015, and there are approximately 62,000 new cases a year for men with the most common type being differentiated thyroid cancer (DTC) [1] . The majority of thyroid cancers are well differentiated, having been derived from thyroid follicular cells [2] . Well-differentiated thyroid cancers occur in papillary, follicular, and oncocytic forms, representing 84%, 4%, and 2% of all thyroid cancers, respectively [2] . These cancers are usually curable when found early and in younger patients [2] . However, some patients may experience recurrence or metastasis  \n(meaning it comes back after treatment, possibly having spread to anot","cbCainB5xCLimVkO","https://ap.wps.com/l/cbCainB5xCLimVkO","pdf",647433,1,19,"English","en",105,"# Introduction\n## Overview\n## Clinical Management\n## Literature Review","[{\"question\":\"What problem does the study address in differentiated thyroid cancer?\",\"answer\":\"It addresses the variable recurrence risk in differentiated thyroid cancer and the need for more precise prognostic prediction to guide monitoring and treatment intensity.\"},{\"question\":\"How is the machine learning approach evaluated in the study?\",\"answer\":\"The study trains and validates several machine learning models using a dataset of 383 patients, applying multiple feature selection methods and reporting performance across two validation methods.\"},{\"question\":\"Which key inputs drive the top recurrence prediction results?\",\"answer\":\"The results are based on whether the tumor’s response was structurally incomplete, whether the stage was advanced (III, IVA, or IVB), and the patient’s age.\"}]","Machine Learning in Differentiated Thyroid Cancer Recurrence and Risk Prediction - A 383-Patient Study Using Feature Selection | PDF",1785684753,48,{"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},"machine-learning-in-differentiated-thyroid-cancer-recurrence-and-risk-prediction-a-383-patient-study-using-feature-selection","",{"@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/machine-learning-in-differentiated-thyroid-cancer-recurrence-and-risk-prediction-a-383-patient-study-using-feature-selection/118656/",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 problem does the study address in differentiated thyroid cancer?","Question",{"text":75,"@type":76},"It addresses the variable recurrence risk in differentiated thyroid cancer and the need for more precise prognostic prediction to guide monitoring and treatment intensity.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the machine learning approach evaluated in the study?",{"text":80,"@type":76},"The study trains and validates several machine learning models using a dataset of 383 patients, applying multiple feature selection methods and reporting performance across two validation methods.",{"name":82,"@type":73,"acceptedAnswer":83},"Which key inputs drive the top recurrence prediction results?",{"text":84,"@type":76},"The results are based on whether the tumor’s response was structurally incomplete, whether the stage was advanced (III, IVA, or IVB), and the patient’s age.","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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]