[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119795-en":3,"doc-seo-119795-105":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},119795,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","Towards Generalizable Machine Learning Models for Computer-Aided Diagnosis in Medicine - Dissertation","Hidden stratification describes training datasets that contain unlabeled case subsets influencing machine learning performance. Models that overlook these hidden groups may show strong overall accuracy and sensitivity yet still fail on low-prevalence disease cases, which are clinically critical because misdiagnosis can cause significant harm. This work targets robust, trustworthy CAD and treatment-effect prediction by detecting latent stratification and evaluating models using both overall metrics and subgroup performance, including the “worst group”. Three stratification methods are studied.","DePaul University  \nDigital Commons@DePaul  \n\n| College of Computing and Digital Media Dissertations | Jarvis College of Computing and Digital Media |\n| --- | --- |\n| Spring 5-30-2023\u003Cbr>Towards generalizable machine learning models for computer-aided diagnosis in medicine\u003Cbr>Yiyang Wang\u003Cbr>DePaul University, [ianwang7152@gmail.com](ianwang7152@gmail.com)\u003Cbr>Follow this and additional works at: [https://via.library.depaul.edu/cdm_etd](https://via.library.depaul.edu/cdm_etd)\u003Cbr> Part of the Biomedical Informatics Commons, and the Data Science Commons |  |\n\nRecommended Citation  \nWang, Yiyang, \"Towards generalizable machine learning models for computer-aided diagnosis in medicine\" (2023) . College of Computing and Digital Media Dissertations. 48.  \n[https://via.library.depaul.edu/cdm_etd/48](https://via.library.depaul.edu/cdm_etd/48)  \nThis Dissertation is brought to you for free and open access by the Jarvis College of Computing and Digital Media at Digital Commons@DePaul. It has been accepted for inclusion in College of Computing and Digital Media Dissertations by an authorized administrator of Digital Commons@DePaul. For more information, please contact [digitalservices@depaul.edu](digitalservices@depaul.edu).  \nTOWARDS GENERALIZABLE MACHINE LEARNING MODELS FOR COMPUTER-AIDED DIAGNOSIS IN MEDICINE  \nBY  \nYIYANG WANG  \nA DISSERTATION SUBMITTED TO THE COLLEGE OF COMPUTING AND DIGITAL MEDIA OF DEPAUL UNIVERSITY  \nIN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE DEGREE OF DOCTOR OF PHILOSOPHY COMPUTER SCIENCE  \nDEPAUL UNIVERSITY  \nCHICAGO, ILLINOIS  \nJune 2023  \nDePaul University  \nCollege of Computing and Digital Media  \nDissertation Verification  \nThis doctoral dissertation has been read and approved by the dissertation committee below according to the requirements of the Computer and Information Systems PhD program and DePaul University.  \nName: Yiyang Wang  \nTitle of dissertation:  \nTowards Generalizable Machine Learning Models for Computer-Aided Diagnosis in Medicine  \nDate of Dissertation Defense: May 30, 2023  \nDaniela Stan Raicu Dissertation Advisor*  \nJacob Furst  \n1st Reader  \nThiruvarangan Ramaraj  \n2nd Reader  \nSamuel G. Armato  \n3rd Reader  \n4th Reader (if applicable)  \n5th Reader (if applicable)  \n* A copy of this form has been signed, but may only be viewed after submission and approval of FERPA request letter.  \nAbstract  \nHidden stratification represents a phenomenon in which a training dataset contains unlabeled (hidden) subsets of cases that may affect machine learning model performance. Machine learning models that ignore the hidden stratification phenomenon--despite promising overall performance measured as accuracy and sensitivity--often fail at predicting the low prevalence cases, but those cases remain important. In the medical domain, patients with diseases are often less common than healthy patients, and a misdiagnosis of a patient with a disease can have significant clinical impacts. Therefore, to build a robust and trustworthy CAD system and a reliable treatment effect prediction model, we cannot only pursue machine learning models with high overall accuracy, but we also need to discover any hidden stratification in the data and evaluate the proposing machine learning models with respect to both overall performance and the performance on certain subsets (groups) of the data, such as the ‘worst group’.  \nIn this study, I investigated three approaches for data stratification: a novel algorithmic deep learning (DL) approach that learns similarities among cases and two schema completion approaches that utilize domain expert knowledge. I further proposed an innovative way to integrate the discovered latent groups into the loss functions of DL models to allow for better model generalizability under the domain shift scenario caused by the data heterogeneity.  \nMy results on lung nodule Computed Tomography (CT) images and breast cancer histopathology images demonstrate that learning homogeneous groups within","cbCaiuFuKC3xEgIB","https://ap.wps.com/l/cbCaiuFuKC3xEgIB","pdf",2128228,1,134,"English","en",105,"# CHAPTER 1. Introduction\n## Hidden Stratification","[{\"question\":\"What is hidden stratification, and why does it matter for computer-aided diagnosis?\",\"answer\":\"Hidden stratification means a dataset contains unlabeled subsets that affect model behavior. Ignoring it can lead to strong overall metrics while underperforming on rare, clinically important cases.\"},{\"question\":\"How does the study improve generalizability under domain shift?\",\"answer\":\"It integrates discovered latent groups into deep learning loss functions, aiming to produce better generalizability when data heterogeneity causes domain shift.\"},{\"question\":\"Which medical imaging tasks are used to evaluate the proposed approaches?\",\"answer\":\"The approaches are demonstrated on lung nodule CT images and breast cancer histopathology images, showing improved performance for low-prevalence and worst-performing cases.\"}]","Towards Generalizable Machine Learning Models for Computer-Aided Diagnosis in Medicine - Dissertation | PDF",1785726340,338,{"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},"towards-generalizable-machine-learning-models-for-computer-aided-diagnosis-in-medicine-dissertation","",{"@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/towards-generalizable-machine-learning-models-for-computer-aided-diagnosis-in-medicine-dissertation/119795/",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","2026-08-03",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 is hidden stratification, and why does it matter for computer-aided diagnosis?","Question",{"text":75,"@type":76},"Hidden stratification means a dataset contains unlabeled subsets that affect model behavior. Ignoring it can lead to strong overall metrics while underperforming on rare, clinically important cases.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study improve generalizability under domain shift?",{"text":80,"@type":76},"It integrates discovered latent groups into deep learning loss functions, aiming to produce better generalizability when data heterogeneity causes domain shift.",{"name":82,"@type":73,"acceptedAnswer":83},"Which medical imaging tasks are used to evaluate the proposed approaches?",{"text":84,"@type":76},"The approaches are demonstrated on lung nodule CT images and breast cancer histopathology images, showing improved performance for low-prevalence and worst-performing cases.","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"]