[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123381-en":3,"doc-seo-123381-105":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},123381,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Evaluating Gender Fairness of Machine Learning Algorithms for Pain Detection - Paper Review","Automated pain detection using machine learning and deep learning offers major value in healthcare, especially when patients cannot reliably self-report pain. Yet accuracy and fairness across demographic groups, notably gender, remain insufficiently studied. This paper evaluates gender fairness in pain detection models trained on the UNBC-McMaster Shoulder Pain Expression Archive Database using only facial-expression images. Traditional ML and advanced vision models are compared with multiple performance and fairness metrics, revealing persistent gender bias.","FG2025 \\#****  \n000  \n001  \n002  \n003  \n004  \n005  \n006  \n007  \n008  \n009  \n010  \n011  \n012  \n013  \n014  \n015  \n016  \n017  \n018  \n019  \n020  \n021  \n022  \n023  \n024  \n025  \n026  \n027  \n028  \n029  \n030  \n031  \n032  \n033  \n034  \n035  \n036  \n037  \n038  \n039  \n040  \n041  \n042  \n043  \n044  \n045  \n046  \n047  \n048  \n049  \n050  \n051  \n052  \n053  \n054  \n055  \n056  \n057  \n058  \n059  \n060  \n061  \n062  \n063  \n064  \n065  \n066  \nFG2025 Submission. CONFIDENTIAL REVIEW COPY. DO NOT DISTRIBUTE.  \nEvaluating Gender Fairness of ML Algorithms for Pain Detection  \nFG2025  \n\\#****  \n067  \n068  \n069  \n070  \n071  \n072  \n073  \n074  \n075  \nAbstract—Automated pain detection through machine learning (ML) and deep learning (DL) algorithms holds significant potential in healthcare, particularly for patients unable to selfreport pain levels. However, the accuracy and fairness of these algorithms across different demographic groups (e.g., gender) remain under-researched. This paper investigates the gender fairness of ML and DL models trained on the UNBC-McMaster Shoulder Pain Expression Archive Database, evaluating the performance of various models in detecting pain based solely on the visual modality of participants’ facial expressions. We compare traditional ML algorithms, Linear Support Vector Machine (L SVM) and Radial Basis Function SVM (RBF SVM), with DL methods, Convolutional Neural Network (CNN) and Vision Transformer (ViT), using a range of performance and fairness metrics. While ViT achieved the highest accuracy and aselection of fairness metrics, all models exhibited gender-based biases. These findings highlight the persistent trade-off between accuracy and fairness, emphasising the need for fairness-aware techniques to mitigate biases in automated healthcare systems.  \nI. INTRODUCTION  \nMachine Learning (ML) has become an essential tool in modern healthcare, offering the potential to automate complex tasks, such as pain detection, through images and videos [34] . However, as these technologies are adopted, ensuring fairness becomes critical to avoid perpetuating or exacerbating existing biases [71], [9] .  \nML fairness refers to the absence of prejudice or bias in a machine learning system concerning sensitive attributes such as gender, race, or age [50] . In pain detection models, fairness ensures that individuals across different demographic groups are equally likely to be correctly classified. More specifically, gender fairness focuses on providing equal treatment and outcomes for male and female groups [50], [14] . For example, a fair pain detection system would ensure equal probability of predicting pain for individuals regardless of gender, assuming equivalent pain intensity [14] . While various fairness metrics such as Equalised Odds and Equal Accuracy exist [72],[8], no single metric captures all aspects of fairness, making this a challenging but necessary area of research [56] .  \nBias in ML systems can originate from dataset bias in the input data, or from algorithmic bias in the models themselves [50],[66],[4]. This study focuses on investigating algorithmic bias, aiming to address disparities introduced by ML models beyond those present in the dataset. Understanding and mitigating these biases is particularly important in healthcare, where biased systems can disproportionately harm underrepresented or historically marginalised groups. Pain detection is a critical task in clinical settings, aiding healthcare professionals in monitoring patients and making  \ninformed decisions. Automated pain detection systems, particularly those based on facial expressions, are promising because they are non-invasive, real-time, and practical [34] . Yet, existing research has primarily focused on improving accuracy without sufficient attention to fairness [49] . This gap is particularly concerning given documented gender disparities in healthcare. Studies show that societal and cultural norms influence how men and women perceive, express, and report pai","cbCaig1arkLcKeky","https://ap.wps.com/l/cbCaig1arkLcKeky","pdf",996902,1,9,"English","en",105,"# Abstract\n# I. Introduction\n## ML fairness and gender fairness\n## Sources of bias in ML systems\n## Motivation and contributions\n# II. Literature Review\n## A. Methods for Pain Detection","[{\"question\":\"Why is gender fairness important in machine learning-based pain detection?\",\"answer\":\"Gender fairness ensures male and female groups receive equal treatment and are equally likely to be correctly classified for pain. Without it, automated systems can perpetuate healthcare disparities.\"},{\"question\":\"What dataset and input modality are used in the study?\",\"answer\":\"The study trains on the UNBC-McMaster Shoulder Pain Expression Archive Database and uses only the visual modality of participants’ facial expressions.\"},{\"question\":\"Which models are compared, and what trade-off is observed?\",\"answer\":\"The study compares traditional ML methods (L SVM, RBF SVM) with deep vision models (CNN, ViT). While ViT achieves the highest accuracy, all models show gender-based biases, indicating a persistent accuracy–fairness trade-off.\"}]","Evaluating Gender Fairness of Machine Learning Algorithms for Pain Detection - Paper Review | PDF",1785816208,23,{"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},"evaluating-gender-fairness-of-machine-learning-algorithms-for-pain-detection-paper-review","",{"@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/evaluating-gender-fairness-of-machine-learning-algorithms-for-pain-detection-paper-review/123381/",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","2026-08-04",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},"Why is gender fairness important in machine learning-based pain detection?","Question",{"text":75,"@type":76},"Gender fairness ensures male and female groups receive equal treatment and are equally likely to be correctly classified for pain. Without it, automated systems can perpetuate healthcare disparities.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What dataset and input modality are used in the study?",{"text":80,"@type":76},"The study trains on the UNBC-McMaster Shoulder Pain Expression Archive Database and uses only the visual modality of participants’ facial expressions.",{"name":82,"@type":73,"acceptedAnswer":83},"Which models are compared, and what trade-off is observed?",{"text":84,"@type":76},"The study compares traditional ML methods (L SVM, RBF SVM) with deep vision models (CNN, ViT). While ViT achieves the highest accuracy, all models show gender-based biases, indicating a persistent accuracy–fairness trade-off.","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},[93,97,101,105,110,115,120,123,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]