[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-121399-en":3,"doc-seo-121399-105":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},121399,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning Fairness for Depression Detection Using EEG Data","This paper evaluates machine learning fairness for depression detection using electroencephalogram (EEG) data, presenting the first such attempt in this setting. Experiments compare multiple deep learning architectures, including CNN, LSTM, and GRU, across three EEG datasets: Mumtaz, MODMA, and Rest. Five bias-mitigation strategies are applied in pre-, in-, and post-processing stages to study their effectiveness. Results show bias exists in both EEG datasets and depression-detection algorithms, and mitigation methods address bias differently across fairness measures.","MACHINE LEARNING FAIRNESS FOR DEPRESSION DETECTION USING EEG DATA  \nAngus Man Ho Kwok⋆ Jiaee Cheong⋆†‡ Sinan Kalkan† Hatice Gunes⋆⋆University of Cambridge †Middle East Technical University ‡The Alan Turing Institute  \nABSTRACT  \nThis paper presents the very first attempt to evaluate machine learning fairness for depression detection using electroencephalogram (EEG) data. We conduct experiments using different deep learning architectures such as Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks across three EEG datasets: Mumtaz, MODMA and Rest. We employ five different bias mitigation strategies atthe pre-, in-and post-processing stages and evaluate their effectiveness. Our experimental results show that bias exists in existing EEG datasets and algorithms for depression detection, and different bias mitigation methods address bias at different levels across different fairness measures.  \nIndex Terms— EEG, ML fairness, Depression Detection  \n1 Introduction  \nMajor depressive disorders (MDD) are becoming increasingly prevalent worldwide. Machine learning (ML), especially deep learning (DL) based methods, have been recently used in many research studies for depression detection with success [1, 2, 3] . In concurrence, ML bias is becoming a growing source of concern [4] . Bias can be understood as discrimination against individuals based on certain sensitive attributes such as age, race and gender [5, 6, 7] . Fairness conversely dictates that no individual or subgroup should be advantaged or disadvantaged based on their inherent characteristics. Given the high stakes involved in MHD analysis, it is crucial to investigate and mitigate the ML biases present. Research indicated the presence of ML bias across a variety of tasks ranging from automated video interviews [8] to image search [9] . However, none of the existing works have addressed ML fairness in MDD detection using EEG data.  \nOur contributions in this paper are as follows. First, our study is the first attempt to evaluate ML fairness for depression detection using electroencephalogram (EEG) data. None of the existing work on ML fairness for depression detection [10, 11, 12, 13] has investigated bias mitigation for depression detection using EEG data. Second, we study and compare the effectiveness of a diverse set of bias mitigation techniques to improve fairness in EEG-based depression detection. We show they have different effects on performance and fairness. We conduct our experiments using three different deep architectures across three datasets, Mumtaz,  \nMODMA and Rest. Throughout our experimentation, we attempt to address the following two research questions (RQs) . RQ 1: Is there bias within existing EEG data and ML algorithm for depression detection? RQ 2: How effective are existing bias mitigation methods at improving ML fairness for depression detection using EEG data? Our experimental results indicate that both data and algorithmic biases exist and that different bias mitigation provides different degree of effectiveness across different datasets and algorithms.  \n\n| Raw data |  | Training Data Preparation |  |  |  |  |  |  |  |  |  |  Modified  dataset |  |\n| --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- |\n|  |  | General data\u003Cbr>pre-processing |  |  | Original |  |  |  | Bias-mitigation (pre-processing) |  |  |  |  |\n|  |  |  |  |  | dataset |  |  |  |  |  |  |  |  |\n|  |  |  |  |  |  |  |  |  |  |  |  |  |  |\n|  |  |  |  |  |  |  |  |  |  |  |  |  |  |\n| Training dataset  |  |  | Model Training |  |  |  |  |  |  |  |  Trained model |  |  |\n|  |  |  | Training: Minimising loss function ℒ |  |  |  |  |  |  |  |  |  |  |\n|  |  |  | Training: Minimising modified loss ℒ ’ |  |  |  |  |  |  |  |  |  |  |\n|  |  |  |  |  |  |  |  |  |  |  |  |  |  |\n|  |  |  |  |  |  |  |  |  |  |  |  |  |  |\n| Raw |  |  |  | Test |  | Inference |  |  |  |  |  |  | Predicted\u003Cbr>labe","cbCaidyoA2Lpgz2c","https://ap.wps.com/l/cbCaidyoA2Lpgz2c","pdf",337034,1,5,"English","en",105,"# Introduction\n## Bias mitigation methods\n# Methodology\n## Bias mitigation methods","[{\"question\":\"Is bias present in EEG datasets and algorithms for depression detection?\",\"answer\":\"Yes. The experiments indicate both data bias and algorithmic bias exist for depression detection using EEG data.\"},{\"question\":\"Which deep learning architectures and datasets are evaluated?\",\"answer\":\"The study evaluates CNN, LSTM, and GRU architectures on three EEG datasets: Mumtaz, MODMA, and Rest.\"},{\"question\":\"How are bias mitigation strategies applied and what is their impact?\",\"answer\":\"Five strategies are used across pre-, in-, and post-processing stages. Different methods improve fairness to different degrees and operate at different levels, depending on dataset and algorithm.\"}]","Machine Learning Fairness for Depression Detection Using EEG Data | PDF",1785735498,13,{"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-fairness-for-depression-detection-using-eeg-data","",{"@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-fairness-for-depression-detection-using-eeg-data/121399/",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},"Is bias present in EEG datasets and algorithms for depression detection?","Question",{"text":75,"@type":76},"Yes. The experiments indicate both data bias and algorithmic bias exist for depression detection using EEG data.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which deep learning architectures and datasets are evaluated?",{"text":80,"@type":76},"The study evaluates CNN, LSTM, and GRU architectures on three EEG datasets: Mumtaz, MODMA, and Rest.",{"name":82,"@type":73,"acceptedAnswer":83},"How are bias mitigation strategies applied and what is their impact?",{"text":84,"@type":76},"Five strategies are used across pre-, in-, and post-processing stages. Different methods improve fairness to different degrees and operate at different levels, depending on dataset and algorithm.","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},[93,97,101,105,109,114,119,122,127,130,134],{"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":21,"doc_module":4,"doc_module_name":46,"category_name":106,"show_sort_weight":107,"slug":108},"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":46,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":46,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"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":21,"slug":137},19,"General","general"]