[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-459431-105":3,"detail-sidebar-cat-0-en-105":80,"doc-detail-459431-en":130},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":73,"head_meta":75,"extra_data":77,"updated_unix":79},105,"en","addressing-ai-bias-in-mri-based-dementia-classification-among-hispanic-individuals","Addressing AI Bias in MRI-Based Dementia Classification Among Hispanic Individuals","","MRI-based dementia classification models trained mainly on non-Hispanic White (NHW) participants often generalize poorly to Hispanic populations, producing biased outcomes. This poster presentation compares dementia classification performance between NHW and Hispanic groups and assesses bias mitigation approaches to improve diagnostic fairness. MRI features were extracted without harmonization, then XGBoost models were evaluated with balanced accuracy and disparity-aware fairness metrics, supported by SHAP interpretation.",{"@graph":14,"@context":72},[15,34,55],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/healthcare/","Healthcare",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/addressing-ai-bias-in-mri-based-dementia-classification-among-hispanic-individuals/459431/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/addressing-ai-bias-in-mri-based-dementia-classification-among-hispanic-individuals/459431.png","ImageObject",300,407,{"name":42,"@type":43},"Genevieve","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-10-30","2026-09-30",true,{"@type":52,"interactionType":53,"userInteractionCount":22},"InteractionCounter",{"@type":54},"ViewAction",{"@type":56,"mainEntity":57},"FAQPage",[58,64,68],{"name":59,"@type":60,"acceptedAnswer":61},"Why is AI bias a concern in MRI-based dementia classification for Hispanic individuals?","Question",{"text":62,"@type":63},"Models trained predominantly on non-Hispanic White participants may not generalize well to Hispanic groups, leading to biased predictions and performance disparities.","Answer",{"name":65,"@type":60,"acceptedAnswer":66},"Which bias mitigation techniques were evaluated in the study?",{"text":67,"@type":63},"The study implemented correlation removal (CR) and Kernel Mean Matching (KMM) to reduce fairness and performance gaps between NHW and Hispanic populations.",{"name":69,"@type":60,"acceptedAnswer":70},"How were model performance and fairness assessed?",{"text":71,"@type":63},"XGBoost classifiers were evaluated using balanced accuracy and fairness metrics, including disparities in false positive rate (FPR) and false negative rate (FNR).","https://schema.org",{"og:url":32,"og:type":74,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":76,"canonical":32},"index,follow",{"doc_id":78,"site_id":7},459431,1790755911,{"code":4,"msg":81,"data":82},"success",[83,87,91,95,100,105,109,114,119,122,126],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":84,"show_sort_weight":85,"slug":86},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":88,"show_sort_weight":89,"slug":90},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":92,"show_sort_weight":93,"slug":94},"Exam",70,"exam",{"id":96,"doc_module":4,"doc_module_name":25,"category_name":97,"show_sort_weight":98,"slug":99},5,"Comic",60,"comic",{"id":101,"doc_module":4,"doc_module_name":25,"category_name":102,"show_sort_weight":103,"slug":104},6,"Technology",50,"technology",{"id":106,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":107,"slug":108},7,40,"healthcare",{"id":110,"doc_module":4,"doc_module_name":25,"category_name":111,"show_sort_weight":112,"slug":113},8,"Research & Report",30,"research-report",{"id":115,"doc_module":4,"doc_module_name":25,"category_name":116,"show_sort_weight":117,"slug":118},9,"Religion & Spirituality",20,"religion-spirituality",{"id":117,"doc_module":4,"doc_module_name":25,"category_name":120,"show_sort_weight":117,"slug":121},"World Cup","world-cup",{"id":123,"doc_module":4,"doc_module_name":25,"category_name":124,"show_sort_weight":123,"slug":125},10,"Lifestyle","lifestyle",{"id":127,"doc_module":4,"doc_module_name":25,"category_name":128,"show_sort_weight":96,"slug":129},19,"General","general",{"code":4,"msg":81,"data":131},{"doc_id":78,"user_id":132,"nickname":42,"user_avatar":133,"doc_module":4,"category_id":106,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":22,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":30,"language":139,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":12,"update_tm":79,"read_time":110,"preview_page_count":4},1374391974585,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","DOI: 10. 1002/alz70856_105856  \nBIOMARKERS  \nPOSTER PRESENTATION  \nNEUROIMAGING  \nAddressing AI Bias in MRI-Based Dementia Classification Among Hispanic Individuals  \nNgoc-Huynh Ho1  Sokratis Charisis 1  Sachintha Ransara Brandigampala2  Di Wang3  Susan R. Heckbert4  David M Martinez 1  Timothy M. Hughes5 Nicolas Honnorat 1  Derek B. Archer6, 7, 8  Timothy J. Hohman6, 9, 10, 11  Sudha Seshadri 12  Christos Davatzikos 13  Mohamad Habes 14  \n1 Glenn Biggs Institute for Alzheimer’s & Neurodegenerative Diseases, University of Texas Health Sciences Center at San Antonio, San Antonio, TX, USA  \n2 University of Texas Health Science Center at San Antonio, San Antonio, TX, USA  \n3 UT Health Science Center at San Antonio, San Antonio, TX, USA  \n4 University of Washington, Seattle, WA, USA  \n5Wake Forest University School of Medicine, Winston-Salem, NC, USA  \n6Vanderbilt Genetics Institute, Vanderbilt University Medical Center, Nashville, TN, USA  \n7Vanderbilt Memory & Alzheimer’s Center, Vanderbilt University Medical Center, Nashville, TN, USA  \n8 Department of Neurology, Vanderbilt Memory & Alzheimer’s Center, Vanderbilt University Medical Center, Nashville, TN, USA  \n9 Department of Neurology, Vanderbilt University Medical Center, Nashville, TN, USA  \n10Vanderbilt Brain Institute, Vanderbilt University Medical Center, Nashville, TN, USA  \n11Vanderbilt Memory and Alzheimer’s Center, Vanderbilt University School of Medicine, Nashville, TN, USA  \n12 Glenn Biggs Institute for Alzheimer’s and Neurodegenerative Diseases, University of Texas Health Science Center, San Antonio, TX, USA  \n13 Department of Radiology, University of Pennsylvania, Philadelphia, PA, USA  \n14 Glenn Biggs Institute for Alzheimer’s & Neurodegenerative Diseases, University of  \nAbstract  \nBackground: MRI based dementia classification using diagnostic tools trained predominantly on non-Hispanic White (NHW) participants often fail to generalize to other groups such as Hispanic, leading to biased outcomes. This study investigates disparities in dementia classification between NHW and Hispanic populations and evaluates bias mitigation techniques to improve diagnostic fairness.  \nMethod: MRI-based features without harmonization were extracted using MUSE for 2,541NHWand249Hispanic participantsfrom the NationalAlzheimer’s Coordinating Center for classifying normally cognitive and demented patients, with dementia prevalences of 35.97% and 45.78%, respectively. XGBoost classifiers were trained and assessed using balanced accuracy (BA) and fairness metrics, including false positive rate (FPR) and false negative rate (FNR) disparities. Bias mitigation techniques such as correlation removal (CR) and Kernel Mean Matching (KMM) were implemented. SHAP maps illustrated population-specific brain regions contributing to dementia predictions.  \nResult: KMM demonstrated the lowest disparity in BA between NHW and Hispanic populations (Figure 1), with differences of 1.5% and 6% when trained on Hispanic and NHW datasets, respectively. CR slightly enhanced overall model accuracy when trained on the combined dataset, achieving a 0.8% improvement over the baseline, and reduced disparities to 4%. KMM minimized FPR differences, achieving 0.8% when trained on NHW and 8.3% when trained on Hispanic data, and recorded the lowest FNR disparity of 11.2% for NHW training (Figure 2). CR achieved the smallest FPR differences when trained on all groups and the lowest FNR disparity when trained on Hispanic participants. SHAP visualizations(Figure3)revealed that the model identified  \nThis is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.  \n© 2025 The Alzheimer’s Association. Alzheimer’s & Dementia published by Wiley Periodicals LLC on behalf of Alzheimer’s Association.  \nAlzheimer’s Dement. 2025;21(Suppl. 2):e105856.  \n[https://doi.org/10.1002/alz70856_105856](ht","cbCaiuCjcWgDm27R","https://ap.wps.com/l/cbCaiuCjcWgDm27R","pdf",1315564,"English","# Abstract\n## Background\n## Method\n## Result\n## Conclusion","[{\"question\":\"Why is AI bias a concern in MRI-based dementia classification for Hispanic individuals?\",\"answer\":\"Models trained predominantly on non-Hispanic White participants may not generalize well to Hispanic groups, leading to biased predictions and performance disparities.\"},{\"question\":\"Which bias mitigation techniques were evaluated in the study?\",\"answer\":\"The study implemented correlation removal (CR) and Kernel Mean Matching (KMM) to reduce fairness and performance gaps between NHW and Hispanic populations.\"},{\"question\":\"How were model performance and fairness assessed?\",\"answer\":\"XGBoost classifiers were evaluated using balanced accuracy and fairness metrics, including disparities in false positive rate (FPR) and false negative rate (FNR).\"}]","Addressing AI Bias in MRI-Based Dementia Classification Among Hispanic Individuals | PDF"]