[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-449190-105":59,"doc-detail-449190-en":134},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","587-algorithmic-fairness-of-qprediction-cardiometabolic-risk-prediction-models","587 - Algorithmic Fairness of QPrediction Cardiometabolic Risk Prediction Models","","Evaluation of fairness in three established QPrediction family risk prediction models—QRISK3, QDiabetes, and QStroke—assessing 10-year cardiovascular disease, type 2 diabetes, and stroke risk estimates. Using UK Biobank data (502,131 participants), calibration was examined via observed cumulative incidence comparisons and inverse probability weighted survival Brier scores, while discrimination used inverse probability weighted overall and group-specific TPR, TNR, FPR, and FNR. Results showed systematic risk overprediction in validation cohorts; parity was not achieved for ethnicity, education, income, and deprivation in FNR/TNR, while immigration status largely met parity. Conclusions address implications for clinical deployment and shifting responsibility.",{"@graph":69,"@context":126},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/587-algorithmic-fairness-of-qprediction-cardiometabolic-risk-prediction-models/449190/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/587-algorithmic-fairness-of-qprediction-cardiometabolic-risk-prediction-models/449190.png","ImageObject",300,407,{"name":92,"@type":93},"Marglet","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-03","2026-09-30",true,{"@type":102,"interactionType":103,"userInteractionCount":8},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"Which QPrediction models are evaluated and what outcomes do they predict?","Question",{"text":112,"@type":113},"The study evaluates QRISK3, QDiabetes, and QStroke, predicting 10-year cardiovascular disease risk, type 2 diabetes risk, and stroke risk, respectively.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How were calibration and discrimination assessed in this study?",{"text":117,"@type":113},"Calibration used comparisons between predicted risks and observed cumulative incidence rates plus inverse probability weighted survival Brier scores. Discrimination used inverse probability weighted overall and group-specific rates (TPR, TNR, FPR, FNR).",{"name":119,"@type":110,"acceptedAnswer":120},"What were the key fairness-related findings across demographic subgroups?",{"text":121,"@type":113},"All models showed systematic overprediction. Prediction parity was not reached in ethnicity, education, average household income, and deprivation for FNR and TNR, while immigration status showed no major discrimination differences and parity was achieved.",{"name":123,"@type":110,"acceptedAnswer":124},"What do the conclusions suggest about model variables and real-world deployment?",{"text":125,"@type":113},"Including ethnicity and deprivation may improve calibration consistency across subgroups, but baseline-only measurement and changing social conditions can affect fairness over time. Deployments in clinical settings may inadvertently shift responsibility for health outcomes to patients.","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},449190,1791001903,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":8,"language":143,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":144,"faqs":145,"seo_title":146,"seo_description":67,"update_tm":147,"read_time":81},2336477982702,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","2nd World Congress on Migration, Ethnicity, Race & Health Abstract Book vi117  \nAbstract citation ID: ckaf180.324  \n587 Algorithmic Fairness of QPrediction Cardiometabolic Risk Prediction Models  \nInchuen Huynh1, Denise Utochkin1, Alexandros Katsiferis2, Tri  \nLong Nguyen1,3, Tibor V Varga1  \n1Department of Public Health, Copenhagen Health Complexity Center, University of Copenhagen, Copenhagen, Denmark  \n2Department of Public Health, Section for Health Data Science and AI, University of Copenhagen, Copenhagen, Denmark  \n3Section of Epidemiology, Department of Public Health, University of Copenhagen, Copenhagen, Denmark  \nEP1.4, e-Poster Terminal 1, September 4, 2025, 11:35-13:00  \nAims: To evaluate the fairness of three established risk prediction models belonging to the QPrediction family: QRISK3, QDiabetes, and QStroke, which estimate 10-year risks for cardiovascular disease, type 2 diabetes, and stroke, respectively.  \nMethods: We used data from the UK Biobank, a large-scale prospective cohort study comprising 502,131 participants. To assess calibration, the predicted risks were compared to the observed cumulative incidence rates and inverse probability weighted survival Brier scores were calculated as a summary metric of model calibration. To assess discrimination, we calculated inverse probability weighted overall and group-specific true positive, true negative, false positive, and false negative rates (TPR, TNR, FPR, FNR) . We compared the rates between subgroups of demographics and considered prediction parity when values were close to each other to a prespecified degree.  \nResults: After applying model-specific exclusion criteria, we analyzed data from 405,855 participants for QRISK3, 458,700 for QDiabetes, and 490,471 for QStroke. Overall, all models showed systematic overprediction of risks for the UK Biobank validation cohorts, with the degree of overprediction varying between the models. Prediction parity was not reached in FNR and TNR in terms of ethnicity, education level, average household income before taxation, Townsend deprivation score. For immigration status, there were no major differences in the discrimination metrics, and prediction parity was achieved. For QDiabetes, the trends were similar, apart from ethnicity, where the opposite was observed as for QRISK3 .  \nConclusions: Inclusion of ethnicity and deprivation in the models may have contributed to more consistent calibration across subgroups. Variables were measured only at baseline, while many social and economic conditions can shift over time. Although including social determinants of health can improve predictive performance, the models are typically deployed in a clinical setting to guide individual-level decision making, which can inadvertently shift responsibility for health outcomes onto patients.","cbCaih93vKyf9jtK","https://ap.wps.com/l/cbCaih93vKyf9jtK","pdf",35969,"English","# Aims\n# Methods\n# Results\n# Conclusions","[{\"question\":\"Which QPrediction models are evaluated and what outcomes do they predict?\",\"answer\":\"The study evaluates QRISK3, QDiabetes, and QStroke, predicting 10-year cardiovascular disease risk, type 2 diabetes risk, and stroke risk, respectively.\"},{\"question\":\"How were calibration and discrimination assessed in this study?\",\"answer\":\"Calibration used comparisons between predicted risks and observed cumulative incidence rates plus inverse probability weighted survival Brier scores. Discrimination used inverse probability weighted overall and group-specific rates (TPR, TNR, FPR, FNR).\"},{\"question\":\"What were the key fairness-related findings across demographic subgroups?\",\"answer\":\"All models showed systematic overprediction. Prediction parity was not reached in ethnicity, education, average household income, and deprivation for FNR and TNR, while immigration status showed no major discrimination differences and parity was achieved.\"},{\"question\":\"What do the conclusions suggest about model variables and real-world deployment?\",\"answer\":\"Including ethnicity and deprivation may improve calibration consistency across subgroups, but baseline-only measurement and changing social conditions can affect fairness over time. Deployments in clinical settings may inadvertently shift responsibility for health outcomes to patients.\"}]","587 - Algorithmic Fairness of QPrediction Cardiometabolic Risk Prediction Models | PDF",1790729502]