{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,4]],"date-time":"2026-09-04T03:43:32Z","timestamp":1788493412679,"version":"build-2803163510"},"reference-count":39,"publisher":"JMIR Publications Inc.","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JMIR Med Inform"],"abstract":"Abstract<\/jats:title>\n \n Background<\/jats:title>\n Artificial intelligence (AI) is increasingly applied to health care, yet concerns about fairness persist, particularly in relation to sociodemographic disparities. Previous studies suggest that socioeconomic status (SES) and sex may influence AI model performance, potentially affecting groups that are historically underserved or understudied.<\/jats:p>\n <\/jats:sec>\n \n Objective<\/jats:title>\n This study aimed to (1) assess algorithmic bias in AI-driven dementia prediction models based on SES and sex (biological sex), (2) compare the utility of an individual-level SES measure (the Housing-Based Socioeconomic Status [HOUSES] Index) versus an area-level measure (the Area Deprivation Index) for bias detection, and (3) evaluate the effectiveness of an oversampling technique (the Synthetic Minority Oversampling Technique for Nominal and Continuous features) for bias mitigation.<\/jats:p>\n <\/jats:sec>\n \n Methods<\/jats:title>\n This study used data from two population-based cohorts: the Mayo Clinic Study on Aging (n=3041) and the Rochester Epidemiology Project (n=19,572). Four AI models (random forest, logistic regression, support vector machine, and Na\u00efve Bayes) were trained using a 5-year observation window of structured electronic health record data to predict dementia onset within the subsequent 1-year window. Fairness and model performance were assessed using the balanced error rate (BER) across intersecting SES-sex subgroups. The Synthetic Minority Oversampling Technique for Nominal and Continuous features algorithm was applied to the training data to balance the representation of SES groups.<\/jats:p>\n <\/jats:sec>\n \n Results<\/jats:title>\n Across both cohorts, individuals with lower SES generally exhibited higher BERs (worse performance) than high SES groups, confirming the presence of bias. In the MCSA cohort, males with high SES, as indicated by the HOUSES Index, consistently exhibited the lowest BERs across all evaluated models. Balancing the training data based on a specific SES measure showed a trend toward reducing the BER disparity when evaluated using that same measure. However, this targeted improvement demonstrated nonuniversal benefits; in some cases, it exacerbated disparities when evaluated using other, unbalanced SES measures. This pattern suggests that fairness interventions are not universally beneficial across different definitions of the protected attribute. While the balancing approach improved fairness in model performance for lower SES groups, it often came at the cost of a slight reduction in overall model performance. However, an exception was observed in the MCSA cohort when balancing based on the HOUSES Index using logistic regression, support vector machine, and Na\u00efve Bayes, where the performances of both the high and low SES groups improved.<\/jats:p>\n <\/jats:sec>\n \n Conclusions<\/jats:title>\n This research highlights the importance of incorporating sociodemographic context into AI modeling in health care. The choice of SES measure may lead to different assessments of algorithmic bias. The HOUSES Index, as a validated individual-level SES measure, may be more effective for bias mitigation than area-level measures. Future AI development should integrate bias mitigation strategies to ensure models do not reinforce existing disparities in health outcomes.<\/jats:p>\n <\/jats:sec>","DOI":"10.2196\/80405","type":"journal-article","created":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T21:55:08Z","timestamp":1767822908000},"page":"e80405-e80405","source":"Crossref","is-referenced-by-count":1,"title":["Assessing the Impact of Sociodemographic Factors on Artificial Intelligence Models in Predicting Dementia: Retrospective Cohort Study"],"prefix":"10.2196","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9230-3209","authenticated-orcid":false,"given":"Xingyi","family":"Liu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0075-9802","authenticated-orcid":false,"given":"Muskan","family":"Garg","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8328-136X","authenticated-orcid":false,"given":"Maria","family":"Vassilaki","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9789-8544","authenticated-orcid":false,"given":"Jennifer","family":"St Sauver","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8178-6601","authenticated-orcid":false,"given":"Ronald C","family":"Petersen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4871-0429","authenticated-orcid":false,"given":"Momin M","family":"Malik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8938-2997","authenticated-orcid":false,"given":"Chung Il","family":"Wi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2112-4240","authenticated-orcid":false,"given":"Young J","family":"Juhn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8256-2602","authenticated-orcid":false,"given":"Sunghwan","family":"Sohn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1010","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"issue":"5","key":"R1","doi-asserted-by":"publisher","first-page":"3708","DOI":"10.1002\/alz.13809","article-title":"2024 Alzheimer\u2019s disease facts and figures","volume":"20","journal-title":"Alzheimers Dement"},{"key":"R2","unstructured":"Sage growth partners. The state of healthcare automation: urgent need, growing awareness and tremendous potential. 2021. URL: https:\/\/go.sage-growth.com\/state-of-healthcare-automation [Accessed 04-02-2026]"},{"key":"R3","unstructured":"National trends in hospital and physician adoption of electronic health records. ASTP - Assistant Secretary for Technology Policy. 2025. URL: https:\/\/www.healthit.gov\/data\/quickstats\/national-trends-hospital-and-physician-adoption-electronic-health-records [Accessed 22-01-2026]"},{"key":"R4","unstructured":"Artificial intelligence-enabled medical devices. US Food and Drug Administration (FDA). 2024. URL: https:\/\/www.fda.gov\/medical-devices\/software-medical-device-samd\/artificial-intelligence-and-machine-learning-aiml-enabled-medical-devices [Accessed 22-01-2026]"},{"issue":"1","key":"R5","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41591-020-01192-7","article-title":"An algorithmic approach to reducing unexplained pain disparities in underserved populations","volume":"27","author":"Pierson","journal-title":"Nat Med"},{"key":"R6","unstructured":"Steinwachs DM Stratton K Kwan LY . Accounting for social risk factors in medicare payment. National Academies Press; 2017. URL: https:\/\/www.nationalacademies.org\/read\/23635\/chapter\/1 [Accessed 22-01-2026]"},{"issue":"6464","key":"R7","doi-asserted-by":"publisher","first-page":"447","DOI":"10.1126\/science.aax2342","article-title":"Dissecting racial bias in an algorithm used to manage the health of populations","volume":"366","author":"Obermeyer","journal-title":"Science"},{"issue":"8","key":"R8","first-page":"666","volume":"94","author":"Nelson","journal-title":"J Natl Med Assoc"},{"issue":"14","key":"R9","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1001\/jama.2017.1964","article-title":"Vital directions for health and health care: priorities from a National Academy of Medicine initiative","volume":"317","author":"Dzau","journal-title":"JAMA"},{"issue":"9","key":"R10","doi-asserted-by":"publisher","first-page":"874","DOI":"10.1056\/NEJMms2004740","article-title":"Hidden in plain sight\u2014reconsidering the use of race correction in clinical algorithms","volume":"383","author":"Vyas","journal-title":"N Engl J Med"},{"issue":"9","key":"R11","doi-asserted-by":"publisher","first-page":"1608","DOI":"10.2105\/AJPH.2006.102525","article-title":"Approaching health disparities from a population perspective: the National Institutes of Health Centers for Population Health and Health Disparities","volume":"98","author":"Warnecke","journal-title":"Am J Public Health"},{"issue":"11","key":"R12","doi-asserted-by":"publisher","first-page":"1498","DOI":"10.1001\/jamainternmed.2018.4481","article-title":"Assessment of the effect of adjustment for patient characteristics on hospital readmission rates: implications for pay for performance","volume":"178","author":"Roberts","journal-title":"JAMA Intern Med"},{"issue":"4","key":"R13","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1001\/jamapediatrics.2015.4440","article-title":"Association of social determinants with children\u2019s hospitals\u2019 preventable readmissions performance","volume":"170","author":"Sills","journal-title":"JAMA Pediatr"},{"issue":"8","key":"R14","doi-asserted-by":"publisher","first-page":"717","DOI":"10.1097\/00005650-200208000-00011","article-title":"Effect of patient socioeconomic status on physician profiles for prevention, disease management, and diagnostic testing costs","volume":"40","author":"Franks","journal-title":"Med Care"},{"issue":"6","key":"R15","doi-asserted-by":"publisher","first-page":"418","DOI":"10.7326\/M17-0691","article-title":"Holding providers accountable for health care outcomes","volume":"167","author":"Baker","journal-title":"Ann Intern Med"},{"issue":"1","key":"R16","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1370\/afm.749","article-title":"Influence of patients\u2019 socioeconomic status on clinical management decisions: a qualitative study","volume":"6","author":"Bernheim","journal-title":"Ann Fam Med"},{"issue":"6","key":"R17","doi-asserted-by":"publisher","first-page":"575","DOI":"10.1056\/NEJMsa040609","article-title":"Primary care physicians who treat Blacks and Whites","volume":"351","author":"Bach","journal-title":"N Engl J Med"},{"issue":"3","key":"R18","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1001\/jama.2014.7204","article-title":"Quality reporting that addresses disparities in health care","volume":"312","author":"Jha","journal-title":"JAMA"},{"issue":"6493","key":"R19","doi-asserted-by":"publisher","DOI":"10.1126\/science.aax9553","article-title":"Social determinants of health and survival in humans and other animals","volume":"368","author":"Snyder-Mackler","journal-title":"Science"},{"issue":"2","key":"R20","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1377\/hlthaff.21.2.60","article-title":"Socioeconomic disparities in health: pathways and policies","volume":"21","author":"Adler","journal-title":"Health Aff (Millwood)"},{"issue":"2","key":"R21","doi-asserted-by":"publisher","first-page":"010318","DOI":"10.7189\/jogh.09.020318","article-title":"Artificial intelligence and algorithmic bias: implications for health systems","volume":"9","author":"Panch","journal-title":"J Glob Health"},{"issue":"6","key":"R22","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pdig.0000278","article-title":"Bias in artificial intelligence algorithms and recommendations for mitigation","volume":"2","author":"Nazer","journal-title":"PLOS Digit Health"},{"issue":"7","key":"R23","doi-asserted-by":"publisher","first-page":"1142","DOI":"10.1093\/jamia\/ocac052","article-title":"Assessing socioeconomic bias in machine learning algorithms in health care: a case study of the HOUSES index","volume":"29","author":"Juhn","journal-title":"J Am Med Inform Assoc"},{"key":"R24","doi-asserted-by":"crossref","unstructured":"Cadena-Hernandez AG Trejo-Castro AI Celaya-Padilla JM Tamez-Pena J Martinez-Torteya A . Longitudinal gender-specific differences in the conversion from mild cognitive impairment to Alzheimer\u2019s disease. Presented at: 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI); Mar 4-7, 2018; Las Vegas, NV, USA. [doi: 10.1109\/BHI.2018.8333404]","DOI":"10.1109\/BHI.2018.8333404"},{"issue":"3","key":"R25","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1007\/s40708-016-0035-5","article-title":"Clusters of male and female Alzheimer\u2019s disease patients in the Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI) database","volume":"3","author":"Gamberger","journal-title":"Brain Inform"},{"key":"R26","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2016.12.004","article-title":"Devising an interpretable calibrated scale to quantitatively assess the dementia stage of subjects with Alzheimer\u2019s disease: a machine learning approach","volume":"6","author":"Aditya","journal-title":"Informatics in Medicine Unlocked"},{"issue":"1","key":"R27","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1186\/s12911-021-01627-2","article-title":"Factors associated with access to assistive technology and telecare in home-dwelling people with dementia: baseline data from the LIVE@Home.Path trial","volume":"21","author":"Puaschitz","journal-title":"BMC Med Inform Decis Mak"},{"issue":"1","key":"R28","doi-asserted-by":"publisher","DOI":"10.1186\/s12911-023-02244-x","article-title":"Dementia prediction in the general population using clinically accessible variables: a proof-of-concept study using machine learning. The AGES-Reykjavik study","volume":"23","author":"Twait","journal-title":"BMC Med Inform Decis Mak"},{"key":"R29","doi-asserted-by":"crossref","unstructured":"Liu Z Garg M Fu S et al. Harnessing transfer learning for dementia prediction: leveraging sex-different mild cognitive impairment prognosis. Presented at: 2023 IEEE International Conference on Bioinformatics and Biomedicine (BIBM); Dec 5-8, 2023; Istanbul, Turkiye. [doi: 10.1109\/BIBM58861.2023.10385516]","DOI":"10.1109\/BIBM58861.2023.10385516"},{"key":"R30","doi-asserted-by":"crossref","unstructured":"Wu H Sylolypavan A Wang M Wild S . Quantifying health inequalities induced by data and AI models. Presented at: Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence; Jul 23-29, 2022; Vienna, Austria. 2022.[doi: 10.24963\/ijcai.2022\/721]","DOI":"10.24963\/ijcai.2022\/721"},{"issue":"1","key":"R31","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1159\/000115751","article-title":"The Mayo Clinic Study of Aging: design and sampling, participation, baseline measures and sample characteristics","volume":"30","author":"Roberts","journal-title":"Neuroepidemiology"},{"issue":"3","key":"R32","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1111\/j.1365-2796.2004.01388.x","article-title":"Mild cognitive impairment as a diagnostic entity","volume":"256","author":"Petersen","journal-title":"J Intern Med"},{"issue":"8","key":"R33","doi-asserted-by":"publisher","first-page":"1228","DOI":"10.1176\/ajp.152.8.1228","article-title":"Diagnostic and Statistical Manual of Mental Disorders, 4th ed. (DSM-IV)","volume":"152","author":"Guze","journal-title":"AJP"},{"issue":"12","key":"R34","doi-asserted-by":"publisher","first-page":"1202","DOI":"10.1016\/j.mayocp.2012.08.012","article-title":"History of the Rochester Epidemiology Project: half a century of medical records linkage in a US population","volume":"87","author":"Rocca","journal-title":"Mayo Clin Proc"},{"issue":"26","key":"R35","doi-asserted-by":"publisher","first-page":"2456","DOI":"10.1056\/NEJMp1802313","article-title":"Making neighborhood-disadvantage metrics accessible - the Neighborhood Atlas","volume":"378","author":"Kind","journal-title":"N Engl J Med"},{"issue":"5","key":"R36","doi-asserted-by":"publisher","first-page":"933","DOI":"10.1007\/s11524-011-9572-7","article-title":"Development and initial testing of a new socioeconomic status measure based on housing data","volume":"88","author":"Juhn","journal-title":"J Urban Health"},{"issue":"7 Suppl 1","key":"R37","doi-asserted-by":"publisher","first-page":"S44","DOI":"10.1097\/MLR.0b013e3181a23e3a","article-title":"The medical expenditure panel survey: a national information resource to support healthcare cost research and inform policy and practice","volume":"47","author":"Cohen","journal-title":"Med Care"},{"key":"R38","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over\u2011sampling technique","volume":"16","author":"Chawla","journal-title":"J Artif Intell Res"},{"issue":"2","key":"R39","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.mayocp.2011.11.009","article-title":"Generalizability of epidemiological findings and public health decisions: an illustration from the Rochester Epidemiology Project","volume":"87","author":"St Sauver","journal-title":"Mayo Clin Proc"}],"container-title":["JMIR Medical Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e80405","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T18:13:53Z","timestamp":1782843233000},"score":1,"resource":{"primary":{"URL":"https:\/\/medinform.jmir.org\/2026\/1\/e80405"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,17]]},"references-count":39,"URL":"https:\/\/doi.org\/10.2196\/80405","relation":{},"ISSN":["2291-9694"],"issn-type":[{"value":"2291-9694","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,17]]},"article-number":"v14i5e80405"}}