{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,26]],"date-time":"2026-10-26T18:57:04Z","timestamp":1793041024494,"version":"4.5.0"},"reference-count":51,"publisher":"American Medical Association (AMA)","issue":"11","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JAMA Netw Open"],"abstract":"Importance<\/jats:title>Predictive models using machine learning techniques have potential to improve early detection and management of Alzheimer disease (AD). However, these models potentially have biases and may perpetuate or exacerbate existing disparities.<\/jats:p><\/jats:sec>Objective<\/jats:title>To characterize the algorithmic fairness of longitudinal prediction models for AD progression.<\/jats:p><\/jats:sec>Design, Setting, and Participants<\/jats:title>This prognostic study investigated the algorithmic fairness of logistic regression, support vector machines, and recurrent neural networks for predicting progression to mild cognitive impairment (MCI) and AD using data from participants in the Alzheimer Disease Neuroimaging Initiative evaluated at 57 sites in the US and Canada. Participants aged 54 to 91 years who contributed data on at least 2 visits between September 2005 and May 2017 were included. Data were analyzed in October 2022.<\/jats:p><\/jats:sec>Exposures<\/jats:title>Fairness was quantified across sex, ethnicity, and race groups. Neuropsychological test scores, anatomical features from T1 magnetic resonance imaging, measures extracted from positron emission tomography, and cerebrospinal fluid biomarkers were included as predictors.<\/jats:p><\/jats:sec>Main Outcomes and Measures<\/jats:title>Outcome measures quantified fairness of prediction models (logistic regression [LR], support vector machine [SVM], and recurrent neural network [RNN] models), including equal opportunity, equalized odds, and demographic parity. Specifically, if the model exhibited equal sensitivity for all groups, it aligned with the principle of equal opportunity, indicating fairness in predictive performance.<\/jats:p><\/jats:sec>Results<\/jats:title>A total of 1730 participants in the cohort (mean [SD] age, 73.81 [6.92] years; 776 females [44.9%]; 69 Hispanic [4.0%] and 1661 non-Hispanic [96.0%]; 29 Asian [1.7%], 77 Black [4.5%], 1599 White [92.4%], and 25 other race [1.4%]) were included. Sensitivity for predicting progression to MCI and AD was lower for Hispanic participants compared with non-Hispanic participants; the difference (SD) in true positive rate ranged from 20.9% (5.5%) for the RNN model to 27.8% (9.8%) for the SVM model in MCI and 24.1% (5.4%) for the RNN model to 48.2% (17.3%) for the LR model in AD. Sensitivity was similarly lower for Black and Asian participants compared with non-Hispanic White participants; for example, the difference (SD) in AD true positive rate was 14.5% (51.6%) in the LR model, 12.3% (35.1%) in the SVM model, and 28.4% (16.8%) in the RNN model for Black vs White participants, and the difference (SD) in MCI true positive rate was 25.6% (13.1%) in the LR model, 24.3% (13.1%) in the SVM model, and 6.8% (18.7%) in the RNN model for Asian vs White participants. Models generally satisfied metrics of fairness with respect to sex, with no significant differences by group, except for cognitively normal (CN)\u2013MCI and MCI-AD transitions (eg, an absolute increase [SD] in the true positive rate of CN-MCI transitions of 10.3% [27.8%] for the LR model).<\/jats:p><\/jats:sec>Conclusions and Relevance<\/jats:title>In this study, models were accurate in aggregate but failed to satisfy fairness metrics. These findings suggest that fairness should be considered in the development and use of machine learning models for AD progression.<\/jats:p><\/jats:sec>","DOI":"10.1001\/jamanetworkopen.2023.42203","type":"journal-article","created":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T16:33:56Z","timestamp":1699374836000},"page":"e2342203","source":"Crossref","is-referenced-by-count":52,"title":["Algorithmic Fairness of Machine Learning Models for Alzheimer Disease Progression"],"prefix":"10.1001","volume":"6","author":[{"given":"Chenxi","family":"Yuan","sequence":"first","affiliation":[{"name":"Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia"},{"name":"Penn Statistics in Imaging and Visualization Endeavor, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristin A.","family":"Linn","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia"},{"name":"Penn Statistics in Imaging and Visualization Endeavor, Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rebecca A.","family":"Hubbard","sequence":"additional","affiliation":[{"name":"Department of Biostatistics, Epidemiology, and Informatics, Perelman School of Medicine, University of Pennsylvania, Philadelphia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10","published-online":{"date-parts":[[2023,11,7]]},"reference":[{"key":"zoi231221r1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ebiom.2022.104250","article-title":"Algorithmic fairness in computational medicine.","volume":"84","author":"Xu","year":"2022","journal-title":"EBioMedicine"},{"issue":"1","key":"zoi231221r2","doi-asserted-by":"publisher","first-page":"229","DOI":"10.1016\/j.neuroimage.2012.04.056","article-title":"Combining MRI and CSF measures for classification of Alzheimer\u2019s disease and prediction of mild cognitive impairment conversion.","volume":"62","author":"Westman","year":"2012","journal-title":"Neuroimage"},{"key":"zoi231221r3","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1016\/j.neuroimage.2019.01.031","article-title":"A parameter-efficient deep learning approach to predict conversion from mild cognitive impairment to Alzheimer\u2019s disease.","volume":"189","author":"Spasov","year":"2019","journal-title":"Neuroimage"},{"key":"zoi231221r4","doi-asserted-by":"publisher","first-page":"180","DOI":"10.1016\/j.neurobiolaging.2016.07.005","article-title":"Longitudinal clinical score prediction in Alzheimer\u2019s disease with soft-split sparse regression based random forest.","volume":"46","author":"Huang","year":"2016","journal-title":"Neurobiol Aging"},{"issue":"OCT","key":"zoi231221r5","doi-asserted-by":"publisher","first-page":"55","DOI":"10.3389\/fnagi.2013.00055","article-title":"Biomarker-based prediction of progression in MCI: Comparison of AD signature and hippocampal volume with spinal fluid amyloid-\u00df and tau.","volume":"5","author":"Dickerson","year":"2013","journal-title":"Front Aging Neurosci"},{"issue":"3","key":"zoi231221r6","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1002\/alz.v16.3","article-title":"Predicting sporadic Alzheimer\u2019s disease progression via inherited Alzheimer\u2019s disease-informed machine-learning.","volume":"16","author":"Franzmeier","year":"2020","journal-title":"Alzheimers Dement"},{"issue":"4","key":"zoi231221r7","doi-asserted-by":"publisher","first-page":"1401","DOI":"10.3233\/JAD-180711","article-title":"Metabolomics analyses of saliva detect novel biomarkers of Alzheimer\u2019s disease.","volume":"65","author":"Huan","year":"2018","journal-title":"J Alzheimers Dis"},{"issue":"1","key":"zoi231221r8","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.dadm.2017.07.006","article-title":"Blood-based metabolic signatures in Alzheimer\u2019s disease.","volume":"8","author":"de Leeuw","year":"2017","journal-title":"Alzheimers Dement (Amst)"},{"issue":"2","key":"zoi231221r9","doi-asserted-by":"publisher","first-page":"895","DOI":"10.1016\/j.neuroimage.2011.09.069","article-title":"Multi-modal multi-task learning for joint prediction of multiple regression and classification variables in Alzheimer\u2019s disease.","volume":"59","author":"Zhang","year":"2012","journal-title":"Neuroimage"},{"key":"zoi231221r10","doi-asserted-by":"publisher","first-page":"232","DOI":"10.1016\/j.neuroimage.2015.02.037","article-title":"Gaussian process classification of Alzheimer\u2019s disease and mild cognitive impairment from resting-state fMRI.","volume":"112","author":"Challis","year":"2015","journal-title":"Neuroimage"},{"issue":"5795","key":"zoi231221r11","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1126\/science.1132939","article-title":"The connectivity map: using gene-expression signatures to connect small molecules, genes, and disease.","volume":"313","author":"Lamb","year":"2006","journal-title":"Science"},{"issue":"2","key":"zoi231221r12","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1001\/jamaneurol.2016.3783","article-title":"Sex and race differences in the association between statin use and the incidence of Alzheimer disease.","volume":"74","author":"Zissimopoulos","year":"2017","journal-title":"JAMA Neurol"},{"issue":"1","key":"zoi231221r14","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1038\/s41591-019-0649-2","article-title":"Treating health disparities with artificial intelligence.","volume":"26","author":"Chen","year":"2020","journal-title":"Nat Med"},{"issue":"11","key":"zoi231221r15","doi-asserted-by":"publisher","first-page":"1247","DOI":"10.1001\/jamadermatol.2018.2348","article-title":"Machine learning and health care disparities in dermatology.","volume":"154","author":"Adamson","year":"2018","journal-title":"JAMA Dermatol"},{"issue":"7714","key":"zoi231221r16","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1038\/d41586-018-05707-8","article-title":"AI can be sexist and racist\u2014it\u2019s time to make it fair.","volume":"559","author":"Zou","year":"2018","journal-title":"Nature"},{"issue":"6","key":"zoi231221r17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457607","article-title":"A Survey on bias and fairness in machine learning.","volume":"54","author":"Mehrabi","year":"2021","journal-title":"ACM Comput Surv"},{"issue":"9","key":"zoi231221r19","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.3390\/e23091165","article-title":"The problem of fairness in synthetic healthcare data.","volume":"23","author":"Bhanot","year":"2021","journal-title":"Entropy (Basel)"},{"issue":"4","key":"zoi231221r20","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1001\/jama.2022.23867","article-title":"Prevention of bias and discrimination in clinical practice algorithms.","volume":"329","author":"Shachar","year":"2023","journal-title":"JAMA"},{"issue":"8","key":"zoi231221r21","doi-asserted-by":"publisher","first-page":"918","DOI":"10.1038\/s41593-020-0658-y","article-title":"The extent and drivers of gender imbalance in neuroscience reference lists.","volume":"23","author":"Dworkin","year":"2020","journal-title":"Nat Neurosci"},{"issue":"1","key":"zoi231221r22","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41591-021-01614-0","article-title":"AI in health and medicine.","volume":"28","author":"Rajpurkar","year":"2022","journal-title":"Nat Med"},{"issue":"12","key":"zoi231221r23","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1038\/s41551-022-00914-1","article-title":"Self-supervised learning in medicine and healthcare.","volume":"6","author":"Krishnan","year":"2022","journal-title":"Nat Biomed Eng"},{"key":"zoi231221r24","doi-asserted-by":"publisher","DOI":"10.1002\/alz.v18.S6","article-title":"Kambeitz algorithmic fairness in biomarker-based machine learning models to predict Alzheimer\u2019s dementia in individuals with mild cognitive impairment.","volume":"18","author":"Sahin","year":"2022","journal-title":"Alzheimers Dement"},{"issue":"6464","key":"zoi231221r25","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","year":"2019","journal-title":"Science"},{"issue":"12","key":"zoi231221r26","doi-asserted-by":"publisher","first-page":"2176","DOI":"10.1038\/s41591-021-01595-0","article-title":"Underdiagnosis bias of artificial intelligence algorithms applied to chest radiographs in under-served patient populations.","volume":"27","author":"Seyyed-Kalantari","year":"2021","journal-title":"Nat Med"},{"issue":"23","key":"zoi231221r27","doi-asserted-by":"publisher","first-page":"12592","DOI":"10.1073\/pnas.1919012117","article-title":"Gender imbalance in medical imaging datasets produces biased classifiers for computer-aided diagnosis.","volume":"117","author":"Larrazabal","year":"2020","journal-title":"Proc Natl Acad Sci U S A"},{"key":"zoi231221r28","doi-asserted-by":"publisher","first-page":"11149","DOI":"10.1007\/s10462-023-10415-5","article-title":"Trustworthy artificial intelligence in Alzheimer\u2019s disease: state of the art, opportunities, and challenges.","volume":"56","author":"El-Sappagh","year":"2023","journal-title":"Artif Intell Rev"},{"key":"zoi231221r30","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.neucom.2022.09.009","article-title":"Automatic detection of Alzheimer\u2019s disease progression: an efficient information fusion approach with heterogeneous ensemble classifiers.","volume":"512","author":"El-Sappagh","year":"2022","journal-title":"Neurocomputing (Amst)"},{"issue":"4","key":"zoi231221r31","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1002\/jmri.v27:4","article-title":"The Alzheimer\u2019s Disease Neuroimaging Initiative (ADNI): MRI methods.","volume":"27","author":"Jack","year":"2008","journal-title":"J Magn Reson Imaging"},{"issue":"9","key":"zoi231221r33","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","year":"2020","journal-title":"N Engl J Med"},{"issue":"12","key":"zoi231221r35","doi-asserted-by":"publisher","first-page":"866","DOI":"10.7326\/M18-1990","article-title":"Ensuring fairness in machine learning to advance health equity.","volume":"169","author":"Rajkomar","year":"2018","journal-title":"Ann Intern Med"},{"key":"zoi231221r36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2020.117203","article-title":"Predicting Alzheimer\u2019s disease progression using deep recurrent neural networks.","volume":"222","author":"Nguyen","year":"2020","journal-title":"Neuroimage"},{"issue":"8","key":"zoi231221r37","doi-asserted-by":"publisher","first-page":"903","DOI":"10.1016\/j.jalz.2016.12.015","article-title":"Predicting progression to dementia in persons with mild cognitive impairment using cerebrospinal fluid markers.","volume":"13","author":"Handels","year":"2017","journal-title":"Alzheimers Dement"},{"key":"zoi231221r38","doi-asserted-by":"publisher","first-page":"220","DOI":"10.3389\/fnagi.2019.00220","article-title":"Deep learning in Alzheimer\u2019s disease: diagnostic classification and prognostic prediction using neuroimaging data.","volume":"11","author":"Jo","year":"2019","journal-title":"Front Aging Neurosci"},{"issue":"1","key":"zoi231221r39","doi-asserted-by":"publisher","first-page":"483","DOI":"10.1016\/j.trci.2019.07.001","article-title":"Forecasting the progression of Alzheimer\u2019s disease using neural networks and a novel preprocessing algorithm.","volume":"5","author":"Albright","year":"2019","journal-title":"Alzheimers Dement (N Y)"},{"key":"zoi231221r40","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.media.2019.01.004","article-title":"Training recurrent neural networks robust to incomplete data: application to Alzheimer\u2019s disease progression modeling.","volume":"53","author":"Mehdipour Ghazi","year":"2019","journal-title":"Med Image Anal"},{"key":"zoi231221r41","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.neuroimage.2018.08.040","article-title":"Using high-dimensional machine learning methods to estimate an anatomical risk factor for Alzheimer\u2019s disease across imaging databases.","volume":"183","author":"Casanova","year":"2018","journal-title":"Neuroimage"},{"key":"zoi231221r43","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2020.561802","article-title":"Addressing fairness, bias, and appropriate use of artificial intelligence and machine learning in global health.","volume":"3","author":"Fletcher","year":"2021","journal-title":"Front Artif Intell"},{"issue":"8","key":"zoi231221r44","doi-asserted-by":"publisher","first-page":"1461","DOI":"10.1002\/alz.v18.8","article-title":"Black and White individuals differ in dementia prevalence, risk factors, and symptomatic presentation.","volume":"18","author":"Lennon","year":"2022","journal-title":"Alzheimers Dement"},{"issue":"3","key":"zoi231221r45","doi-asserted-by":"publisher","first-page":"275","DOI":"10.1001\/jamaneurol.2020.4471","article-title":"Trends in relative incidence and prevalence of dementia across non-Hispanic Black and White individuals in the United States, 2000-2016.","volume":"78","author":"Power","year":"2021","journal-title":"JAMA Neurol"},{"key":"zoi231221r46","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2020.103621","article-title":"An empirical characterization of fair machine learning for clinical risk prediction.","volume":"113","author":"Pfohl","year":"2021","journal-title":"J Biomed Inform"},{"key":"zoi231221r47","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1146\/biodatasci.2021.4.issue-1","article-title":"Ethical machine learning in healthcare.","volume":"4","author":"Chen","year":"2021","journal-title":"Annu Rev Biomed Data Sci"},{"issue":"1","key":"zoi231221r49","doi-asserted-by":"publisher","DOI":"10.1002\/dad2.v12.1","article-title":"Predicting amyloid status using self-report information from an online research and recruitment registry: The Brain Health Registry.","volume":"12","author":"Ashford","year":"2020","journal-title":"Alzheimers Dement (Amst)"},{"issue":"2","key":"zoi231221r50","doi-asserted-by":"publisher","first-page":"691","DOI":"10.3233\/JAD-200108","article-title":"Progression of Alzheimer\u2019s disease by self-reported cancer history in the Alzheimer\u2019s Disease Neuroimaging Initiative.","volume":"76","author":"Fowler","year":"2020","journal-title":"J Alzheimers Dis"},{"issue":"24","key":"zoi231221r51","doi-asserted-by":"publisher","first-page":"e2454","DOI":"10.1212\/WNL.0000000000207338","article-title":"Association of the informant-reported memory decline with cognitive and brain deterioration through the Alzheimer clinical continuum.","volume":"100","author":"Kuhn","year":"2023","journal-title":"Neurology"},{"key":"zoi231221r13","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1145\/3351095.3372828","volume-title":"FAT* \u201920: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","author":"Raghavan","year":"2020"},{"key":"zoi231221r18","doi-asserted-by":"crossref","first-page":"339","DOI":"10.1145\/3287560.3287594","volume-title":"FAT* \u201819: Proceedings of the Conference on Fairness, Accountability, and Transparency. Association for Computing Machinery","author":"Chen","year":"2019"},{"key":"zoi231221r29","doi-asserted-by":"crossref","first-page":"1062","DOI":"10.1145\/3593013.3594063","volume-title":"FAccT \u201823: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency","author":"Petti","year":"2023"},{"key":"zoi231221r34","first-page":"1","volume-title":"FairWare '18: Proceedings of the International Workshop on Software Fairness","author":"Verma","year":"2018"},{"key":"zoi231221r42","first-page":"16339","volume-title":"Advances in Neural Information Processing Systems. Vol 33","author":"Bayle","year":"2020"},{"key":"zoi231221r48","doi-asserted-by":"crossref","first-page":"4691","DOI":"10.24963\/ijcai.2017\/654","volume-title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","author":"Danks","year":"2017"},{"key":"zoi231221r32","unstructured":"Marinescu? RV, Oxtoby? NP, Young? AL, . TADPOLE challenge: prediction of longitudinal evolution in Alzheimer\u2019s disease.? arXiv. Preprint posted online May 10, 2018. doi:10.48550\/arXiv.1805.03909"}],"container-title":["JAMA Network Open"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/articlepdf\/2811461\/yuan_2023_oi_231221_1698415358.87588.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,7]],"date-time":"2023-11-07T16:34:04Z","timestamp":1699374844000},"score":1,"resource":{"primary":{"URL":"https:\/\/jamanetwork.com\/journals\/jamanetworkopen\/fullarticle\/2811461"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,7]]},"references-count":51,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,11,1]]}},"URL":"https:\/\/doi.org\/10.1001\/jamanetworkopen.2023.42203","relation":{},"ISSN":["2574-3805"],"issn-type":[{"value":"2574-3805","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,7]]}}}