{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T15:46:54Z","timestamp":1782143214827,"version":"3.54.5"},"reference-count":30,"publisher":"BMJ","issue":"1","license":[{"start":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T00:00:00Z","timestamp":1782086400000},"content-version":"unspecified","delay-in-days":21,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"name":"Framingham Heart Study Brain Aging Program","award":["U19-AG068753"],"award-info":[{"award-number":["U19-AG068753"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMS\/NIGMS-2347698"],"award-info":[{"award-number":["DMS\/NIGMS-2347698"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NIH\/National Institute on Aging","award":["R01-AG080810"],"award-info":[{"award-number":["R01-AG080810"]}]},{"name":"NIH\/National Institute on Aging","award":["U01-AG072577"],"award-info":[{"award-number":["U01-AG072577"]}]},{"name":"NIH\/National Institute on Aging","award":["U19-AG068753"],"award-info":[{"award-number":["U19-AG068753"]}]}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["BMJ Health Care Inform"],"accepted":{"date-parts":[[2026,5,14]]},"published-print":{"date-parts":[[2026,6]]},"abstract":"<jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>Social determinants of health (SDOH) may improve Alzheimer\u2019s disease (AD) risk prediction by capturing upstream contextual risk beyond routinely measured clinical variables. We aimed to develop and validate an accurate, interpretable machine-learning pipeline for AD risk prediction in UK Biobank using routinely collected data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using data from 13\u2009076 participants in the UK Biobank, we developed an automated machine-learning pipeline for AD risk prediction with feature selection and a C5.0 boosted-tree classifier. Data were split into training, development and test sets (7:2:1); missing values were imputed in the training data only, and feature selection, tuning and threshold calibration were performed using the training\/development data, with final evaluation on the independent test set. Internal validation used repeated subsampling without replacement.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>During up to 16 years of follow-up, 927 participants developed AD. Feature selection reduced 3590 variables to 26 predictors spanning age, APOE4, SDOH, medical history and routine clinical measures. The final model showed good discrimination (area under the precision\u2013recall curve 0.89) and adequate calibration (Hosmer-Lemeshow p=0.71), with stable performance under repeated subsampling. Sex-stratified models showed similar patterns.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>SDOH contributed useful predictive information, but their associations should be interpreted as predictive rather than causal and may reflect socioeconomic confounding and healthcare access.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This model could support scalable AD risk screening using routinely collected data, but external validation and recalibration in non-UK populations are needed before broader application.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/bmjhci-2025-101803","type":"journal-article","created":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T14:47:06Z","timestamp":1782139626000},"page":"e101803","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":0,"title":["Alzheimer\u2019s disease risk prediction from clinical and social determinants of health: a machine learning cohort study in UK Biobank"],"prefix":"10.1136","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6503-7491","authenticated-orcid":false,"given":"Junming","family":"Hu","sequence":"first","affiliation":[{"name":"Bioinformatics Program, Boston University, Boston, Massachusetts, USA"},{"name":"Department of Medicine (Section of Biomedical Genetics), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Simon","family":"Lu","sequence":"additional","affiliation":[{"name":"Department of Medicine (Section of Computational Biomedicine), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Medicine (Section of Biomedical Genetics), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kehan","family":"Qian","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, Boston University, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Habbiburr","family":"Rehman","sequence":"additional","affiliation":[{"name":"Department of Medicine (Section of Biomedical Genetics), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Congcong","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Medicine (Section of Biomedical Genetics), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"Farrell","sequence":"additional","affiliation":[{"name":"Department of Medicine (Section of Biomedical Genetics), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Julio E","family":"Castrillon-Candas","sequence":"additional","affiliation":[{"name":"Department of Mathematics and Statistics, Boston University, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rhoda","family":"Au","sequence":"additional","affiliation":[{"name":"Departments of Anatomy & Neurobiology, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"},{"name":"Department of Neurology, Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"},{"name":"Departments of Epidemiology, Boston University School of Public Health, Boston, MA, USA"},{"name":"Framingham Heart Study, Boston University School of Medicine, Framingham, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lindsay A","family":"Farrer","sequence":"additional","affiliation":[{"name":"Bioinformatics Program, Boston University, Boston, Massachusetts, USA"},{"name":"Department of Medicine (Section of Biomedical Genetics), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"},{"name":"Departments of Epidemiology, Boston University School of Public Health, Boston, MA, USA"},{"name":"Framingham Heart Study, Boston University School of Medicine, Framingham, MA, USA"},{"name":"Departments of Ophthalmology, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei Q","family":"Qiu","sequence":"additional","affiliation":[{"name":"Alzheimer\u2019s Disease Research Center, Boston University School of Medicine, Boston, Massachusetts, USA"},{"name":"Pharmacology & Experimental Therapeutics, Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"},{"name":"Department of Psychiatry, Boston University Chobanian & Avedisian School of Medicine, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7259-4301","authenticated-orcid":false,"given":"Jinying","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Medicine (Section of Preventive Medicine and Epidemiology), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"},{"name":"Data Science Core, Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoling","family":"Zhang","sequence":"additional","affiliation":[{"name":"Bioinformatics Program, Boston University, Boston, Massachusetts, USA"},{"name":"Department of Medicine (Section of Biomedical Genetics), Boston University Chobanian & Avedisian School of Medicine, Boston, Massachusetts, USA"},{"name":"Framingham Heart Study, Boston University School of Medicine, Framingham, MA, USA"},{"name":"Departments of Biostatistics, Boston University School of Public Health, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2026,6,22]]},"reference":[{"key":"2026062207452115000_33.1.e101803.1","doi-asserted-by":"crossref","first-page":"1778","DOI":"10.1212\/WNL.0b013e31828726f5","article-title":"Alzheimer disease in the United States (2010-2050) estimated using the 2010 census","volume":"80","author":"Hebert","year":"2013","journal-title":"Neurology (ECronicon)"},{"key":"2026062207452115000_33.1.e101803.2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(17)31363-6"},{"key":"2026062207452115000_33.1.e101803.3","doi-asserted-by":"crossref","DOI":"10.1186\/s13195-017-0283-5","article-title":"On the path to 2025: understanding the Alzheimer\u2019s disease continuum","volume":"9","author":"Aisen","year":"2017","journal-title":"Alzheimers Res Ther"},{"key":"2026062207452115000_33.1.e101803.4","doi-asserted-by":"publisher","DOI":"10.1016\/j.jalz.2018.02.018"},{"key":"2026062207452115000_33.1.e101803.5","doi-asserted-by":"crossref","DOI":"10.1002\/dad2.12314","article-title":"Clinical application of CSF biomarkers for Alzheimer\u2019s disease: From rationale to ratios","volume":"14","author":"Bouwman","year":"2022","journal-title":"Alzheimers Dement (Amst)"},{"key":"2026062207452115000_33.1.e101803.6","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-020-0762-2"},{"key":"2026062207452115000_33.1.e101803.7","doi-asserted-by":"publisher","DOI":"10.1001\/JAMA.2020.12134"},{"key":"2026062207452115000_33.1.e101803.8","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-02869-z"},{"key":"2026062207452115000_33.1.e101803.9","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-021-01384-9"},{"key":"2026062207452115000_33.1.e101803.10","doi-asserted-by":"crossref","DOI":"10.3389\/fpubh.2022.853294","article-title":"Early-Stage Alzheimer\u2019s Disease Prediction Using Machine Learning Models","volume":"10","author":"Kavitha","year":"2022","journal-title":"Front Public Health"},{"key":"2026062207452115000_33.1.e101803.11","doi-asserted-by":"crossref","first-page":"379","DOI":"10.1038\/s43587-024-00573-8","article-title":"Leveraging electronic health records and knowledge networks for Alzheimer\u2019s disease prediction and sex-specific biological insights","volume":"4","author":"Tang","year":"2024","journal-title":"Nat Aging"},{"key":"2026062207452115000_33.1.e101803.12","doi-asserted-by":"crossref","DOI":"10.1016\/j.tjpad.2025.100169","article-title":"Using machine learning and electronic health record (EHR) data for the early prediction of Alzheimer\u2019s Disease and Related Dementias","volume":"12","author":"Akter","year":"2025","journal-title":"J Prev Alzheimers Dis"},{"key":"2026062207452115000_33.1.e101803.13","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-023-00970-0","article-title":"Large language models to identify social determinants of health in electronic health records","volume":"7","author":"Guevara","year":"2024","journal-title":"NPJ Digit Med"},{"key":"2026062207452115000_33.1.e101803.14","doi-asserted-by":"crossref","DOI":"10.1002\/dad2.12221","article-title":"Development of a dementia prediction model for primary care: The Hisayama Study","volume":"13","author":"Honda","year":"2021","journal-title":"Alzheimers Dement (Amst)"},{"key":"2026062207452115000_33.1.e101803.15","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0310712","article-title":"Identifying individuals at high risk for dementia in primary care: Development and validation of the DemRisk risk prediction model using routinely collected patient data","volume":"19","author":"Reeves","year":"2024","journal-title":"PLoS One"},{"key":"2026062207452115000_33.1.e101803.16","doi-asserted-by":"crossref","first-page":"785","DOI":"10.3233\/JAD-2010-091573","article-title":"Are certain lifestyle habits associated with lower Alzheimer\u2019s disease risk?","volume":"20","author":"Arab","year":"2010","journal-title":"J Alzheimers Dis"},{"key":"2026062207452115000_33.1.e101803.17","first-page":"e944","article-title":"Association of Healthy Lifestyles With Risk of Alzheimer Disease and Related Dementias in Low-Income Black and White Americans","volume":"99","author":"Yang","year":"2022","journal-title":"Neurology (ECronicon)"},{"key":"2026062207452115000_33.1.e101803.18","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pmed.1001779","article-title":"UK biobank: an open access resource for identifying the causes of a wide range of complex diseases of middle and old age","volume":"12","author":"Sudlow","year":"2015","journal-title":"PLoS Med"},{"key":"2026062207452115000_33.1.e101803.19","doi-asserted-by":"crossref","unstructured":"Kuhn M , Johnson K . Applied predictive modeling. New York, NY: Springer, 2013.","DOI":"10.1007\/978-1-4614-6849-3"},{"key":"2026062207452115000_33.1.e101803.20","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1109\/TSMCA.2009.2029559","article-title":"RUSBoost: A Hybrid Approach to Alleviating Class Imbalance","volume":"40","author":"Seiffert","year":"2010","journal-title":"IEEE Trans Syst Man Cybern A Syst Hum"},{"key":"2026062207452115000_33.1.e101803.21","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2008.2007853"},{"key":"2026062207452115000_33.1.e101803.22","doi-asserted-by":"crossref","DOI":"10.1016\/j.eclinm.2022.101665","article-title":"Development of a novel dementia risk prediction model in the general population: A large, longitudinal, population-based machine-learning study","volume":"53","author":"You","year":"2022","journal-title":"EClinicalMedicine"},{"key":"2026062207452115000_33.1.e101803.23","doi-asserted-by":"crossref","DOI":"10.1001\/jamanetworkopen.2023.18132","article-title":"Estimating Dementia Risk Using Multifactorial Prediction Models","volume":"6","author":"Kivim\u00e4ki","year":"2023","journal-title":"JAMA Netw Open"},{"key":"2026062207452115000_33.1.e101803.24","doi-asserted-by":"crossref","first-page":"1284","DOI":"10.1001\/jamaneurol.2023.3599","article-title":"APOE Genotype and Alzheimer Disease Risk Across Age, Sex, and Population Ancestry","volume":"80","author":"Belloy","year":"2023","journal-title":"JAMA Neurol"},{"key":"2026062207452115000_33.1.e101803.25","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-007-0114-2"},{"key":"2026062207452115000_33.1.e101803.26","doi-asserted-by":"crossref","first-page":"3806157","DOI":"10.1155\/2016\/3806157","article-title":"Getting to NO Alzheimer\u2019s Disease: Neuroprotection versus Neurotoxicity Mediated by Nitric Oxide","volume":"2016","author":"Balez","year":"2016","journal-title":"Oxid Med Cell Longev"},{"key":"2026062207452115000_33.1.e101803.27","doi-asserted-by":"crossref","DOI":"10.1073\/pnas.2220028120","article-title":"Ambient air pollution and Alzheimer\u2019s disease: the role of the composition of fine particles","volume":"120","author":"Peters","year":"2023","journal-title":"Proc Natl Acad Sci U S A"},{"key":"2026062207452115000_33.1.e101803.28","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0254174","article-title":"Geographic variation in Alzheimer\u2019s disease mortality","volume":"16","author":"Topping","year":"2021","journal-title":"PLoS One"},{"key":"2026062207452115000_33.1.e101803.29","first-page":"160","article-title":"Cereal Intake Increases and Dairy Products Decrease Risk of Cognitive Decline among Elderly Female Japanese","volume":"1","author":"Otsuka","year":"2014","journal-title":"J Prev Alzheimers Dis"},{"key":"2026062207452115000_33.1.e101803.30","doi-asserted-by":"crossref","first-page":"1232","DOI":"10.1159\/000531847","article-title":"Association between Mobile Phone Use and Incidence of Dementia: A Prospective Cohort Study Using the UK Biobank","volume":"69","author":"Zhao","year":"2023","journal-title":"Gerontology"}],"container-title":["BMJ Health &amp; Care Informatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/bmjhci-2025-101803","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,22]],"date-time":"2026-06-22T14:47:11Z","timestamp":1782139631000},"score":1,"resource":{"primary":{"URL":"https:\/\/informatics.bmj.com\/lookup\/doi\/10.1136\/bmjhci-2025-101803"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":30,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,6,22]]},"published-print":{"date-parts":[[2026,6]]}},"alternative-id":["10.1136\/bmjhci-2025-101803"],"URL":"https:\/\/doi.org\/10.1136\/bmjhci-2025-101803","relation":{},"ISSN":["2632-1009"],"issn-type":[{"value":"2632-1009","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}