{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"medRxiv"}],"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T11:26:03Z","timestamp":1768562763257,"version":"3.49.0"},"posted":{"date-parts":[[2023,2,23]]},"group-title":"Epidemiology","reference-count":28,"publisher":"openRxiv","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2023,2,23]]},"abstract":"<jats:title>SUMMARY<\/jats:title>\n                <jats:sec>\n                  <jats:title>Background<\/jats:title>\n                  <jats:p>Dementia is defined by cognitive decline that affects functional status. Longitudinal ageing surveys often lack a clinical diagnosis of dementia though measure cognitive and function over time. We used unsupervised machine learning and longitudinal data to identify transition to probable dementia.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Methods<\/jats:title>\n                  <jats:p>Multiple Factor Analysis was applied to longitudinal function and cognitive data of 15,278 baseline participants (aged 50 years and more) from the Survey of Health, Ageing, and Retirement in Europe (SHARE) (waves 1, 2 and 4\u20137, between 2004 and 2017). Hierarchical Clustering on Principal Components discriminated three clusters at each wave. We estimated probable or \u201cLikely Dementia\u201d prevalence by sex and age, and assessed whether dementia risk factors increased the risk of being assigned probable dementia status using multistate models. Next, we compared the \u201cLikely Dementia\u201d cluster with self-reported dementia status and replicated our findings in the English Longitudinal Study of Ageing (ELSA) cohort (waves 1\u20139, between 2002 and 2019, 7,840 participants at baseline).<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Findings<\/jats:title>\n                  <jats:p>Our algorithm identified a higher number of probable dementia cases compared with self-reported cases and showed good discriminative power across all waves (AUC ranged from 0.754 [0.722\u20130.787] to 0.830 [0.800\u20130.861]). \u201cLikely Dementia\u201d status was more prevalent in older people, displayed a 2:1 female\/male ratio and was associated with nine factors that increased risk of transition to dementia: low education, hearing loss, hypertension, drinking, smoking, depression, social isolation, physical inactivity, diabetes, and obesity. Results were replicated in ELSA cohort with good accuracy.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Interpretation<\/jats:title>\n                  <jats:p>Machine learning clustering can be used to study dementia determinants and outcomes in longitudinal population ageing surveys in which dementia clinical diagnosis is lacking.<\/jats:p>\n                <\/jats:sec>\n                <jats:sec>\n                  <jats:title>Funding<\/jats:title>\n                  <jats:p>French Institute for Public Health Research (IReSP), French National Institute for Health and Medical Research (Inserm), NeurATRIS Grant (ANR-11-INBS-0011), and Front-Cog University Research School (ANR-17-EUR-0017).<\/jats:p>\n                <\/jats:sec>","DOI":"10.1101\/2023.02.17.23286078","type":"posted-content","created":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T18:50:17Z","timestamp":1677178217000},"source":"Crossref","is-referenced-by-count":2,"title":["Identification of High Likelihood of Dementia in Population-Based Surveys using Unsupervised Clustering: a Longitudinal Analysis"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7788-3321","authenticated-orcid":false,"given":"Amin","family":"Gharbi-Meliani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7271-8877","authenticated-orcid":false,"given":"Fran\u00e7ois","family":"Husson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9319-0031","authenticated-orcid":false,"given":"Henri","family":"Vandendriessche","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0286-5521","authenticated-orcid":false,"given":"Eleonore","family":"Bayen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0919-3825","authenticated-orcid":false,"given":"Kristine","family":"Yaffe","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3000-2210","authenticated-orcid":false,"given":"Anne-Catherine","family":"Bachoud-L\u00e9vi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6551-4641","authenticated-orcid":false,"given":"Laurent Cleret","family":"de Langavant","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"54368","reference":[{"key":"2023022511150709000_2023.02.17.23286078v1.1","doi-asserted-by":"crossref","unstructured":"American Psychiatric Association. Diagnostic and statistical manual of mental disorders: DSM-5, 5th edition. Washington, DC, 2013.","DOI":"10.1176\/appi.books.9780890425596"},{"key":"2023022511150709000_2023.02.17.23286078v1.2","doi-asserted-by":"crossref","first-page":"e011146","DOI":"10.1136\/bmjopen-2016-011146","article-title":"Prevalence and determinants of undetected dementia in the community: a systematic literature review and a meta-analysis","volume":"7","year":"2017","journal-title":"BMJ Open"},{"key":"2023022511150709000_2023.02.17.23286078v1.3","unstructured":"Alzheimer\u2019s Disease International, McGill University. World Alzheimer\u2019s Report 2021. 2021 https:\/\/www.alzint.org\/resource\/world-alzheimer-report-2021\/."},{"key":"2023022511150709000_2023.02.17.23286078v1.4","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyu067"},{"key":"2023022511150709000_2023.02.17.23286078v1.5","doi-asserted-by":"crossref","first-page":"S5","DOI":"10.1093\/geronb\/gbab050","article-title":"Gateway to Global Aging Data Team. Gateway to Global Aging Data: Resources for Cross-National Comparisons of Family, Social Environment, and Healthy Aging","volume":"76","year":"2021","journal-title":"J Gerontol B Psychol Sci Soc Sci"},{"key":"2023022511150709000_2023.02.17.23286078v1.6","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1146\/annurev-publhealth-040119-094437","article-title":"Machine Learning in Epidemiology and Health Outcomes Research","volume":"41","year":"2020","journal-title":"Annu Rev Public Health"},{"key":"2023022511150709000_2023.02.17.23286078v1.7","doi-asserted-by":"crossref","first-page":"e10493","DOI":"10.2196\/10493","article-title":"Unsupervised Machine Learning to Identify High Likelihood of Dementia in Population-Based Surveys: Development and Validation Study","volume":"20","year":"2018","journal-title":"J Med Internet Res"},{"key":"2023022511150709000_2023.02.17.23286078v1.8","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dyt088"},{"key":"2023022511150709000_2023.02.17.23286078v1.9","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v070.i01"},{"key":"2023022511150709000_2023.02.17.23286078v1.10","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v025.i14"},{"key":"2023022511150709000_2023.02.17.23286078v1.11","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v043.i10"},{"key":"2023022511150709000_2023.02.17.23286078v1.12","doi-asserted-by":"crossref","first-page":"413","DOI":"10.1016\/S0140-6736(20)30367-6","article-title":"Dementia prevention, intervention, and care: 2020 report of the Lancet Commission","volume":"396","year":"2020","journal-title":"The Lancet"},{"key":"2023022511150709000_2023.02.17.23286078v1.13","doi-asserted-by":"publisher","DOI":"10.18637\/jss.v038.i07"},{"key":"2023022511150709000_2023.02.17.23286078v1.14","doi-asserted-by":"publisher","DOI":"10.1093\/ije\/dys168"},{"key":"2023022511150709000_2023.02.17.23286078v1.15","doi-asserted-by":"crossref","first-page":"1453","DOI":"10.1016\/S0140-6736(07)61602-X","article-title":"The Strengthening the Reporting of Observational Studies in Epidemiology (STROBE) statement: guidelines for reporting observational studies","volume":"370","year":"2007","journal-title":"Lancet Lond Engl"},{"key":"2023022511150709000_2023.02.17.23286078v1.16","doi-asserted-by":"crossref","first-page":"1098","DOI":"10.1016\/j.jalz.2015.06.1885","article-title":"Guidelines for reporting methodological challenges and evaluating potential bias in dementia research","volume":"11","year":"2015","journal-title":"Alzheimers Dement J Alzheimers Assoc"},{"key":"2023022511150709000_2023.02.17.23286078v1.17","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMc1305541"},{"key":"2023022511150709000_2023.02.17.23286078v1.18","doi-asserted-by":"crossref","first-page":"164","DOI":"10.1186\/s12874-017-0446-x","article-title":"Longitudinal drop-out and weighting against its bias","volume":"17","year":"2017","journal-title":"BMC Med Res Methodol"},{"key":"2023022511150709000_2023.02.17.23286078v1.19","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1159\/000503004","article-title":"The Health and Retirement Study Harmonized Cognitive Assessment Protocol Project: Study Design and Methods","volume":"54","year":"2020","journal-title":"Neuroepidemiology"},{"key":"2023022511150709000_2023.02.17.23286078v1.20","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1186\/s13195-020-00740-0","article-title":"The association of APOE \u03b54 with cognitive function over the adult life course and incidence of dementia: 20 years follow-up of the Whitehall II study","volume":"13","year":"2021","journal-title":"Alzheimers Res Ther"},{"key":"2023022511150709000_2023.02.17.23286078v1.21","doi-asserted-by":"crossref","first-page":"412","DOI":"10.1038\/s41588-022-01024-z","article-title":"New insights into the genetic etiology of Alzheimer\u2019s disease and related dementias","volume":"54","year":"2022","journal-title":"Nat Genet"},{"key":"2023022511150709000_2023.02.17.23286078v1.22","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-24082-z"},{"key":"2023022511150709000_2023.02.17.23286078v1.23","doi-asserted-by":"crossref","first-page":"e65325","DOI":"10.7554\/eLife.65325","article-title":"Alcohol consumption in the general population is associated with structural changes in multiple organ systems","volume":"10","year":"2021","journal-title":"eLife"},{"key":"2023022511150709000_2023.02.17.23286078v1.24","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.k2927"},{"key":"2023022511150709000_2023.02.17.23286078v1.25","doi-asserted-by":"publisher","DOI":"10.1111\/add.16035"},{"key":"2023022511150709000_2023.02.17.23286078v1.26","doi-asserted-by":"publisher","DOI":"10.2188\/jea.JE20200602"},{"key":"2023022511150709000_2023.02.17.23286078v1.27","doi-asserted-by":"crossref","first-page":"1213","DOI":"10.1002\/alz.12285","article-title":"Rural-urban differences in diagnostic incidence and prevalence of Alzheimer\u2019s disease and related dementias","volume":"17","year":"2021","journal-title":"Alzheimers Dement"},{"key":"2023022511150709000_2023.02.17.23286078v1.28","doi-asserted-by":"crossref","first-page":"96001","DOI":"10.1289\/EHP8716","article-title":"Exposure to Air Pollution in Relation to Risk of Dementia and Related Outcomes: An Updated Systematic Review of the Epidemiological Literature","volume":"129","year":"2021","journal-title":"Environ Health Perspect"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1101\/2023.02.17.23286078","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T19:27:26Z","timestamp":1768505246000},"score":1,"resource":{"primary":{"URL":"http:\/\/medrxiv.org\/lookup\/doi\/10.1101\/2023.02.17.23286078"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,23]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1101\/2023.02.17.23286078","relation":{"is-preprint-of":[{"id-type":"doi","id":"10.1186\/s13195-023-01357-9","asserted-by":"subject"}]},"subject":[],"published":{"date-parts":[[2023,2,23]]},"subtype":"preprint"}}