{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T04:19:02Z","timestamp":1771647542951,"version":"3.50.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2019,12,1]],"date-time":"2019-12-01T00:00:00Z","timestamp":1575158400000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T00:00:00Z","timestamp":1575244800000},"content-version":"vor","delay-in-days":1,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100010269","name":"Wellcome Trust","doi-asserted-by":"crossref","award":["202133\/Z\/16\/Z"],"award-info":[{"award-number":["202133\/Z\/16\/Z"]}],"id":[{"id":"10.13039\/100010269","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Med Inform Decis Mak"],"published-print":{"date-parts":[[2019,12]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Identifying dementia early in time, using real world data, is a public health challenge. As only two-thirds of people with dementia now ultimately receive a formal diagnosis in United Kingdom health systems and many receive it late in the disease process, there is ample room for improvement. The policy of the UK government and National Health Service (NHS) is to increase rates of timely dementia diagnosis. We used data from general practice (GP) patient records to create a machine-learning model to identify patients who have or who are developing dementia, but are currently undetected as having the condition by the GP.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>We used electronic patient records from Clinical Practice Research Datalink (CPRD). Using a case-control design, we selected patients aged &gt;65y with a diagnosis of dementia (cases) and matched them 1:1 by sex and age to patients with no evidence of dementia (controls). We developed a list of 70 clinical entities related to the onset of dementia and recorded in the 5\u2009years before diagnosis. After creating binary features, we trialled machine learning classifiers to discriminate between cases and controls (logistic regression, na\u00efve Bayes, support vector machines, random forest and neural networks). We examined the most important features contributing to discrimination.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The final analysis included data on 93,120 patients, with a median age of 82.6\u2009years; 64.8% were female. The na\u00efve Bayes model performed least well. The logistic regression, support vector machine, neural network and random forest performed very similarly with an AUROC of 0.74. The top features retained in the logistic regression model were disorientation and wandering, behaviour change, schizophrenia, self-neglect, and difficulty managing.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>Our model could aid GPs or health service planners with the early detection of dementia. Future work could improve the model by exploring the longitudinal nature of patient data and modelling decline in function over time.<\/jats:p><\/jats:sec>","DOI":"10.1186\/s12911-019-0991-9","type":"journal-article","created":{"date-parts":[[2019,12,2]],"date-time":"2019-12-02T18:03:14Z","timestamp":1575309794000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":56,"title":["Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches"],"prefix":"10.1186","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5613-8509","authenticated-orcid":false,"given":"Elizabeth","family":"Ford","sequence":"first","affiliation":[]},{"given":"Philip","family":"Rooney","sequence":"additional","affiliation":[]},{"given":"Seb","family":"Oliver","sequence":"additional","affiliation":[]},{"given":"Richard","family":"Hoile","sequence":"additional","affiliation":[]},{"given":"Peter","family":"Hurley","sequence":"additional","affiliation":[]},{"given":"Sube","family":"Banerjee","sequence":"additional","affiliation":[]},{"given":"Harm","family":"van Marwijk","sequence":"additional","affiliation":[]},{"given":"Jackie","family":"Cassell","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,12,2]]},"reference":[{"key":"991_CR1","volume-title":"The use of antipsychotic medication for people with dementia: time for action","author":"S Banerjee","year":"2009","unstructured":"Banerjee S. The use of antipsychotic medication for people with dementia: time for action. London: Department of Health; 2009."},{"key":"991_CR2","unstructured":"Living well with dementia: A National Dementia Strategy [https:\/\/www.gov.uk\/government\/uploads\/system\/uploads\/attachment_data\/file\/168220\/dh_094051.pdf]."},{"issue":"8","key":"991_CR3","doi-asserted-by":"publisher","first-page":"705","DOI":"10.1016\/j.arcmed.2012.10.006","volume":"43","author":"S Banerjee","year":"2012","unstructured":"Banerjee S. The macroeconomics of dementia\u2014will the world economy get Alzheimer's disease? Arch Med Res. 2012;43(8):705\u20139.","journal-title":"Arch Med Res"},{"key":"991_CR4","unstructured":"Dementia [https:\/\/www.england.nhs.uk\/mental-health\/dementia\/]."},{"key":"991_CR5","unstructured":"Prince M, Knapp M, Guerchet M, McCrone P, Prina M, Comas-Herrera A, Wittenberg R, Adelaja B, Hu B, King D et al: Dementia UK Update In. Edited by Society As, vol. Second Edition. London, UK; 2014."},{"issue":"11","key":"991_CR6","doi-asserted-by":"publisher","first-page":"965","DOI":"10.1097\/JGP.0b013e3181b2075e","volume":"17","author":"M Pentzek","year":"2009","unstructured":"Pentzek M, Wollny A, Wiese B, Jessen F, Haller F, Maier W, Riedel-Heller SG, Angermeyer MC, Bickel H, Mosch E, et al. Apart from nihilism and stigma: what influences general practitioners' accuracy in identifying incident dementia? The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry. 2009;17(11):965\u201375.","journal-title":"The American journal of geriatric psychiatry : official journal of the American Association for Geriatric Psychiatry"},{"issue":"8","key":"991_CR7","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1080\/13607863.2011.596805","volume":"15","author":"A Connolly","year":"2011","unstructured":"Connolly A, Gaehl E, Martin H, Morris J, Purandare N. Underdiagnosis of dementia in primary care: variations in the observed prevalence and comparisons to the expected prevalence. Aging Ment Health. 2011;15(8):978\u201384.","journal-title":"Aging Ment Health"},{"key":"991_CR8","unstructured":"Dementia diagnosis rate workbooks [https:\/\/www.england.nhs.uk\/publication\/dementia-diagnosis-rate-workbook\/]."},{"key":"991_CR9","unstructured":"Prince M, Bryce R, Ferri C: World Alzheimer report 2011: the benefits of early diagnosis and intervention: Alzheimer's disease international; 2011."},{"issue":"3","key":"991_CR10","doi-asserted-by":"publisher","first-page":"827","DOI":"10.1093\/ije\/dyv098","volume":"44","author":"E Herrett","year":"2015","unstructured":"Herrett E, Gallagher AM, Bhaskaran K, Forbes H, Mathur R, van Staa T, Smeeth L. Data resource profile: clinical practice research Datalink (CPRD). Int J Epidemiol. 2015;44(3):827\u201336.","journal-title":"Int J Epidemiol"},{"key":"991_CR11","doi-asserted-by":"publisher","first-page":"204209861985401","DOI":"10.1177\/2042098619854010","volume":"10","author":"RE Ghosh","year":"2019","unstructured":"Ghosh RE, Crellin E, Beatty S, Donegan K, Myles P, Williams R. How clinical practice research Datalink data are used to support pharmacovigilance. Ther Adv Drug Saf. 2019;10:2042098619854010.","journal-title":"Ther Adv Drug Saf"},{"key":"991_CR12","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1093\/fampra\/cml068","volume":"24","author":"C Bamford","year":"2007","unstructured":"Bamford C, Eccles M, Steen N, Robinson L. Can primary care record review facilitate earlier diagnosis of dementia? Fam Pract. 2007;24:108\u201316.","journal-title":"Fam Pract"},{"issue":"4","key":"991_CR13","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1159\/000107594","volume":"24","author":"IH Ramakers","year":"2007","unstructured":"Ramakers IH, Visser PJ, Aalten P, Boesten JH, Metsemakers JF, Jolles J, Verhey FR. Symptoms of preclinical dementia in general practice up to five years before dementia diagnosis. Dement Geriatr Cogn Disord. 2007;24(4):300\u20136.","journal-title":"Dement Geriatr Cogn Disord"},{"issue":"6","key":"991_CR14","doi-asserted-by":"publisher","first-page":"318","DOI":"10.1038\/nrneurol.2010.54","volume":"6","author":"Blossom C. M. Stephan","year":"2010","unstructured":"Stephan BC, Kurth T, Matthews FE, Brayne C, Dufouil C. Dementia risk prediction in the population: are screening models accurate? Nat Rev Neurol. 2010;6(6):318.","journal-title":"Nature Reviews Neurology"},{"issue":"s4","key":"991_CR15","doi-asserted-by":"publisher","first-page":"S329","DOI":"10.3233\/JAD-141413","volume":"42","author":"B Stephan","year":"2014","unstructured":"Stephan B, Brayne C. Risk factors and screening methods for detecting dementia: a narrative review. J Alzheimers Dis. 2014;42(s4):S329\u201338.","journal-title":"J Alzheimers Dis"},{"issue":"2","key":"991_CR16","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1097\/YCO.0000000000000235","volume":"29","author":"BC Stephan","year":"2016","unstructured":"Stephan BC, Tang E, Muniz-Terrera G. Composite risk scores for predicting dementia. Curr Opin Psychiatry. 2016;29(2):174\u201380.","journal-title":"Curr Opin Psychiatry"},{"issue":"9","key":"991_CR17","doi-asserted-by":"publisher","first-page":"e0136181","DOI":"10.1371\/journal.pone.0136181","volume":"10","author":"Eugene Y. H. Tang","year":"2015","unstructured":"Tang EYH, Harrison SL, Errington L, Gordon MF, Visser PJ, Novak G. Current developments in dementia risk prediction modelling: an updated systematic review. PLoS One. 2015;10(9):e0136181.","journal-title":"PLOS ONE"},{"key":"991_CR18","unstructured":"The PHG Foundation: Dementia Risk Prediction Models: What do policy makers need to know? In. Cambridge, UK: The University of Cambridge; 2019."},{"issue":"1","key":"991_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12916-016-0549-y","volume":"14","author":"K Walters","year":"2016","unstructured":"Walters K, Hardoon S, Petersen I, Iliffe S, Omar RZ, Nazareth I, Rait G. Predicting dementia risk in primary care: development and validation of the dementia risk score using routinely collected data. BMC Med. 2016;14(1):1\u201312.","journal-title":"BMC Med"},{"issue":"2","key":"991_CR20","doi-asserted-by":"publisher","first-page":"e16852","DOI":"10.1371\/journal.pone.0016852","volume":"6","author":"Frank Jessen","year":"2011","unstructured":"Jessen F, Wiese B, Bickel H, Eifflander-Gorfer S, Fuchs A, Kaduszkiewicz H. Prediction of dementia in primary care patients. PLoS One. 2011;6.","journal-title":"PLoS ONE"},{"key":"991_CR21","doi-asserted-by":"crossref","unstructured":"Jammeh EA, Camille BC, Stephen WP, Escudero J, Anastasiou A, Zhao P, Chenore T, Zajicek J, Ifeachor E. Machine-learning based identification of undiagnosed dementia in primary care: a feasibility study. BJGP open. 2018;2(2):bjgpopen18X101589.","DOI":"10.3399\/bjgpopen18X101589"},{"key":"991_CR22","unstructured":"Clinical Practice Research Datalink [www.cprd.com]."},{"issue":"2","key":"991_CR23","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1177\/2042098611435911","volume":"3","author":"T Williams","year":"2012","unstructured":"Williams T, Van Staa T, Puri S, Eaton S. Recent advances in the utility and use of the general practice research database as an example of a UK primary care data resource. Ther Adv Drug Saf. 2012;3(2):89\u201399.","journal-title":"Ther Adv Drug Saf"},{"key":"991_CR24","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1136\/bmj.300.6732.1092","volume":"300","author":"J Chisholm","year":"1990","unstructured":"Chisholm J. The read clinical classification. BMJ. 1990;300:1092.","journal-title":"BMJ"},{"key":"991_CR25","unstructured":"[https:\/\/www.visionhealth.co.uk\/vision-medical-software\/]."},{"issue":"12","key":"991_CR26","doi-asserted-by":"publisher","first-page":"e004023","DOI":"10.1136\/bmjopen-2013-004023","volume":"3","author":"Paul Russell","year":"2013","unstructured":"Russell P, Banerjee S, Watt J, Adleman R, Agoe B, Burnie N, Carefull A, Chandan K, Constable D, Daniels M, et al. Improving the identification of people with dementia in primary care: evaluation of the impact of primary care dementia coding guidance on identified prevalence. BMJ Open. 2013;3(12):e004023.","journal-title":"BMJ Open"},{"key":"991_CR27","doi-asserted-by":"publisher","first-page":"c3584","DOI":"10.1136\/bmj.c3584","volume":"341","author":"G Rait","year":"2010","unstructured":"Rait G, Walters K, Bottomley C, Petersen I, Iliffe S, Nazareth I. Survival of people with clinical diagnosis of dementia in primary care: cohort study. Br Med J. 2010;341:c3584.","journal-title":"Br Med J"},{"issue":"3","key":"991_CR28","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0194735","volume":"13","author":"E Ford","year":"2018","unstructured":"Ford E, Greenslade N, Paudyal P, Bremner S, Smith HE, Banerjee S, Sadhwani S, Rooney P, Oliver S, Cassell J. Predicting dementia from primary care records: a systematic review and meta-analysis. PLoS One. 2018;13(3):e0194735.","journal-title":"PLoS One"},{"key":"991_CR29","unstructured":"[https:\/\/clinicalcodes.rss.mhs.man.ac.uk\/]."},{"issue":"1","key":"991_CR30","doi-asserted-by":"crossref","first-page":"267","DOI":"10.1111\/j.2517-6161.1996.tb02080.x","volume":"58","author":"Robert Tibshirani","year":"1996","unstructured":"Tibshirani R. Regression shrinkage and selection via the lasso. J R Stat Soc Ser B Methodol. 1996;58(1):267\u201388.","journal-title":"Journal of the Royal Statistical Society: Series B (Methodological)"},{"issue":"9","key":"991_CR31","doi-asserted-by":"publisher","first-page":"1315","DOI":"10.1097\/JTO.0b013e3181ec173d","volume":"5","author":"JN Mandrekar","year":"2010","unstructured":"Mandrekar JN. Receiver operating characteristic curve in diagnostic test assessment. J Thorac Oncol. 2010;5(9):1315\u20136.","journal-title":"J Thorac Oncol"},{"issue":"3","key":"991_CR32","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.cppeds.2010.10.006","volume":"41","author":"AG Fiks","year":"2011","unstructured":"Fiks AG. Designing computerized decision support that works for clinicians and families. Curr Probl Pediatr Adolesc Health Care. 2011;41(3):60\u201388.","journal-title":"Curr Probl Pediatr Adolesc Health Care"},{"issue":"1","key":"991_CR33","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1186\/1472-6947-9-6","volume":"9","author":"MH Trivedi","year":"2009","unstructured":"Trivedi MH, Daly EJ, Kern JK, Grannemann BD, Sunderajan P, Claassen CA. Barriers to implementation of a computerized decision support system for depression: an observational report on lessons learned in \"real world\" clinical settings. BMC Medical Inform Decis Making. 2009;9(1):6.","journal-title":"BMC Medical Inform Decis Making"},{"key":"991_CR34","doi-asserted-by":"crossref","unstructured":"Moerel L, Storm M: Automated decisions based on profiling: information, explanation or justification\u2013that is the question! Autonomous Systems and the Law (2019) Editors: Nikita Aggarwal, Horst Eidenm\u00fcller, Luca Enriques, Jennifer Payne, Kristin van Zwieten Beck CH 2019.","DOI":"10.2139\/ssrn.3356631"},{"key":"991_CR35","unstructured":"GPRD and research - An overview for researchers [https:\/\/www.ukri.org\/about-us\/policies-and-standards\/gdpr-and-research-an-overview-for-researchers\/]."},{"issue":"7","key":"991_CR36","first-page":"663","volume":"23","author":"S Cahill","year":"2008","unstructured":"Cahill S, Clark M, O'connell H, Lawlor B, Coen R, Walsh C. The attitudes and practices of general practitioners regarding dementia diagnosis in Ireland. International Journal of Geriatric Psychiatry. J Psychiatry Late Life Allied Sci. 2008;23(7):663\u20139.","journal-title":"J Psychiatry Late Life Allied Sci"},{"issue":"2\u20133","key":"991_CR37","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/S0738-3991(99)00034-8","volume":"39","author":"H van Hout","year":"2000","unstructured":"van Hout H, Vernooij-Dassen M, Bakker K, Blom M, Grol R. General practitioners on dementia: tasks, practices and obstacles. Patient Educ Couns. 2000;39(2\u20133):219\u201325.","journal-title":"Patient Educ Couns"}],"container-title":["BMC Medical Informatics and Decision Making"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-019-0991-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12911-019-0991-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12911-019-0991-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,28]],"date-time":"2024-07-28T00:48:34Z","timestamp":1722127714000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcmedinformdecismak.biomedcentral.com\/articles\/10.1186\/s12911-019-0991-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,12]]},"references-count":37,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,12]]}},"alternative-id":["991"],"URL":"https:\/\/doi.org\/10.1186\/s12911-019-0991-9","relation":{},"ISSN":["1472-6947"],"issn-type":[{"value":"1472-6947","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,12]]},"assertion":[{"value":"5 June 2019","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 November 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 December 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This study was approved by the Independent Scientific Advisory Committee at the Medicines and Healthcare Products Regulatory Authority, UK, protocol number 15_111_R. Following approval, administrative permissions to access and use the electronic patient records were granted by Clinical Practice Research Datalink ().Consultations with stakeholders (GPs) for guiding the design of research do not need ethics approvals or written consent.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}},{"value":"For EHR data: Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"248"}}