Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches
dc.contributor.author | Ford, E | |
dc.contributor.author | Rooney, P | |
dc.contributor.author | Oliver, S | |
dc.contributor.author | Hoile, R | |
dc.contributor.author | Hurley, P | |
dc.contributor.author | Banerjee, Sube | |
dc.contributor.author | van Marwijk, H | |
dc.contributor.author | Cassell, J | |
dc.date.accessioned | 2021-10-22T10:03:47Z | |
dc.date.issued | 2019-12-02 | |
dc.identifier.issn | 1472-6947 | |
dc.identifier.issn | 1472-6947 | |
dc.identifier.other | 248 | |
dc.identifier.uri | http://hdl.handle.net/10026.1/18146 | |
dc.description.abstract |
Background: 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. Methods: We used electronic patient records from Clinical Practice Research Datalink (CPRD). Using a case-control design, we selected patients aged >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 years before diagnosis. After creating binary features, we trialled machine learning classifiers to discriminate between cases and controls (logistic regression, naïve Bayes, support vector machines, random forest and neural networks). We examined the most important features contributing to discrimination. Results: The final analysis included data on 93,120 patients, with a median age of 82.6 years; 64.8% were female. The naïve 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. Conclusions: 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. | |
dc.format.extent | 248- | |
dc.format.medium | Electronic | |
dc.language | en | |
dc.language.iso | en | |
dc.publisher | BioMed Central | |
dc.subject | Dementia | |
dc.subject | General practice | |
dc.subject | Diagnosis | |
dc.subject | Prediction | |
dc.subject | Machine learning | |
dc.subject | Early detection | |
dc.subject | Primary care | |
dc.subject | Electronic health records | |
dc.title | Identifying undetected dementia in UK primary care patients: a retrospective case-control study comparing machine-learning and standard epidemiological approaches | |
dc.type | journal-article | |
dc.type | Comparative Study | |
dc.type | Journal Article | |
dc.type | Research Support, Non-U.S. Gov't | |
plymouth.author-url | https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000500802800001&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=11bb513d99f797142bcfeffcc58ea008 | |
plymouth.issue | 1 | |
plymouth.volume | 19 | |
plymouth.publication-status | Published | |
plymouth.journal | BMC Medical Informatics and Decision Making | |
dc.identifier.doi | 10.1186/s12911-019-0991-9 | |
plymouth.organisational-group | /Plymouth | |
plymouth.organisational-group | /Plymouth/Faculty of Health | |
plymouth.organisational-group | /Plymouth/Faculty of Health/Peninsula Medical School | |
plymouth.organisational-group | /Plymouth/Faculty of Health/Peninsula Medical School/PMS - Manual | |
plymouth.organisational-group | /Plymouth/REF 2021 Researchers by UoA | |
plymouth.organisational-group | /Plymouth/REF 2021 Researchers by UoA/UoA03 Allied Health Professions, Dentistry, Nursing and Pharmacy | |
plymouth.organisational-group | /Plymouth/Users by role | |
plymouth.organisational-group | /Plymouth/Users by role/Academics | |
plymouth.organisational-group | /Plymouth/Users by role/Researchers in ResearchFish submission | |
dc.publisher.place | England | |
dcterms.dateAccepted | 2019-11-21 | |
dc.rights.embargodate | 2021-10-23 | |
dc.identifier.eissn | 1472-6947 | |
dc.rights.embargoperiod | Not known | |
rioxxterms.versionofrecord | 10.1186/s12911-019-0991-9 | |
rioxxterms.licenseref.uri | http://www.rioxx.net/licenses/all-rights-reserved | |
rioxxterms.licenseref.startdate | 2019-12-02 | |
rioxxterms.type | Journal Article/Review |