Cargando…
Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study
Background: Timely diagnosis of dementia is a policy priority in the United Kingdom (UK). Primary care physicians receive incentives to diagnose dementia; however, 33% of patients are still not receiving a diagnosis. We explored automating early detection of dementia using data from patients’ electr...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
F1000 Research Limited
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7385545/ https://www.ncbi.nlm.nih.gov/pubmed/32766457 http://dx.doi.org/10.12688/wellcomeopenres.15903.1 |
_version_ | 1783563807262507008 |
---|---|
author | Ford, Elizabeth Starlinger, Johannes Rooney, Philip Oliver, Seb Banerjee, Sube van Marwijk, Harm Cassell, Jackie |
author_facet | Ford, Elizabeth Starlinger, Johannes Rooney, Philip Oliver, Seb Banerjee, Sube van Marwijk, Harm Cassell, Jackie |
author_sort | Ford, Elizabeth |
collection | PubMed |
description | Background: Timely diagnosis of dementia is a policy priority in the United Kingdom (UK). Primary care physicians receive incentives to diagnose dementia; however, 33% of patients are still not receiving a diagnosis. We explored automating early detection of dementia using data from patients’ electronic health records (EHRs). We investigated: a) how early a machine-learning model could accurately identify dementia before the physician; b) if models could be tuned for dementia subtype; and c) what the best clinical features were for achieving detection. Methods: Using EHRs from Clinical Practice Research Datalink in a case-control design, we selected patients aged >65y with a diagnosis of dementia recorded 2000-2012 (cases) and matched them 1:1 to controls; we also identified subsets of Alzheimer’s and vascular dementia patients. Using 77 coded concepts recorded in the 5 years before diagnosis, we trained random forest classifiers, and evaluated models using Area Under the Receiver Operating Characteristic Curve (AUC). We examined models by year prior to diagnosis, subtype, and the most important features contributing to classification. Results: 95,202 patients (median age 83y; 64.8% female) were included (50% dementia cases). Classification of dementia cases and controls was poor 2-5 years prior to physician-recorded diagnosis (AUC range 0.55-0.65) but good in the year before (AUC: 0.84). Features indicating increasing cognitive and physical frailty dominated models 2-5 years before diagnosis; in the final year, initiation of the dementia diagnostic pathway (symptoms, screening and referral) explained the sudden increase in accuracy. No substantial differences were seen between all-cause dementia and subtypes. Conclusions: Automated detection of dementia earlier than the treating physician may be problematic, if using only primary care data. Future work should investigate more complex modelling, benefits of linking multiple sources of healthcare data and monitoring devices, or contextualising the algorithm to those cases that the GP would need to investigate. |
format | Online Article Text |
id | pubmed-7385545 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | F1000 Research Limited |
record_format | MEDLINE/PubMed |
spelling | pubmed-73855452020-08-05 Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study Ford, Elizabeth Starlinger, Johannes Rooney, Philip Oliver, Seb Banerjee, Sube van Marwijk, Harm Cassell, Jackie Wellcome Open Res Research Article Background: Timely diagnosis of dementia is a policy priority in the United Kingdom (UK). Primary care physicians receive incentives to diagnose dementia; however, 33% of patients are still not receiving a diagnosis. We explored automating early detection of dementia using data from patients’ electronic health records (EHRs). We investigated: a) how early a machine-learning model could accurately identify dementia before the physician; b) if models could be tuned for dementia subtype; and c) what the best clinical features were for achieving detection. Methods: Using EHRs from Clinical Practice Research Datalink in a case-control design, we selected patients aged >65y with a diagnosis of dementia recorded 2000-2012 (cases) and matched them 1:1 to controls; we also identified subsets of Alzheimer’s and vascular dementia patients. Using 77 coded concepts recorded in the 5 years before diagnosis, we trained random forest classifiers, and evaluated models using Area Under the Receiver Operating Characteristic Curve (AUC). We examined models by year prior to diagnosis, subtype, and the most important features contributing to classification. Results: 95,202 patients (median age 83y; 64.8% female) were included (50% dementia cases). Classification of dementia cases and controls was poor 2-5 years prior to physician-recorded diagnosis (AUC range 0.55-0.65) but good in the year before (AUC: 0.84). Features indicating increasing cognitive and physical frailty dominated models 2-5 years before diagnosis; in the final year, initiation of the dementia diagnostic pathway (symptoms, screening and referral) explained the sudden increase in accuracy. No substantial differences were seen between all-cause dementia and subtypes. Conclusions: Automated detection of dementia earlier than the treating physician may be problematic, if using only primary care data. Future work should investigate more complex modelling, benefits of linking multiple sources of healthcare data and monitoring devices, or contextualising the algorithm to those cases that the GP would need to investigate. F1000 Research Limited 2020-06-08 /pmc/articles/PMC7385545/ /pubmed/32766457 http://dx.doi.org/10.12688/wellcomeopenres.15903.1 Text en Copyright: © 2020 Ford E et al. http://creativecommons.org/licenses/by/4.0/ This is an open access article distributed under the terms of the Creative Commons Attribution Licence, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. |
spellingShingle | Research Article Ford, Elizabeth Starlinger, Johannes Rooney, Philip Oliver, Seb Banerjee, Sube van Marwijk, Harm Cassell, Jackie Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study |
title | Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study |
title_full | Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study |
title_fullStr | Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study |
title_full_unstemmed | Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study |
title_short | Could dementia be detected from UK primary care patients’ records by simple automated methods earlier than by the treating physician? A retrospective case-control study |
title_sort | could dementia be detected from uk primary care patients’ records by simple automated methods earlier than by the treating physician? a retrospective case-control study |
topic | Research Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7385545/ https://www.ncbi.nlm.nih.gov/pubmed/32766457 http://dx.doi.org/10.12688/wellcomeopenres.15903.1 |
work_keys_str_mv | AT fordelizabeth coulddementiabedetectedfromukprimarycarepatientsrecordsbysimpleautomatedmethodsearlierthanbythetreatingphysicianaretrospectivecasecontrolstudy AT starlingerjohannes coulddementiabedetectedfromukprimarycarepatientsrecordsbysimpleautomatedmethodsearlierthanbythetreatingphysicianaretrospectivecasecontrolstudy AT rooneyphilip coulddementiabedetectedfromukprimarycarepatientsrecordsbysimpleautomatedmethodsearlierthanbythetreatingphysicianaretrospectivecasecontrolstudy AT oliverseb coulddementiabedetectedfromukprimarycarepatientsrecordsbysimpleautomatedmethodsearlierthanbythetreatingphysicianaretrospectivecasecontrolstudy AT banerjeesube coulddementiabedetectedfromukprimarycarepatientsrecordsbysimpleautomatedmethodsearlierthanbythetreatingphysicianaretrospectivecasecontrolstudy AT vanmarwijkharm coulddementiabedetectedfromukprimarycarepatientsrecordsbysimpleautomatedmethodsearlierthanbythetreatingphysicianaretrospectivecasecontrolstudy AT casselljackie coulddementiabedetectedfromukprimarycarepatientsrecordsbysimpleautomatedmethodsearlierthanbythetreatingphysicianaretrospectivecasecontrolstudy |