Skip to content

Research at St Andrews

Machine-learning based identification of undiagnosed dementia in primary care: a feasibility study

Research output: Contribution to journalArticle


Emmanuel A. Jammeh, Camille B. Carroll, Stephen W. Pearson, Javier Escudero, Athanasios Anastasiou, Peng Zhao, Todd Chenore, John Zajicek, Emmanuel Ifeachor

School/Research organisations


Background: Up to half of patients with dementia may not receive a formal diagnosis, limiting access to appropriate services. It is hypothesised that it may be possible to identify undiagnosed dementia from a profile of symptoms recorded in routine clinical practice.
Aim:  The aim of this study is to develop a machine learning-based model that could be used in general practice to detect dementia from routinely collected NHS data. The model would be a useful tool for identifying people who may be living with dementia but have not been formally diagnosed.
Design & setting: The study involved a case-control design and analysis of primary care data routinely collected over a 2-year period. Dementia diagnosed during the study period was compared to no diagnosis of dementia during the same period using pseudonymised routinely collected primary care clinical data.
Method: Routinely collected Read-encoded data were obtained from 18 consenting GP surgeries across Devon, for 26 483 patients aged >65 years. The authors determined Read codes assigned to patients that may contribute to dementia risk. These codes were used as features to train a machine-learning classification model to identify patients that may have underlying dementia.
Results: The model obtained sensitivity and specificity values of 84.47% and 86.67%, respectively.
Conclusion:  The results show that routinely collected primary care data may be used to identify undiagnosed dementia. The methodology is promising and, if successfully developed and deployed, may help to increase dementia diagnosis in primary care.


Original languageEnglish
Article numberbjgpopen18X101589
Number of pages13
JournalBJGP Open
Issue number2
Publication statusPublished - 12 Jun 2018

    Research areas

  • NHS data, Primary care, GP practice, Machine learning, Read code, Dementia

Discover related content
Find related publications, people, projects and more using interactive charts.

View graph of relations

Related by author

  1. Simvastatin as a neuroprotective treatment for Parkinson's disease (PD STAT): protocol for a double-blind, randomised, placebo-controlled futility study

    Carroll, C. B., Webb, D., Stevens, K. N., Vickery, J., Eyre, V., Ball, S., Wyse, R., Webber, M., Foggo, A., Zajicek, J., Whone, A. & Creanor, S., 7 Oct 2019, In : BMJ Open. 9, 10, 11 p., e029740.

    Research output: Contribution to journalArticle

  2. Assessment of a home-based standing frame programme in people with progressive multiple sclerosis (SUMS): a pragmatic, multi-centre, randomised, controlled trial and cost-effectiveness analysis

    Freeman, J. A., Hendrie, W., Jarrett, L., Hawton, A., Barton, A., Dennett, R., Jones, B., Zajicek, J. P. & Creanor, S., 1 Aug 2019, In : Lancet Neurology. 18, 8, p. 736-747

    Research output: Contribution to journalArticle

  3. A self-management programme to reduce falls and improve safe mobility in people with secondary progressive MS: the BRiMS feasibility RCT

    Gunn, H., Andrade, J., Paul, L., Miller, L., Creanor, S., Stevens, K., Green, C., Ewings, P., Barton, A., Berrow, M., Vickery, J., Marshall, B., Zajicek, J. P. & Freeman, J., 1 Jun 2019, In : Health Technology Assessment. 23, 27, p. 1-166

    Research output: Contribution to journalArticle

  4. Improving the quality of cognitive screening assessments: ACEmobile, an iPad-based version of the Addenbrooke's Cognitive Examination-III

    Newman, C. G. J., Bevins, A. D., Zajicek, J. P., Hodges, J. R., Vuillermoz, E., Dickenson, J. M., Kelly, D. S., Brown, S. & Noad, R. F., 2018, In : Alzheimer's & Dementia: Diagnosis, Assessment & Disease Monitoring. 10, p. 182-187 6 p.

    Research output: Contribution to journalArticle

  5. Balance Right in Multiple Sclerosis (BRiMS): a guided self-management programme to reduce falls and improve quality of life, balance and mobility in people with secondary progressive multiple sclerosis: a protocol for a feasibility randomised controlled trial

    Gunn, H., Andrade, J., Paul, L., Miller, L., Creanor, S., Green, C., Marsden, J., Ewings, P., Berrow, M., Vickery, J., Barton, A., Marshall, B., Zajicek, J. & Freeman, J. A., 27 Jul 2017, In : Pilot and Feasibility Studies. 4, 12 p., 26.

    Research output: Contribution to journalArticle

ID: 253425361