Dementia could be detected via routinely collected data

A new machine-learning model that scans routinely collected NHS data has shown promising signs of being able to predict undiagnosed dementia in primary care. The results from the feasibility study suggest that the model could significantly reduce the number of those living with undiagnosed dementia | BJGP Open | via ScienceDaily


Improving dementia care through increased and timely diagnosis is a priority for the NHS, yet around half of those living with dementia are unaware they live with the condition. Now a new machine-learning model that scans routinely collected NHS data has shown promising signs of being able to predict undiagnosed dementia in primary care.

Led by the University of Plymouth, the study collected Read-encoded data from 18 consenting GP surgeries across Devon, UK, for 26,483 patients aged over 65. The Read codes — a thesaurus of clinical terms used to summarise clinical and administrative data for UK GPs — were assessed on whether they may contribute to dementia risk, with factors included such as weight and blood pressure. These codes were used to train a machine-learning classification model to identify patients that may have underlying dementia.

The results showed that 84% of people who had dementia were detected as having the condition (sensitivity value) while 87% of people without dementia had been correctly acknowledged as not having the condition (specificity value), according to the data.

These results indicate that the model can detect those with underlying dementia with an accuracy of 84%. This suggests that the machine-learning model could, in future, significantly reduce the number of those living with undiagnosed dementia — from around 50% (current estimated figure) to 8%.

Full story at ScienceDaily

Full reference:  Jammeh, E. A. et al. | Machine-learning based identification of undiagnosed dementia in primary care: a feasibility study | BJGP Open |  2018

After diagnosis of dementia: what to expect from health and social care services

Department of Health and Social Care | May 2018 | After diagnosis of dementia: what to expect from health and social care services

A new report from the Department of Health and Social Care examines the role of advanced care planning and explores the barriers to its implementation as identified by people with incurable cancer and health and social care professionals.  It also examines opportunities for change and sets out responsibilities of governments and policy makers.

This document is for anyone diagnosed with dementia and the people who care for them. It has details about what support they should get.  It also includes information about:

  • what is in a care plan
  • how health care and social care services can help
  • support available to family and friends who are carers
  • how to take part in research

The full guidance is available to read from Department of Health and Social Care 

Hospitals do not recognise dementia in a third of patients admitted with other conditions

Hospitals fail to recognise dementia in a third of patients who have already had the condition diagnosed if they are admitted to hospital for a different reason | Alzheimer’s and Dementia | via BMJ


Researchers reviewed data on 21 387 patients aged over 65 who had been assessed at South London and Maudsley NHS Foundation Trust memory clinics from 2008 to 2006. A total of 8246 people had dementia diagnosed and were then admitted to general hospitals 37 329 times after their diagnosis.

The results, published in Alzheimer’s and Dementia, showed that 6429 patients (78%) had a dementia diagnosis recorded at some point in their hospital records. The proportion of all individual hospital records that included dementia was 50.3% and, among the 26 894 non-elective hospital admissions, the proportion was 63.3%.

Hospitals were more likely to miss dementia in patients who were younger, single, had more physical illness, had better cognitive function and less agitation or activity of daily living impairment, or were from an ethnic minority group.

Full story at BMJ

Full article: Sommerlad A, et al. | Accuracy of general hospital dementia diagnoses in England: sensitivity, specificity, and predictors of diagnostic accuracy 2008-2016 | Alzheimer’s and Dementia | published online 24 April 2018

The diagnostic accuracy of automated tests for cognitive impairment

Review finds some promising results for identifying MCI and early dementia, but notes shortcomings within available evidence | International Journal of  Geriatric Psychiatry

The aim of this review is to determine whether automated computerised tests accurately identify patients with progressive cognitive impairment and, if so, to investigate their role in monitoring disease progression and/or response to treatment.

Six electronic databases (Medline, Embase, Cochrane, Institute for Scientific Information, PsycINFO, and ProQuest) were searched from January 2005 to August 2015 to identify papers for inclusion. Studies assessing the diagnostic accuracy of automated computerised tests for mild cognitive impairment (MCI) and early dementia against a reference standard were included. Where possible, sensitivity, specificity, positive predictive value, negative predictive value, and likelihood ratios were calculated. The Quality Assessment of Diagnostic Accuracy Studies tool was used to assess risk of bias.

Sixteen studies assessing 11 diagnostic tools for MCI and early dementia were included. No studies were eligible for inclusion in the review of tools for monitoring progressive disease and response to treatment. The overall quality of the studies was good. However, the wide range of tests assessed and the non‐standardised reporting of diagnostic accuracy outcomes meant that statistical analysis was not possible.

Some tests have shown promising results for identifying MCI and early dementia. However, concerns over small sample sizes, lack of replicability of studies, and lack of evidence available make it difficult to make recommendations on the clinical use of the computerised tests for diagnosing, monitoring progression, and treatment response for MCI and early dementia. Research is required to establish stable cut‐off points for automated computerised tests used to diagnose patients with MCI or early dementia.

Aslam, R. W. et al. | A systematic review of the diagnostic accuracy of automated tests for cognitive impairment | International Journal of  Geriatric Psychiatry | Volume 33, Issue 4 | April 2018 | Pages 561-575

Diagnostic pathway for patients with cognitive impairment

Study finds that cognitive impairment is commonly not diagnosed at the earliest stages of the disease and efforts should be made towards public awareness and earlier disease detection and intervention |  Journal of Alzheimer’s Disease | Centre for Dementia Prevention



To ensure that patients with dementia and their caregivers receive appropriate treatment and support, early diagnosis is essential but remains challenging.

Real-world data from a multi-national, cross-sectional survey of physicians and their patients were analyzed to quantify the diagnostic pathway for dementia, including a focus on severity of patients’ cognitive impairment (CI) at the time of symptom onset, referral and subsequent diagnosis.

Data were collected for 7,620 patients with CI. Most patients saw a healthcare professional within 1 year of first symptoms and received a diagnosis within 3–7 months of initial consultation.  However, only 20% of patients received a diagnosis before their disease progressed beyond the prodromal stage and 23.5% already had moderate CI at diagnosis.

These findings show that the goal of identifying and diagnosing CI at the earliest stages of disease is, for many patients, not achieved. Efforts toward public awareness and proactive, earlier detection and intervention, must be maintained—indeed where possible invigorated.

More detail at Centre for Dementia Prevention

Full reference: Ritchie, C et al. | Quantifying the Diagnostic Pathway for Patients with Cognitive Impairment: Real-World Data from Seven European and North American CountriesJournal of Alzheimer’s Disease |  2018 vol. 62, no. 1 |  pp. 457-466

A roadmap to advance dementia research in prevention, diagnosis, intervention, and care by 2025

Pickett JBird CBallard C, et al. | A roadmap to advance dementia research in prevention, diagnosis, intervention, and care by 2025 | International Journal of Geriatric Psychiatry  201817


  • A broad-based taskforce of researchers, clinicians, UK funders of dementia research, people with dementia, and carer representatives was convened to generate consensus on research ambitions in prevention, diagnosis, intervention, and care for people with dementia.
  • Five goals and 30 recommendations that align with current national dementia strategies and plans were produced. A 10-point action plan was developed to support the delivery of these goals.



National and global dementia plans have focused on the research ambition to develop a cure or disease-modifying therapy by 2025, with the initial focus on investment in drug discovery approaches. We set out to develop complementary research ambitions in the areas of prevention, diagnosis, intervention, and care and strategies for achieving them.


Alzheimer’s Society facilitated a taskforce of leading UK clinicians and researchers in dementia, UK funders of dementia research, people with dementia, and carer representatives to develop, using iterative consensus methodology, goals and recommendations to advance dementia research.


The taskforce developed 5 goals and 30 recommendations. The goals focused on preventing future cases of dementia through risk reduction, maximising the benefit of a dementia diagnosis, improving quality of life, enabling the dementia workforce to improve practice, and optimising the quality and inclusivity of health and social care systems. Recommendations addressed gaps in knowledge and limitations in research methodology or infrastructure that would facilitate research in prioritised areas. A 10-point action plan provides strategies for delivering the proposed research agenda.


By creating complementary goals for research that mirror the need to find effective treatments, we provide a framework that enables a focus for new investment and initiatives. This will support a broader and more holistic approach to research on dementia, addressing prevention, surveillance of population changes in risk and expression of dementia, the diagnostic process, diagnosis itself, interventions, social support, and care for people with dementia and their families.

Full document: A roadmap to advance dementia research in prevention, diagnosis, intervention, and care by 2025

Young onset dementia decision making guide for GPs

The Young Dementia Network has created a young onset decision making guide for GPs.

This guide aims to support GPs in identifying the most common signs and symptoms of young onset and rarer forms of dementia. It aims to help GPs identify ‘red flags’ which suggest referral to specialist diagnostic services may be required.

gp guide
Image source:

Key facts:

• Over 42,000 people are living with young onset dementia in the UK.

• It takes on average 4.4 years for younger people to be diagnosed, twice as long as older people, delaying access to treatment and support.

• Many younger people are misdiagnosed with depression, anxiety, stress, marital issues, menopause or personality disorder.

Download the guide by visiting Young Dementia UK

Full document: Diagnosing dementia in younger people:
A decision-making guide for GPs

New research shows where in the brain the earliest signs of Alzheimer’s occur

Researchers have convincingly shown where in the brain the earliest signs of Alzheimer’s occur.  Nature Communications | Story via ScienceDaily

In Alzheimer’s, the initial changes in the brain occur through retention of the protein, ?-amyloid (beta-amyloid). The process begins 10-20 years before the first symptoms become noticeable in the patient.

In Nature Communications, a research team has presented results showing where in the brain the initial accumulation of ?-amyloid occurs.  It is hoped that the discovery could potentially become significant to future Alzheimer’s research while contributing to improved diagnostics.

Full story at ScienceDaily

Link to the research: Palmqvist, S et al. Earliest accumulation of β-amyloid occurs within the default-mode network and concurrently affects brain connectivity. Nature Communications, 2017; 8 (1)

The prevalence of comorbid cancer and dementia

Findings suggest that dementia is associated with poorer cancer outcomes

Objectives: A comorbid diagnosis of cancer and dementia (cancer–dementia) may have unique implications for patient cancer-related experience. The objectives were to estimate prevalence of cancer–dementia and related experiences of people with dementia, their carers and cancer clinicians including cancer screening, diagnosis, treatment and palliative care.

Method: Databases were searched  using key terms such as dementia, cancer and experience. Inclusion criteria were as follows: (a) English language, (b) published any time until early 2016, (c) diagnosis of cancer–dementia and (d) original articles that assessed prevalence and/or cancer-related experiences including screening, cancer treatment and survival. Due to variations in study design and outcomes, study data were synthesised narratively.

Results: Forty-seven studies were included in the review with a mix of quantitative (n = 44) and qualitative (n = 3) methodologies. Thirty-four studies reported varied cancer–dementia prevalence rates (range 0.2%–45.6%); the others reported reduced likelihood of receiving: cancer screening, cancer staging information, cancer treatment with curative intent and pain management, compared to those with cancer only. The findings indicate poorer cancer-related clinical outcomes including late diagnosis and higher mortality rates in those with cancer–dementia despite greater health service use.

Conclusions: There is a dearth of good-quality evidence investigating the cancer–dementia prevalence and its implications for successful cancer treatment. Findings suggest that dementia is associated with poorer cancer outcomes although the reasons for this are not yet clear. Further research is needed to better understand the impact of cancer–dementia and enable patients, carers and clinicians to make informed cancer-related decisions.

Full reference: L. McWilliams, C et al. | A systematic review of the prevalence of comorbid cancer and dementia and its implications for cancer-related care | Aging & Mental Health |  Published online: 18 Jul 2017

Delayed-onset post-traumatic stress disorder symptoms in dementia

In this review, Tarun Kuruvilla et al. consider three examples of delayed-onset PTSD and its frequent association, or misdiagnosis, as one of the numerous manifestations of the behavioural and psychological symptoms of dementia | Progress in Neurology and Psychiatry

Image source: Progress in Neurology and Psychiatry

Dementia sufferers commonly experience non-cognitive symptoms as their disease progresses. These symptoms are often labelled as behavioural and psychological symptoms of dementia (BPSD) and encompass a broad range of symptoms relating to mood changes such as depression and anxiety, psychosis, and inappropriate behaviours like wandering, shouting and agitation. Post-traumatic stress disorder (PTSD) is a common diagnosis amongst working-age adults but it is infrequently diagnosed in the elderly, particularly those with dementia. Previous case reports have published examples of dementia sufferers experiencing post-traumatic stress disorder symptoms long after the original traumatic event. Despite these examples, little is known about the manifestation of traumatic exposure in the older adult population. We consider whether delayed-onset post-traumatic symptoms in the elderly are being misdiagnosed, instead falling under the umbrella of BPSD. In this article, we attempt to expand on previous work by describing three cases of delayed-onset PTSD associated with the development of dementia. We explore potential biological and psychosocial theories to explain the aetiology of these symptoms with reference to the literature. We end by considering the clinical implications for future practice, including suggestions for improved diagnosis and management.

Full reference: Martinez-Clavera, C. et al. (2017) Delayed-onset post-traumatic stress disorder symptoms in dementia. Progress in Neurology and Psychiatry. Vol. 21 (no. 03).