Worldwide, national dementia strategies emphasize the need for improving the diagnostic pathway at the point of primary care toward timely diagnosis. Currently, general practitioner (GP) clinical judgement of cognitive impairment is the basis of referral initiation to specialist services. Existing primary care cognitive assessment tools (eg, the General Practitioner Assessment of Cognition [GPCOG], the Mini-Cog, and the Six-Item Cognitive Impairment Test [6CIT]), are crude or time-consuming screening instruments which can only detect cognitive impairment when it is well established. Dementia is difficult to diagnose; in a study concerning false positive diagnoses, 60% of GPs misdiagnosed dementia [1]. More detailed tests deployed in secondary care are expensive and often physically and psychologically intrusive for the patient (eg, lumbar puncture). As a result, many false positives are identified in referred patients. A key limitation of existing screening tests is the lack of robust evidence to support them; few have been well validated in the populations for which they are intended.

Figure 1 demonstrates the dementia diagnostic pathway for patients. Patients who are referred by their GP are triaged. At the memory clinic, patients undergo 2 appointments; the first is typically conducted by a nurse and involves administration of a cognitive assessment. At the second appointment (the diagnostic clinic visit), conducted by a dementia medical specialist, the patient receives the outcome of the assessment (see “Outcomes” within Figure 1 for examples of typical outcomes).

The COVID-19 pandemic has effectively brought clinical practice in the memory services to a standstill. Nationally, memory services have adapted to the new environment by moving to remote patient assessments to continue meeting service user demand while reducing viral transmission [2]. However, the remote use of cognitive assessments has been variable, while there has been scant evaluation of the outcome of such a change in clinical practice [3]. Emerging research in remote memory clinics has highlighted computerized cognitive tests, such as the Integrated Cognitive Assessment (ICA), as prominent candidates for adoption in clinical practice both during the pandemic and for post-COVID-19 implementation as part of health care innovation [4].

The ICA is a 5-minute computerized cognitive test based on a rapid categorization task that employs an artificial intelligence model to improve its accuracy in detecting cognitive impairment [5]. The ICA is self-administered and independent of language [6,7]. The value proposition of the ICA is that an accurate and sensitive tool for diagnosis will streamline the diagnosis of dementia by reducing false positive results from GP referrals and, therefore, minimizing the need for further, expensive and time-consuming assessments.

In order to address this challenge, we initiated the Accelerating Dementia Pathway Technologies (ADePT) study. The intention of conducting this study is to develop a real-world evidence basis to support the adoption of ICA as an inexpensive screening tool for the detection of cognitive impairment to improve the efficiency of the dementia care pathway.

The ADePT study is an ongoing multicenter real-world evidence study. The objective of ADePT is to deliver real-world evidence on practices and the economic case for ICA adoption in memory clinics for the assessment of cognitive impairment associated with dementia, Alzheimer Disease (AD), mild cognitive impairment (MCI), and similar diseases, including the assessment of preferred business models by comparing the accuracy of GP referrals against the ICA.

The ADePT study was funded in January 2020 by Innovate UK (Project Number 105837). The first patient visit was conducted in November 2020.

As of September 2021, 86 participants have been recruited for the study, with 23 participants also completing a retest visit. Initially, the study was designed for in-person visits at the memory clinic; however, in light of the COVID-19 pandemic, the study was amended to allow remote as well as face-to-face visits.

The study was also expanded from a single site to 4 sites in the United Kingdom, based at the following trusts: Devon Partnership NHS Trust, North Bristol NHS Foundation Trust, Oxford Health NHS Foundation Trust, and Sussex Partnership NHS Foundation Trust.

We expect results to be published by the second quarter of 2022.

In summary, the ADePT project aims to improve the efficiency of the dementia pathway at its very beginning and supports systems integration at the intersection between primary and secondary care. The introduction of a standardized, self-administered, digital assessment tool for the timely detection of neurodegeneration as part of a decision-support system that can signpost accordingly can reduce unnecessary referrals, service backlog, and assessment variability.

Remote assessments in the post-COVID-19 clinical environment are expected to form a core part of frontline service delivery as both services and their service user attitudes change while the use of smartphones and tablet computers is expanding in older adults [8]. Early identification is key as evidenced by the Prime Minister’s Challenge in 2020 [9] and is now corroborated by the advent of novel disease-modifying treatments [10].

We hypothesize that the health economic benefits for such a decision support tool will overshadow the relatively low price of such a proprietary technology compared to pen and paper conventional tests that demand time and expertise most primary care practitioners may not have, in combination with limitations in their validity in prodromal dementia and invariable cultural and interpretation bias.

The main strength of this study is that it accommodates face-to-face and remote assessments as part of day-to-day practice in a memory service setting with minimal disruption to the pathway, while obtaining real-world data on participant experience and the acceptability of such a tool in a rapidly changing technological environment.

In the ADePT study, we investigate GP referrals to memory clinics, where GP colleagues have already made the clinical decision to refer to specialists. As a result, these cases may only be assessed as true or false positives based on prospective diagnosis of neurodegeneration or not.A more complete picture of the quality of primary care cognitive assessment would also require the study of true and false negatives (ie, those patients who were not referred to memory clinics by their GPs). This is a limitation of the study, albeit an unavoidable one as the latter would require multisite recruitment from GP surgeries and prospective participant follow-up which would be impractical. However, we expect that the ADePT results can inform a future longitudinal study in primary care.

To date, research on digital cognitive tests in primary care has been scant. A valid and acceptable tool can improve early diagnosis, provide timely interventions, enhance clinical and health economic outcomes, reduce burden on memory services, and foster interoperability and continuity of care throughout the patient journey in the dementia pathway. A remote assessment tool can also close the clinically important service gap that is the monitoring of disease progression both in already diagnosed patients and those with MCI. Monitoring of the latter patient group is particularly topical as there is no current service provision, as novel treatments are becoming available [10]. The ADePT project aims to provide appropriate evidence to support policy change to shape best practice guidelines in the dementia pathway. Finally, objective and consistent measurement of cognition for at-risk populations will support research and candidate identification in primary care for a disease that continues to take a toll on patients, services, and families.