End User and Primary Care Physicians’ Perspectives on Digital Innovations in Dementia Risk Detection: Focus on a Digital Sleep Biomarker
Bibliographic record
Abstract
BACKGROUND: Dementia is a global health priority. Early identification in asymptomatic or mildly symptomatic individuals (ie, dementia risk detection) is proposed as a clinical solution for early intervention and could support researchers to identify novel neuropathological targets and recruit to clinical trials. Digital biomarkers of behavioral or physiological markers, including sleep, are cited as a potential low-cost, noninvasive, and objective method for dementia risk detection. Understanding perspectives on digital biomarkers, particularly acceptability, from potential end users and clinical staff is required when considering implementation within any clinical service. With emerging evidence of sleep as a risk marker for dementia, the efficacy of the Dementia Research Institute Sleep Index (DRI-SI), based on continuous remote monitoring of sleep patterns detected by a digital sleep mat, for dementia risk detection, is currently being explored by the InSleep46 study. OBJECTIVE: This qualitative substudy aimed to explore perspectives of potential end users and primary care physicians regarding the use of a digital sleep mat to measure the DRI-SI and its application towards dementia risk detection. METHODS: Thirty-one potential end users (age: 31-82 years, 11 female and 20 male) from Newcastle and London, United Kingdom, with personal or caregiving experience related to dementia, participated in qualitative focus group workshops. They shared opinions on integrating the sleep mat into their homes, the DRI-SI's potential for identifying dementia risk, and the necessary information for engagement with related clinical services. Seven primary care physicians from across England participated in semistructured interviews regarding the potential application of the DRI-SI in dementia risk detection and its integration into current clinical practice. Inductive thematic analysis was conducted to identify key themes. RESULTS: Four key themes emerged from end user focus groups: (1) practical use, (2) prospective acceptability, (3) clinical management, and (4) data concerns. Three main themes came from the semistructured interviews with physicians: (1) prospective acceptability, (2) health care provision, and (3) practical considerations. Common themes were identified in both groups but held differing perspectives. End users were focused on practical aspects of integrating the digital sleep mat within their daily life, the effect of the DRI-SI on clinical care, and privacy concerns regarding data use. Primary care physicians were concerned more broadly with how the DRI-SI and dementia risk detection service would integrate into current clinical practice, the impact on clinical resources and patient well-being, and the need for clinical actionability and guidance on discussing results with patients. CONCLUSIONS: End users would find the DRI-SI acceptable as part of their clinical care, but primary care physicians require a more robust evidence base. Future research should explore the integration of the DRI-SI into clinical care/research pathways to enhance clinical acceptability. Five key recommendations have been made for further development of digital biomarkers for dementia risk populations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.028 | 0.041 |
| Meta-epidemiology (narrow) | 0.000 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.008 | 0.009 |
| Scholarly communication | 0.009 | 0.006 |
| Open science | 0.001 | 0.009 |
| Research integrity | 0.005 | 0.006 |
| Insufficient payload (model declined to judge) | 0.004 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".