Managing Cognitive Decline Through a Social Robot–Based Intervention: Protocol for the engAGE Proof of Concept and Randomized Controlled Trial (Preprint)
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
<sec> <title>BACKGROUND</title> Dementia is challenging society in terms of the quality of life, the costs of health care systems, and caregivers’ burden. Dementia is often preceded by a status of mild cognitive impairment (MCI), during which a healthy lifestyle and cognitive therapy seem to be effective in counteracting the decline. </sec> <sec> <title>OBJECTIVE</title> The engAGE (Managing Cognitive Decline Through Theatre Therapy, Artificial Intelligence, and Social Robot–Driven Interventions) project aimed to build a technological platform to counteract cognitive decline in older adults with MCI through both cognitive therapy and lifestyle management. </sec> <sec> <title>METHODS</title> The engAGE platform was built around the social robot Pepper, which provides cognitive therapy. An activity tracker and a mobile app were also integrated within the platform to help older adults with MCI monitor their sleep and physical activity, in addition to offering cognitive games at home. The proof of concept (PoC) of engAGE was designed as a 6-month long randomized controlled trial (RCT) aimed to test the solution in three European countries: Italy, Switzerland, and Norway. During this period, under the supervision of a psychologist or a therapist, Pepper provided cognitive therapy on a weekly basis at health care or daycare facilities. In parallel, the use of the mobile app and the activity tracker was recommended on a daily basis. Participants were recruited through health care institutions and care organizations and evaluated through face-to-face interviews. The primary interest of the study was to assess the impact of engAGE on cognitive capacity through the Montreal Cognitive Assessment (MoCA) and the Memory Assessment Clinic Questionnaire (MAC-Q). In addition, changes in social engagement and quality of life were measured through the University of California, Los Angeles (UCLA) Loneliness Scale and the Warwick-Edinburgh Mental Well-Being Scale (WEMWBS). The PoC also focused on the acceptability and usability of engAGE, evaluated through the System Usability Scale (SUS) and the Unified Theory of Acceptance and Use of Technology (UTAUT) questionnaire. In addition, data were collected regarding the frequency of weekly sessions and access to the mobile app, as well as activity tracker measurements. </sec> <sec> <title>RESULTS</title> Data collection commenced in November 2023 and finished in July 2024, with the enrollment of 49 older adults with MCI (n=40, 81.6%, assigned to the experimental group [EG] and n=9, 18.4%, to the control group [CG]) conducted from October 2023 to April 2024. Data analysis was concluded in November 2024, and results will be published by 2026. </sec> <sec> <title>CONCLUSIONS</title> The engAGE PoC represents an innovative study focused on the impact of a technology-based multidomain intervention designed for older adults with MCI that aimed to counteract cognitive decline through cognitive training, as well as improvement in terms of the quality of life, social engagement, physical activity, and sleep quality of primary end users. </sec> <sec> <title>CLINICALTRIAL</title> ClinicalTrials.gov NCT06302686; https://clinicaltrials.gov/study/NCT06302686 </sec> <sec> <title>INTERNATIONAL REGISTERED REPORT</title> RR1-10.2196/67601 </sec>
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.
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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 it