Vision AI-Based Gamified Cognitive Prosthesis for Executive Function: Feasibility and Usability Study
Bibliographic record
Abstract
Background: Dementia is a progressive neurodegenerative condition marked by cognitive decline and loss of functional independence. Among cognitive domains, executive dysfunction is a critical early contributor to reduced self-care capacity and increased caregiver burden. While cognitive assistive technologies have focused primarily on memory, few tools address executive function in real-time, daily tasks. To fill this gap, we developed a novel gamified cognitive prosthesis that integrates artificial intelligence (AI) and computer vision to guide users step-by-step through a simulated egg-cooking task. This system provides real-time audiovisual feedback to support planning, sequencing, and error correction. Objective: This study aimed to evaluate whether the AI-based cognitive prosthesis improves task completion time and executive function performance in individuals with mild dementia. Methods: We conducted a pilot study involving 12 patients with mild dementia and 7 age-matched healthy controls. Participants were asked to complete a 6-step gamified egg boiling task under 2 conditions: with and without guidance. The task was evaluated using a custom "Daily Task Completion Test" and a modified executive function performance test (EFPT) adapted to the cooking activity. Demographic and clinical data (age, sex, education, Mini-Mental State Examination, Clinical Dementia Rating, activities of daily living, instrumental activities of daily living, and Dementia Severity Rating Scale) were recorded. The System Usability Scale (SUS) was also collected postintervention. Results: In the mild dementia group, AI assistance significantly reduced median task completion time from 134.75 (IQR 92.50-134.75) to 92.00 (IQR 65.00-92.00; P=.03) seconds, and significantly improved the Executive Function Performance Test (EFPT) scores from 4.25 (IQR 1.75-4.25) to 1.00 (IQR 0.00-1.00; P=.005), reflecting a 31.7% improvement in efficiency and a 76.5% reduction in required assistance. No significant changes were observed in the control group. The mean SUS score was 80.53 (SD 24.97), indicating high usability. The AI system achieved a cumulative recognition precision of 0.93 (SD 0.07) and cumulative recall of 0.94 (SD 0.11). Conclusions: This pilot study provides preliminary evidence that an AI-based cognitive prosthesis can enhance executive function and task performance in individuals with mild dementia. The results support the feasibility of using real-time AI guidance in everyday tasks to promote independence. Given its modular design and promising usability profile, this system may serve as the foundation for future digital therapeutics targeting executive dysfunction. Larger, longitudinal studies are warranted to evaluate sustained cognitive and functional benefits.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".