Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: JMIR Serious Games

Date Submitted: Mar 20, 2025
Date Accepted: Jul 9, 2025

The final, peer-reviewed published version of this preprint can be found here:

Vision AI-Based Gamified Cognitive Prosthesis for Executive Function: Feasibility and Usability Study

Siow CY, Yang YH, Tsai CJ, Yang WW, Hu CJ, Sung JY, Tani J

Vision AI-Based Gamified Cognitive Prosthesis for Executive Function: Feasibility and Usability Study

JMIR Serious Games 2025;13:e74157

DOI: 10.2196/74157

PMID: 41052508

PMCID: 12500313

Vision Artificial Intelligence-based Gamified Cognitive Prosthesis for Executive Function: A Pilot Study

  • Co Yih Siow; 
  • Yao-Hua Yang; 
  • Cheng-Jui Tsai; 
  • Wan-Wan Yang; 
  • Chaur-Jong Hu; 
  • Jia-Ying Sung; 
  • Jowy Tani

ABSTRACT

Background:

Dementia is a challenging disease marked by cognitive decline and functional impairment, contributing significantly to global health. Progression of dementia leads to increasingly diminishing independence and caregiver burden, highlighting the importance of improving executive functions in early-stage patients. To address this challenge, a novel gamified cognitive prosthesis—simulating egg-cooking task—was developed to replicate sequential actions and train the executive functions required in daily life, as well as providing real-time feedback according to an individual’s performance.

Objective:

Our study aims to investigate whether an interactive, artificial intelligence (AI)-based cognitive prosthesis could enhance executive function and reduce task-completion time on people with mild dementia.

Methods:

Patients with mild dementia (n=12) and healthy controls (n=7) were recruited for this study. Participants were instructed to perform a simple cooking task (egg boiling) with and without visual and auditory cues provided by the executive function cognitive prosthesis. The “Daily task completion test” and a modified executive function performance test (EFPT) were performed in both conditions.

Results:

Among the participants with mild dementia, the use of the executive function cognitive prosthesis has shown to significantly reduce task completion time from 134.75 seconds (92.50-134.75) to 92.00 seconds (65.00-92.00, P = 0.03) and to significantly improve modified EFPT score from 4.25 seconds (1.75-4.25) to 1.00 (0.00-1.00, P <0.01). These findings represent a 31.7% decrease in completion time and a 76.5% improvement in executive function performance scores.

Conclusions:

This pilot study provides preliminary evidence that an AI-based cognitive prosthesis can meaningfully improve task efficiency and executive function in individuals with mild dementia, and may pave the way for a new generation of cognitive enhancement device. Clinical Trial: This study is an evaluation study and not a randomized controlled trial, and therefore is not registered in the clinicaltrial.gov.


 Citation

Please cite as:

Siow CY, Yang YH, Tsai CJ, Yang WW, Hu CJ, Sung JY, Tani J

Vision AI-Based Gamified Cognitive Prosthesis for Executive Function: Feasibility and Usability Study

JMIR Serious Games 2025;13:e74157

DOI: 10.2196/74157

PMID: 41052508

PMCID: 12500313

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.