Currently submitted to: Journal of Medical Internet Research
Date Submitted: Nov 14, 2026
Open Peer Review Period: Nov 15, 2026 - Jan 10, 2027
(currently open for review)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Construction and usability evaluation of a cognitive rehabilitation assessment and training system platform for MCI elderly people based on human-computer interaction
ABSTRACT
Background:
Mild cognitive impairment (MCI) is associated with an increased risk of cognitive decline, highlighting the need for accessible and individualized cognitive rehabilitation approaches. Human-computer interaction (HCI) technologies may provide new opportunities for digital cognitive assessment and training in older adults with MCI. However, the development of age-friendly platforms that integrate multimodal interaction and multidomain cognitive training remains challenging.
Objective:
This study aimed to develop an HCI-based cognitive rehabilitation assessment and training platform for older adults with MCI and evaluate its preliminary usability and user acceptability.
Methods:
This study comprised four phases. First, a literature review and evidence synthesis were conducted to identify relevant components and design considerations for digital cognitive assessment and training. Second, two rounds of Delphi expert consultation involving 15 experts were conducted to establish and refine the platform's functional and design indicators. Third, the platform was developed based on HCI theory, cognitive reserve theory, and age-friendly design principles. Finally, a mixed-methods usability evaluation was conducted with 15 older adults with MCI recruited from a nursing home in Suzhou, China. Data were collected through representative task testing, the System Usability Scale (SUS), and semistructured interviews. Quantitative data were analyzed descriptively, while interview findings were summarized to identify perceived benefits and usability barriers.
Results:
The developed platform integrated cognitive assessment, multidomain game-based training targeting memory, executive function and attention, language, visuospatial function, and calculation, and multimodal interaction through touch-based, eye-tracking-based, and gesture-based technologies. It also provided automated feedback on training performance, including task accuracy, duration, and difficulty. During the Delphi consultation, the expert authority coefficient was 0.84, and Kendall's coefficient of concordance indicated statistically significant agreement in both rounds (P<0.01). In task testing, completion rates for accessing the assessment module, completing cognitive assessment, selecting a training task, performing cognitive training, and viewing training results were 100%, 86.67%, 100%, 80%, and 86.67%, respectively. Difficulties were mainly related to understanding task instructions, completing time-limited activities, eye-tracking recognition, and locating navigation controls. The mean SUS score was 74.67 (SD 8.81). Interview findings indicated positive perceptions of the variety of training activities, graded difficulty, and interactive features. However, participants also reported insufficient on-screen instructions, limited response time, visually complex backgrounds, small font sizes in some sections, and occasional eye-tracking inaccuracies. All 15 participants expressed willingness to continue using the platform.
Conclusions:
The HCI-based platform demonstrated preliminary usability and acceptability among older adults with MCI. Combining multidomain cognitive training with multimodal interaction may provide a feasible approach to digital cognitive rehabilitation. Nevertheless, the identified operational and interaction barriers highlight the need for further age-friendly optimization. Larger studies and longitudinal evaluations are warranted to assess sustained engagement, usability in different settings, and potential clinical benefits.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© 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.