Related Experiment Video
Updated: Jan 9, 2026
A Machine Learning Approach to Design an Efficient Selective Screening of Mild Cognitive Impairment
Published on: January 11, 2020
Development and Validation of a Culturally Adapted Interactive Game-Based Digital Tool for Screening Mild Cognitive
Ruike Sun1, Yu Wang1, Yuqing Xie1
1National Clinical Research Center for Geriatrics (West China Hospital of Sichuan University), Nursing Key Laboratory of Sichuan Province, Healthcare lnnovation Research Laboratory, West China Hospital, West China School of Nursing, Sichuan University, Chengdu, Sichuan, China.
Objectives:
This study aimed to develop and validate a game-based digital cognitive assessment tool integrating gaming scenarios and Chinese cultural elements (IGD-CAT) to screen for mild cognitive impairment (MCI) in China, and to assess its concurrent and discriminative validity.
Design:
A cross-sectional methodological study was conducted to develop and validate the IGD-CAT.
Setting And Participants:
A total of 218 participants were recruited from community and hospital settings between July 2023 and February 2024. All participants underwent traditional cognitive assessments, followed by IGD-CAT administration, and were classified into either normal cognition (NC) or MCI groups.
Methods:
A theoretical framework was established through a literature review, expert panel, and Delphi survey. The IGD-CAT was then developed through medical-engineering collaboration. Concurrent validity was evaluated by correlating IGD-CAT scores with Montreal Cognitive Assessment (MoCA) results. A random forest model was developed to assess the discriminatory validity of IGD-CAT in screening individuals with MCI.
Results:
The IGD-CAT comprises 14 tasks assessing 7 cognitive domains: time orientation, attention, memory, language, calculation, visuospatial abilities, and executive function. Among 196 participants (mean age 63.6 ± 5.81 years), 93 were classified as MCI and 103 as NC. Task scores showed significant positive correlations with MoCA (r = 0.140-0.387), whereas completion times correlated negatively (r = -0.476 to -0.168). The total IGD-CAT score correlated with MoCA (r = 0.529, P < .001), and total time correlated negatively (r = -0.549, P < .001), indicating that higher scores and shorter completion times were associated with better cognitive performance. The random forest model demonstrated strong classification performance, with 89.65% sensitivity, 96.55% specificity, and an area under the curve of 0.96.
Conclusions And Implications:
The IGD-CAT assesses a comprehensive range of cognitive domains, is time efficient, and features an age-friendly design. With high sensitivity, specificity, and accuracy, the IGD-CAT is well-suited for implementation in primary health care settings, communities, hospitals, and home environments.
More Related Videos
06:58Highlighting and Reducing the Impact of Negative Aging Stereotypes During Older Adults' Cognitive Testing
Published on: January 24, 2020
07:31A Computerized Functional Skills Assessment and Training Program Targeting Technology Based Everyday Functional Skills
Published on: February 13, 2020
