A Novel Game-Based Intelligent Test for Detecting Elderly Cognitive Function Impairment

Area of Science:

• Gerontology
• Cognitive Neuroscience
• Psychometrics

Background:

• Cognitive impairment is a growing concern in aging populations.
• Accurate and accessible cognitive assessment tools are crucial for early detection and intervention.
• Traditional cognitive tests may have limitations in engagement and administration.

Purpose of the Study:

• To explore the efficacy of the game-based intelligent test (GBIT) for cognitive assessment.
• To predict Mini-Mental State Examination (MMSE) scores and cognitive impairment risk using GBIT.
• To validate GBIT as a reliable and valid tool for evaluating elderly cognitive function.

Main Methods:

• Recruited 117 elderly subjects in Taiwan (mean age 79.92 ± 8.68).
• Employed multiple regression to analyze GBIT parameters (reaction, attention, coordination, memory) predicting MMSE scores.
• Utilized binary logistic regression to predict cognitive impairment risk.

Main Results:

• Gender, correct reactions, and correct memory positively predicted MMSE scores (R² = 0.69, p < 0.05).
• A decrease in correct reaction or memory questions significantly increased cognitive dysfunction risk (1.09x and 3.76x, respectively; p < 0.05).
• The model achieved 88.20% predictive power (84.00% sensitivity, 92.30% specificity).

Conclusions:

• GBIT demonstrates reliability and effectiveness in predicting cognitive function in the elderly.
• GBIT accurately identifies individuals at risk of cognitive impairment.
• GBIT is a feasible and valuable tool for assessing cognitive function in older adults.