Development and Evaluation of an Artificial Intelligence–Based Cognitive Exercise Game: A Pilot Study

Abstract

Recently, cognitive serious games have successfully been employed to train cognitive abilities in elderly people with mild cognitive impairment, Alzheimer’s disease, and related disorders. However, despite the continuous rehabilitation game design and its applications, the existing cognitive exercise games fall short of user interaction and personalized elements with regard to difficult levels, which leads to users leaving early and losing interests during the gameplay. In this regard, the purpose of the study was to design and develop the serious game inclusive of playful elements for user motivation, the web-based mobile application system for easy accessibility, and Artificial Intelligence– (AI–) based difficulty level adjustment system for prevention from earlier leaving out in the middle of the play so that the elderly users can feel entertaining and immersed into the cognitive game voluntarily. This study was designed as an eight-week pilot experiment with thirty-seven participants in their 60s to 80s for the game’s usability assessment purpose. Results of the study showed that the AI-based cognitive exercise game was acceptable, interesting, and motivating for the elderly people and the test results before and after the eight-week training suggest a relationship between longer the training on the game and lower cognitive assessment scores including geriatric quality of life scale, geriatric depression scale, and Korean version of mini-mental state examination (MMSE). These correlations demonstrate the potential value of serious games in clinical assessment of cognitive status for the elderly users with varying cognitive ability. Based on these results, the elderly-centered serious game with playful element can be potentially used in clinical settings, allowing the cognitive training to be more enjoyable and more medically effective. Given these promising results, a more focused study can extend to the game system or additional game tools or features to be explored that solely target the elderly by applying AI and advanced visualization devices.

Use of serious games with older adults: systematic literature review

“…The first one focused on improving memory, attention, executive function and language, while the other two focused on reaction time and processing speed. In turn, Eun et al (2022) study a series of cognitive mini-games for computers, smartphones, tablets, and other portable devices designed with artificial intelligence that facilitate older users to feel entertained and immersed in cognitive play voluntarily and to benefit from cognitive training. Ghorbani et al (2022) use augmented reality to develop a video game that not only provides cognitive training but also simultaneously examines the mental state of players to slow down the progression of potential cognitive problems and increase the quality of life of the individual.…”

Exploring the Potential of Artificial Intelligence in Individualized Cognitive Training: a Systematic Review

“…Six studies are not empirical in nature and provide from 2018)). According to the SIGN methodology for study design (Harbour and Miller (2001)), eleven used a controlled trial (n=8 non-randomised controlled trial and n=3 Individual randomized controlled trial) and two proposed either a case study (Wilms (2011)) or a non-comparative study (Eun et al (2022)). All the controlled trials included an active control group, either using a between-subject or within-subject design.…”

“…Reinforcement learning methods were commonly used, with three different algorithms employed: Q-learning (n=4), Bucket brigade (n=3), and Actor-critic (n=1). Additionally, Eun et al (2022) proposed a method utilizing deep learning, particularly Long Short-Term Memory (LSTM). The second category comprises six intelligent methods designed to extract valuable information from collected data, facilitating the generation of optimal pedagogical decisions.…”

“…Firstly, out of the seven studies that aimed to evaluate the progression of cognitive performance using pre-post assessments, three interventions (Eun et al (2022); Reidy et al (2020); Xu et al (2018)) employed either a crossover or a non comparative design, making it challenging to distinguish the impact of the control procedure from the individualized approach on cognitive performance. In the other hand, no significant differences in cognitive enhancement were found between the intervention and control groups in Solana et al (2014), indicating that the automated procedure's effectiveness matches that of the manual approach across a comprehensive neuropsychological assessment battery.…”

Artificial Intelligence in Dementia: A Bibliometric Study

“…The advent of AI research has presented exciting possibilities for the development of efficient and accessible tools that can aid in the early prediction of dementia [ 21 ]. Previous evidence has demonstrated the potential of AI to assist physicians in conducting specific tests and investigations for more effective management of dementia [ 22 , 23 , 24 ]. Our study findings show that the majority of research has focused on various aspects of dementia, including disease classification, diagnosis, prediction, segmentation, and early detection.…”