Journal of Internet of Things and Convergence (사물인터넷융복합논문지)

The Korea Internet of Things Society (한국사물인터넷학회)
권호 표지
DOI QR코드

DOI QR Code

A Study of Artificial intelligence technology to improve cognitive rehabilitation training efficiency

인지재활 훈련 효율증진을 위한 인공지능 기술 연구

  • Received : 2023.05.06
  • Accepted : 2023.07.07
  • Published : 2023.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

As society enters an aging population, the increase in the elderly population has raised concerns about health issues among the elderly, particularly dementia and mild cognitive impairment, which have become social issues. As of 2021, the ratio of dementia patients and individuals with mild cognitive impairment to the elderly population was approximately 11%, highlighting the importance of cognitive rehabilitation training. Cognitive rehabilitation training is actively being introduced as one of the treatments in nursing homes and elderly welfare centers, primarily conducted by assigning standardized performance tasks in a structured environment to train specific cognitive domains. To enhance the effectiveness of cognitive rehabilitation training, it is necessary to analyze each cognitive domain (such as attention, memory, language, executive function) and propose personalized cognitive rehabilitation training methods for individuals. In this study, we have proposed a method for utilizing artificial intelligence technology to establish universal and objective criteria for training in seven cognitive domains based MMSE-DS protocol. We have implemented user-customized training content based on an analysis of the user's abilities with the aim of utilizing it in cognitive rehabilitation training.

고령화사회에 접어들며 노인 인구가 증가함과 동시에, 노인의 건강문제 또한 사회문제로 대두되었다. 2021년 기준 노인 인구 대비 치매상병자 및 경도인지장애환자 비율은 약 11%로 인지 재활 훈련의 중요성이 부각되고 있다. 인지재활 훈련은 요양병원 및 노인 복지소에서 적극 도입중인 치료의 하나로, 주로 구조화된 환경에서 특정 인지 영역을 훈련시키기 위해 표준화된 수행 과제를 부여하는 방식으로 진행되고 있다. 인지재활 훈련의 효용성을 증진시키기 위해서는 인지능력의 각 영역(지남력, 기억력, 주의집중력, 계산능력, 시지각능력, 언어능력, 실행능력) 에 대한 분석과 그에 따른 환자 맞춤형 인지재활 훈련 방안의 제시가 필요하다. 본 연구에서는 인공지능 기술을 활용하여 7가지 인지영역 훈련에 대해 범용적이고 객관적인 기준을 인지재활 평가 프로토콜 MMSE-DS 기반으로 설계하였으며, 사용자의 능력 분석을 통해 사용자 맞춤형 훈련 콘텐츠를 구현하여 인지 재활 훈련에 활용하는 방안을 제시하였다.

Keywords

References

  1. Seonghun Kim, Woojin Kim, Yeonju Jang and Hyeoncheol Kim, "Development of Explainable AI-Based Learning Support System," The Journal of Korean Association of Computer Education, Vol.24, No.1, pp.107-115, 2021. https://doi.org/10.32431/KACE.2021.24.1.012
  2. Ye Won Song, A Young Song, Su Jin Kang, Ji Yeon Song, Hu Seon Choi and Byeong Jin Jeon, "The Effect of Computerized Cognition Program (RehaCom) on The Improvement of Cognitive Functions in patients with Schizophrenia," Korean Society of Cognitive Rehabilitation, Vol.4, No.1, pp65-79, 2015. https://doi.org/10.15268/ksim.2013.1.3.079
  3. Park Heesu, Moon Jong-Hoon and Jeong Byoung Lock, "The Effect of Cog. Dr. on Working Memory in Older Adults with Mild Dementia," RESKO, Vol.13, No.2, pp109-117, 2019.  https://doi.org/10.21288/resko.2019.13.2.109
  4. Kim, Minho, Jemin Park, and Najung Lee. "The effect of the computer-based cognitive rehabilitation program (CoTras) on the cognitive function and daily living activities of elderly stroke patients." Journal of the Korean Society of Integrative Medicine Vol.8, No.2, pp.121-130, 2020. https://doi.org/10.15268/KSIM.2020.8.2.121
  5. Lee, H. S., and J. L. Hyun. "The Effect of Tablet PC Cognitive Rehabilitation Training Games on the Improvement of Game Performance and Cognitive Ability of Non-Disabled and Intellectual Disability Children and Analysis of User Effectiveness." Journal of Intellectual Disabilities Vol.22, No.3, pp. 1-27, 2020. https://doi.org/10.35361/KJID.22.3.1
  6. Ahn, S. J., M. K. Lee, and H. Lee. "The effects of cognitive rehabilitation program developed by process-specific approach for chronic schizophrenics." Korean Journal of Clinical Psychology Vol.21, No.1, pp.13-28, 2022.
  7. Almond, Russell G., et al. "Modeling diagnostic assessments with Bayesian networks." Journal of Educational Measurement Vol.44, No.4, pp.341-359, 2007. https://doi.org/10.1111/j.1745-3984.2007.00043.x
  8. Kwon, Young Chul. "Korean version of mini-mental state examination (MMSE-K)." J Korean Neurol Association, Vol.28, No.1, pp.123-135, 1989.
  9. HAN, Ji-Won, et al. "A normative study of the Mini-Mental State Examination for Dementia Screening (MMSE-DS) and its short form (SMMSE-DS) in the Korean elderly." Journal of Korean Geriatric Psychiatry, Vol.14, No1, pp.27-37, 2010.
  10. Piech, Chris, et al. "Deep knowledge tracing." Advances in neural information processing systems, Vol.28, No.1, pp.1-9, 2015.
  11. Corbett, Albert T., and John R. Anderson. "Knowledge tracing: Modeling the acquisition of procedural knowledge." User modeling and user-adapted interaction, Vol.4, No.1, pp.253-278, 1994. https://doi.org/10.1007/BF01099821
  12. Kim, S., et al. "Development of Explainable AI-Based Learning Support System." The Journal of Korean Association of Computer Education, Vol.24, No.1, pp.107-115, 2021. https://doi.org/10.32431/KACE.2021.24.1.012
  13. Puterman, Martin L. "Markov decision processes." Handbooks in operations research and management science, Vol.2, No.1, pp.331-434, 1990. https://doi.org/10.1016/S0927-0507(05)80172-0
  14. Lim, Shiau Hong, Huan Xu, and Shie Mannor. "Reinforcement learning in robust markov decision processes." Advances in Neural Information Processing Systems, Vo.41, No4, pp.1325-1353, 2016.
  15. https://www.aihub.or.kr/aihubdata/data/view.do?currMenu=&topMenu=&aihugDataSe=realm&dataSetSn=133