MCI Cognitive Care App: An AI-Powered Personalized Platform for Cognitive Training in Mild Cognitive Impairment

References

[1] S. Belleville, S. Gilbert, F. Fontaine, S. Gagnon, D. Menard, and L.´ Gauthier, “Improvement of episodic memory in persons with mild cognitive impairment and healthy older adults: Evidence from a cognitive intervention program,” Neuro psychologia, vol. 44, no. 12, pp. 2161–2170, 2007.

[2] A. Bahar-Fuchs, M. Clare, and L. Woods, “Cognitive training and cognitive rehabilitation for mild cognitive impairment and early dementia: A systematic review and meta-analysis,” Neuropsychological Rehabilitation, vol. 23, no. 3, pp. 336–357, 2013.

[3] S. Belleville et al., “Five-year outcomes of cognitive training in individuals with mild cognitive impairment,” Alzheimer’s & Dementia, vol. 20, no. 1, pp. 45–56, 2024.

[4] B. M. Hampstead, “Toward the rational use of cognitive training in individuals with mild cognitive impairment,” Alzheimer’s & Dementia, vol. 19, no. 2, pp. 312–321, 2023.

[5] F. Stasolla, A. Caffo, and G. Perilli, “Integrating reinforcement learning` and virtual reality in neurocognitive rehabilitation,” Frontiers in Digital Health, vol. 5, 2023.

[6] J. Lumsden, E. A. Edwards, N. Lawrence, D. Coyle, and M. R. Munafo, “Gamification of cognitive assessment and cognitive training: ` A systematic review,” JMIR Serious Games, vol. 4, no. 2, e11, 2016.

[7] R. Hamaguchi et al., “Feasibility and reliability of mobile application-based screening for mild cognitive impairment,” Frontiers in Digital Health, vol. 7, 2025.

[8] C. Giuli, M. Papa, and G. Lattanzio, “Cognitive training in aging and mild cognitive impairment: A systematic review,” Journal of Alzheimer’s Disease, vol. 53, no. 3, pp. 1–17, 2016.

[9] N. H. A. Hamid and N. Zakaria, “Mobile- based cognitive retraining for individuals with mild cognitive impairment,” Journal of Aging Research, vol. 2024, Article ID 8821347.

[10] R. S. Sutton and A. G. Barto, “Reinforcement Learning: An Introduction,” MIT Press, 2nd ed., 2021.

[11] K. Anderson et al., “Gamified digital cognitive therapy for aging adults: Behavioural outcomes and adherence,” JMIR Aging, vol. 5, no. 3, e32145, 2022.

[12] L. Chandra, P. Mehta, and S. Kulkarni, “Adaptive bandit algorithms for personalized learning systems,” ACM Transactions on Interactive Intelligent Systems, vol. 13, no. 2, 2023.

[13] J. Kim and H. Park, “Human–AI collaboration for adaptive mental healthcare systems,” IEEE Access, vol. 12, pp. 58432– 58447, 2024.

[14] S. Weller et al., “Gamification effects in digital cognitive control training,” Frontiers in Psychiatry, vol. 13, 2022.

[15] S. Dauflois et al., “DailyCog: A real-world mobile system for detection and monitoring of mild cognitive impairment,” JMIR mHealth and uHealth, vol. 9, no. 6, e24784, 2021.

@article{1717294,
      author = {Sangita Patil, Vedashree Kulkarni, Aditya Gavhane, Aditya Inamdar, Yash Sonawane},
      title = {MCI Cognitive Care App: An AI-Powered Personalized Platform for Cognitive Training in Mild Cognitive Impairment},
      journal = {Iconic Research And Engineering Journals},
      year = {2026},
      volume = {9},
      number = {11},
      pages = {558-561},
      issn = {2456-8880},
      url = {https://www.irejournals.com/formatedpaper/1717294.pdf},
      abstract = {Mild Cognitive Impairment (MCI) is a transitional neurological condition characterized by measurable cognitive decline beyond normal aging while preserving independence in daily activities. Individuals diagnosed with MCI face an elevated risk of progression to dementia, highlighting the importance of early and adaptive intervention. This paper presents the MCI Cognitive Care App, an AI-driven digital cognitive training platform designed to deliver personalized cognitive rehabilitation through adaptive gameplay. The system integrates a suite of cognitive exercises targeting memory, attention, processing speed, and executive function. Personalization is achieved using a reinforcement learning framework based on an Epsilon- Greedy Contextual Bandit algorithm, enabling real-time adaptation of task difficulty, hint frequency, and task sequencing. The platform is implemented as a fully functional prototype comprising a React.js frontend, Node.js backend, and Python-based AI engine. Gamification mechanisms and a multi-role dashboard support sustained engagement and collaborative monitoring by patients, caregivers, and clinicians. A pilot observational evaluation demonstrates improved engagement, smooth difficulty progression, and positive usability outcomes, indicating the feasibility of AI-driven personalization for scalable cognitive rehabilitation.},
      keywords = {Mild Cognitive Impairment, Reinforcement Learning, Contextual Bandits, Cognitive Training, Digital Health, Gamification},
      month = {May},
      doi = {https://doi.org/10.64388/IREV9I11-1717294}
  }