Abstract

Dementia is a progressive neurological condition that impacts heavily on memory, cognitive capacities and day to day activities; which pose huge challenges to both the sufferers and their caregivers. The current mobile applications and traditional healthcare solutions offer a minimum of real-time support and a lack of intelligent and personalized support to manage daily routine and contact with professionals in healthcare. As Artificial Intelligence (AI) is rapidly emerging, there is an increasing demand to integrate systems that may provide a flexible, context-sensitive, and user-friendly care to dementia patients. This paper is an introduction to WeCare, a multimodal AI platform that provides smart and real-time support to improve the care of dementia patients. The offered system incorporates the newest AI solutions, such as voice input processing, futuristic chatbot with AI as a conversational assistant, and text-to-speech systems with easy-to-understand feedback. It has a modular and collaborative structure, with various AI components collaborating to process user input, produce meaningful response, and deliver timely assistance. Also, a secure cloud back-end will help to keep data in real-time and allow caregivers to track the activity of the patient using a special dashboard. The solution proposal will enhance patient autonomy, lessen the workload of caregivers, and have a healthcare-support system that is scalable and efficient. With its ability to make use of multimodal interaction and adaptive AI features, WeCare is a major advancement to intelligent, personalized, and accessible dementia care, and can be further improved in the real-world healthcare context in the future.

References

• P. Xu, X. Zhu, and D. A. Clifton, “Multimodal Learning With Transformers: A Survey,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 10, pp. 12113–12132, Oct. 2023.
• S. Yao and X. Wan, “Multimodal Transformer for Multimodal Machine Translation,” in Proc. 58th Annual Meeting of the Association for Computational Linguistics, 2020, pp. 4346–4350.
• Y.-H. H. Tsai et al., “Multimodal Transformer for Unaligned Multimodal Language Sequences,” arXiv preprint arXiv:1906.00295, 2019.
• S. Pandhi and R. Tiwari, “Dementia Care: An Android Application for Assisting Dementia Patients,” in Proc. 3rd Int. Conf. Intelligent Engineering and Management (ICIEM), IEEE, 2022
• A. Staroverov et al., “Fine-Tuning Multimodal Transformer Models for Generating Actions in Virtual and Real Environments,” IEEE Access, vol. 11, pp. 130548–130560, 2023
• Y. Zhang et al., “Meta-Transformer: A Unified Framework for Multimodal Learning,” arXiv preprint arXiv:2307.10802, 2023
• M. K. Reza, A. Prater-Bennette, and M. S. Asif, “MMSFormer: Multimodal Transformer for Material and Semantic Segmentation,” IEEE Open Journal of Signal Processing, vol. 5, pp. 599–612, 2024.
• S. Ikram et al., “A Transformer-Based Multimodal Object Detection System for Real-World Applications,” IEEE Access, vol. 13, pp. 29162–29178, 2025.
• W. Lyu et al., “A Multimodal Transformer: Fusing Clinical Notes with Structured EHR Data for Interpretable In-Hospital Mortality Prediction,” AMIA Annual Symposium, 2022.
• K. Ding et al., “Speech Based Detection of Alzheimer’s Disease: A Survey of AI Techniques,” Artificial Intelligence Review, Springer, 2024.
• U. Sarawgi et al., “Multimodal Inductive Transfer Learning for Detection of Alzheimer’s Dementia and its Severity,” arXiv preprint arXiv:2009.00700, 2020.
• D. Yu, Research contributions in speech recognition, conversational AI, and multimodal systems, IEEE Fellow & Tencent AI Lab.
• F. Demrozi et al., “Multimodal AI (MMAI) for Next-Generation Healthcare,” 2025.
• J. N. Acosta et al.,“Multimodal Biomedical AI,” Nature Medicine, vol. 28, pp. 1773–1784, 2022.
• L. R. Soenksen et al., “Integrated Multimodal Artificial Intelligence Framework for Healthcare Applications,” arXiv preprint arXiv:2202.12998, 2022.