AI DRIVEN HEALTHCARE CHATBOT FOR OLDER ADULTS

would have far less accessibility .By understanding the intent and generating responses smartly coupled with pre-processing information efficiently the chatbot is adaptable to various real-world situations including but not limited to noisy voice input and ambiguous short messages and low digital literacy among others. The system We utilize conversational AI and intelligent agent technology to create an effective AI-driven Healthcare chatbot for Older Adults that provides accessible personalized and scalable health support to the connected ageing population. Our system will include the Natural Language Understanding components and interfaces using voice and text together with personal health data to provide advice reminders triage and emergency detection to the users .The AI- Driven Healthcare Chatbot for Older Adults shows just how a health conversation agent that is supervised manually can provide expert health information at any time from anywhere on demand. It is also a natural alternative to keeping manual supervision and hotlines. A manual supervision system of nursing and a conventional telephone hotline encourages easy interaction and clear operations for the elderly people while optimally alerting the caregivers and health professionals for collective review with regards to optimisation of shared care. The system designed shall ensure faultless assistance to the user at low latency and proper resources utilization is ensured. This solution can therefore be successfully deployed in home healthcare assisted living community health and many other such settings. This project shows the increasing demand for explainable AI with privacy preservation in healthcare applications. The chatbot offers the user certain trust regarding secure authentication data minimization and visible decision-logging functions in order to be able to protect their data. The design will be modular; adaptation in neighbouring domains is thus easy. For example EHRs telemedicine wearable sensors etc. will seamlessly connect and foster further adoption across the healthcare workflows.In the end the AI-Driven Healthcare Chatbot for Older Adults has achieved what it set out to do with a strong and user-centered design that strikes a perfect balance between accuracy usability and safety. It lays the foundation for future upgrades to include totally integrated multimodal interactions: voice + speech by video; continuous learning with increased personalization; rigorous clinical trials to confirm these innovations may have unexpected side effects; and tighter system integration so it would fit seamlessly into the daily lives of health service providers everywhere.

Pang B. & Lee L. (2008). Opinion Mining and Sentiment Analysis. Foundations and Trends in Information Retrieval 2(1-2) 1-135.Kim Y. (2014). Convolutional Neural Networks for Sentence Classification .Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing 1746–1751.Joulin A. Grave E. Mikolov T. & Ranzato M. A. (2017). Bag of Tricks for Efficient Text Classification. ArXiv preprint ArXiv:1607.01759.Zhou H. et al. (2025). Exploring Older Adults' Perspectives and Acceptance of AI-Driven Health Technologies: Qualitative Study. JMIR Aging 8(1) e66778.Gudala M. et al. (2022). Benefits of Barriers to and Needs for an Artificial Sarabi M. et al. (2018). A Conversational Interface to Improve Medication Adherence: Towards AI Support in Patient's Treatment. arXiv preprint arXiv:1803.09844.Al-Somali S. A. (2025). Integrating artificial intelligence (AI) in healthcare: advancing older adults' health management in Saudi Arabia through AI- powered chatbots. PeerJ Computer Science 11 e2773.Van der Waa J. et al. (2020). Designing a Virtual Agent for Older Adults: A Systematic Review. Frontiers in Robotics and AI 7 576402.Luger T. M. & Sellen A. (2016). A conceptual framework for the role. Portz J. D. et al. (2019). The Role of Te