Generative AI Health Assistants: From Theory to Practice

Document Type : Research Paper

Authors

1 Prof., Department of Data Science and Artificial Intelligence, Faculty of Information Technology, Al-Ahilya Amman University, Amman, Jordan.

2 Assistant Prof., Department of Computer Science, Faculty of Information Technology, Al-Ahilya Amman University, Amman, Jordan.

3 Professor, Vice Chancellor and CEO Wigwe University, Isiokpo, Nigeria.

10.22059/jitm.2026.108010

Abstract

Generative Artificial Intelligence (GenAI) has evolved significantly from early models like variational autoencoders (VAEs) to sophisticated diffusion and hybrid models, enabling the creation of entirely new data from input prompts. In the domain of natural language, powerful large language models (LLMs) such as GPT-4 now generate remarkably coherent responses, while diffusion models have opened up new applications in text-to-image generation and image editing across unimodal and multimodal spaces. These advancements are built upon foundational theories of latent variable modeling, denoising processes, and attention/transformer architectures. This paper traces the development of GenAI, with a focus on its application in mobile AI assistants integrated into smartphones and edge computing platforms. While transformative, these models are typically large and resource-intensive. Their deployment in mobile or edge environments necessitates architectural compression techniques like pruning and quantization, model partitioning between the device and server, or the development of lightweight models designed for constrained settings. This study discusses the practical transition from model architecture to a functional, AI-powered mobile assistant that utilizes dynamic inference across device and edge layers. A mixed-methods approach is employed, combining quantitative benchmarking of latency, accuracy, energy consumption, and resource utilization with qualitative assessments of user experience, trust, and privacy perceptions. The system's design incorporates principles of data protection and user authentication through voice biometric-based watermarking, aligning with our previous work on secure multimedia exchange. Using a heterogeneous dataset of benchmarked prompts, mobile hardware telemetry, and semi-structured user interviews, this research reports on performance metrics, usability findings, and privacy trade-offs. The paper concludes by offering recommended practices and reference architectures, providing a holistic framework for transitioning GenAI from a theoretical innovation to a practical, secure, and ethically aligned tool in mobile and health-oriented applications.

Keywords

References

Abdulsalam, Y. S., & Hedabou, M. (2021). Security and privacy in cloud computing: A technical review. Future Internet, 14(1), 11.
Alhudhud, G., et al. (2023). Secure multimedia exchange using a voice biometric–based security system for intellectual protection.
Ashraf, M., Chen, L., Zhou, X., & Rakha, M. A. (2024). A joint architecture of mixed-attention transformer and octave module for hyperspectral image denoising. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 4331–4349.
Kartal, G. (2024). Evaluating a mobile instant messaging tool for efficient large-class speaking instruction. Computer Assisted Language Learning, 37(5–6), 1252–1280.
Lee, H. P., Sarkar, A., Tankelevitch, L., Drosos, I., Rintel, S., Banks, R., & Wilson, N. (2025, April). The impact of generative AI on critical thinking: Self-reported reductions in cognitive effort and confidence effects from a survey of knowledge workers. In Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems (pp. 1–22).
Mostafavi, A. (2025). Lightweight AI models for IDS in IIoT: Balancing accuracy and computational efficiency.
Moura, J., & Hutchison, D. (2022). Resilience enhancement at edge cloud systems. IEEE Access, 10, 45190–45206.
Nair, V. C., Munilla-Garrido, G., & Song, D. (2023). Going incognito in the metaverse: Achieving theoretically optimal privacy–usability trade-offs in VR. In Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology (pp. 1–16).
Oleiwi, S. S., Mohammed, G. N., & Al-Barazanchi, I. (2022). Mitigation of packet loss with end-to-end delay in wireless body area network applications. International Journal of Electrical and Computer Engineering, 12(1), 460.
Ramadan, Z. (2025). Evaluating advanced retrieval-augmented generation techniques for multi-hop question answering: A comparative study of naive RAG, recursive RAG, and graph RAG [Preprint].
Ray, P. P. (2025). A survey on model context protocol: Architecture, state-of-the-art, challenges and future directions [Preprint]. Authorea.
Reis, J., & Housley, M. (2022). Fundamentals of data engineering. O’Reilly Media.
Salah, M., Abdelfattah, F., Alhalbusi, H., Jassem, S., Mohammed, M., Ismail, M. M., & Al Washahi, M. (2024). Can generative AI craft variable questions? A mixed-method study on AI’s capability to adopt, adapt, and create new scales. [Journal Title if available].
Sarker, I. H. (2022). AI-based modeling: Techniques, applications and research issues towards automation, intelligent and smart systems. SN Computer Science, 3(2), Article 158.
Shahab, M. A. (2024). The impact of generative AI on UI design for mobile applications in terms of efficiency using SPACE framework [Master’s thesis/Doctoral dissertation, Name of Institution].
Singh, N., Buyya, R., & Kim, H. (2024). Securing cloud-based internet of things: Challenges and mitigations. Sensors, 25(1).
Vasheghani Farahani, J., & Treiblmaier, H. (2025). A sustainability assessment of a blockchain-secured solar energy logger for edge IoT environments. Sustainability, 17(17), Article 8063.
Wilson, K., Al Arafat, A., Baugh, J., Yu, R., & Guo, Z. (2025, May). Physics-informed mixed-criticality scheduling for F1Tenth cars with preemptable ROS 2 executors. In Proceedings of the 2025 IEEE 31st Real-Time and Embedded Technology and Applications Symposium (RTAS) (pp. 215–227). IEEE.
Zing, Y., & Zhao, N. (2025). Routing revolution: Strategic applications of meta-heuristic AI in wireless sensor networks—A comprehensive survey. Multimedia Tools and Applications, 1–42
Journal of Information Technology Management
Volume 18, Issue 3
2026
Pages 181-201

Files

Share

How to cite

Statistics