Towards a Personalized mHealth Model Using Intelligent Conversational Agents

• Noeli Antonia Pimentel Vaz UFG / UEG
• Kairo A. Lopes da Silva UFG
• Gislainy Velasco UFG
• Luciana Regina F. da Mata UFMG
• Deborah S. Alves Fernandes UFG
• Sergio T. Carvalho UFG

DOI: https://doi.org/10.5753/sbcas.2025.7767

Resumo

Mobile health (mHealth) applications are increasingly used for health monitoring but often struggle to engage users effectively. This study proposes a computational model to personalize mHealth experiences using intelligent conversational agents that combine Large Language Models (LLMs), vector-based knowledge retrieval, and sentiment analysis. An experiment was conducted to evaluate the model’s application in assisting patients with urinary incontinence after radical prostatectomy. The results demonstrated that incorporating a specialized knowledge base significantly improves the personalization of clinical support. The study underscores the potential of LLMs to improve user experience in healthcare applications and highlights the need for further refinements in adapting interaction strategies to better meet patient needs.

Referências

Ammenwerth, E. et al. (2023). Personalization in mHealth: Innovative informatics methods to improve patient experience and health outcome. Journal of Biomedical Informatics, 147:104523.

Anjos, F. M. S. d. et al. (2024). Analyzing the impact of gamification on a mhealth application for treating urinary incontinence in prostate cancer patients. Journal on Interactive Systems, 15(1):728–740.

Chang, Y. et al. (2024). A survey on evaluation of large language models. ACM TIST.

Chuayrod, P. et al. (2024). The Impact of Prompt Engineering on Large Language Models: A Case Study of Sustainable Development Goals. In 2024 19th iSAI-NLP, pages 1–6.

Davies, A. and Mueller, J. (2020). Introduction to mHealth. pages 1–24. Springer.

Denecke, K. and May, R. (2022). Usability assessment of conversational agents in healthcare: a literature review. Challenges of Trustable AI and Added-Value on Health.

Deniz-Garcia, A. et al. (2023). Quality, usability, and effectiveness of mHealth apps and the role of artificial intelligence: current scenario and challenges. JMIR, 25:e44030.

Estevam, F. E. B., , et al. (2023). Desenvolvimento e análise de qualidade do app iuprost para controle da incontinência urinária em prostatectomizados. Revista Remecs-Revista Multidisciplinar de Estudos Científicos em Saúde, pages 44–44.

Gandy, L. M. et al. (2025). Public Health Discussions on Social Media: Evaluating Automated Sentiment Analysis Methods. JMIR Formative Research, 9(1):e57395.

Gosetto, L. et al. (2023). Personalization of Mobile Apps for Health Behavior Change: Protocol for a Cross-sectional Study. JMIR Research Protocols, 12(1):e38603.

Goumas, G. et al. (2024). Chatbots in Cancer Applications, Advantages and Disadvantages: All that Glitters Is Not Gold. Journal of Personalized Medicine, 14(8):877.

Li, C. (2024). Designing LLM-Based Agents: Key Principles (Part 1). [link].

Li, Y. et al. (2024). Quantifying ai psychology: A psychometrics benchmark for large language models. arXiv preprint arXiv:2406.17675.

Martins, A. et al. (2024). Unlocking human-like conversations: Scoping review of automation techniques for personalized healthcare interventions using conversational agents. International Journal of Medical Informatics, page 105385.

Matthews, P. and Rhodes-Maquaire, C. (2024). Personalisation and Recommendation for Mental Health Apps: A Scoping Review. B & I Technology, pages 1–16.

Mendhe, D. et al. (2024). AI-Enabled Data-Driven Approaches for Personalized Medicine and Healthcare Analytics. In 2024 Ninth ICONSTEM, pages 1–5. IEEE.

Mescher, T. et al. (2024). Mobile Health Apps: Guidance for Evaluation and Implementation by Healthcare Workers. Technology in Behavioral Science, pages 1–12.

Montagna, S. et al. (2023). Data decentralisation of LLM-based chatbot systems in chronic disease self-management. In ACM GoodIT, pages 205–212.

Montenegro, J. L. Z. et al. (2019). Survey of conversational agents in health. Expert Systems with Applications, 129:56–67.

Qiu, J. et al. (2024). LLM-based agentic systems in medicine and healthcare. Nature Machine Intelligence, 6(12):1418–1420.

Rivera-Romero, O. et al. (2023). Designing personalised mHealth solutions: An overview. Journal of Biomedical Informatics, page 104500.

Rodriguez, D. V. et al. (2022). PAMS-A Personalized Automatic Messaging System for User Engagement with a Digital Diabetes Prevention Program. In 2022 IEEE 10th ICHI, pages 297–308. IEEE.

Sahoo, P. et al. (2024). A systematic survey of prompt engineering in large language models: Techniques and applications. arXiv preprint arXiv:2402.07927.

Stiles-Shields, C. et al. (2022). Digital Screening and Automated Resource Identification System to Address COVID-19–Related Behavioral Health Disparities: Feasibility Study. JMIR Formative Research, 6(6):e38162.

Vandelanotte, C. et al. (2023). Increasing physical activity using an just-in-time adaptive digital assistant supported by machine learning: A novel approach for hyper-personalised mHealth interventions. Journal of Biomedical Informatics, 144:104435.

Vaz, N. A. P. et al. (2024). O uso da metodologia crisp-dm para apoiar a análise de dados no aplicativo mhealth iuprost. In Simpósio Brasileiro de Computação Aplicada à Saúde (SBCAS), pages 448–458. SBC.

Wen, B. et al. (2024). Leveraging Large Language Models for Patient Engagement: The Power of Conversational AI in Digital Health. In 2024 IEEE ICDH, pages 104–113.

Yang, Z. et al. (2024a). ChatDiet: Empowering personalized nutrition-oriented food recommender chatbots through an LLM-augmented framework. Smart Health.

Yang, Z. et al. (2024b). Talk2Care: An LLM-based Voice Assistant for Communication between Healthcare Providers and Older Adults. ACM IMWUT, 8(2):1–35.

Zhang, T. et al. (2019). Bertscore: Evaluating text generation with bert. arXiv preprint arXiv:1904.09675.