Chronic patient self-management is crucial for maintaining physical and psychological health, reducing pressure on healthcare systems, and promoting patient empowerment. Digital technologies, particularly chatbots, have emerged as powerful tools for supporting patients in managing their chronic conditions. Large language models (LLMs), such as GPT-4, have shown potential in improving chatbot-based systems in healthcare. However, their adoption in clinical practice faces challenges, including reliability, the need for clinical trials, and privacy concerns. This paper proposes a general architecture for developing an LLM-based chatbot system that supports chronic patients while addressing privacy and security concerns. The architecture is designed to be independent of specific technologies and health conditions, focusing on data protection legislation compliance. A prototype of the system has been developed for hypertension management, demonstrating its potential for motivating patients to monitor their blood pressure and adhere to prescriptions.
Montagna, S., Ferretti, S., Klopfenstein, L., Florio, A., Pengo, M. (2023). Data Decentralisation of LLM-Based Chatbot Systems in Chronic Disease Self-Management. In GoodIT '23: Proceedings of the 2023 ACM Conference on Information Technology for Social Good (pp.205-212). Association for Computing Machinery [10.1145/3582515.3609536].
Data Decentralisation of LLM-Based Chatbot Systems in Chronic Disease Self-Management
Pengo M. F.
2023
Abstract
Chronic patient self-management is crucial for maintaining physical and psychological health, reducing pressure on healthcare systems, and promoting patient empowerment. Digital technologies, particularly chatbots, have emerged as powerful tools for supporting patients in managing their chronic conditions. Large language models (LLMs), such as GPT-4, have shown potential in improving chatbot-based systems in healthcare. However, their adoption in clinical practice faces challenges, including reliability, the need for clinical trials, and privacy concerns. This paper proposes a general architecture for developing an LLM-based chatbot system that supports chronic patients while addressing privacy and security concerns. The architecture is designed to be independent of specific technologies and health conditions, focusing on data protection legislation compliance. A prototype of the system has been developed for hypertension management, demonstrating its potential for motivating patients to monitor their blood pressure and adhere to prescriptions.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
