The global demographic shift toward an aging population presents a critical socio-economic challenge, necessitating "aging in place" solutions that balance autonomy with safety. Although the Internet of Medical Things (IoMT) offers a theoretical foundation for remote monitoring, current implementations often fail to meet real-world requirements due to high costs, intrusive sensing modalities, and a lack of contextual reasoning. This article outlines the architectural requirements of the next-generation platform for digital health support. We argue that the future of monitoring the elderly lies within the framework of Agentic Artificial Intelligence (AI), a system that not only records events but also reasons about them, detects and adapts to anomalies, and communicates with caregivers through natural language. As a result, the next generation of digital wellness platforms must bridge the gap between technical data and human understanding, providing high-precision detection, human-readable, and context-aware recommendations. This shifts systems from simple data loggers to proactive decision-supporting tools.
Agentic AI for Digital Wellness: Challenges and Architectural Perspectives for Smart Home Care
Capogrosso, Luigi
;Biondani, Francesco;Bigardi, Francesca;Cordibella, Stefano;Perbellini, Giovanni;Vendraminetto, Walter;Fummi, Franco
2026-01-01
Abstract
The global demographic shift toward an aging population presents a critical socio-economic challenge, necessitating "aging in place" solutions that balance autonomy with safety. Although the Internet of Medical Things (IoMT) offers a theoretical foundation for remote monitoring, current implementations often fail to meet real-world requirements due to high costs, intrusive sensing modalities, and a lack of contextual reasoning. This article outlines the architectural requirements of the next-generation platform for digital health support. We argue that the future of monitoring the elderly lies within the framework of Agentic Artificial Intelligence (AI), a system that not only records events but also reasons about them, detects and adapts to anomalies, and communicates with caregivers through natural language. As a result, the next generation of digital wellness platforms must bridge the gap between technical data and human understanding, providing high-precision detection, human-readable, and context-aware recommendations. This shifts systems from simple data loggers to proactive decision-supporting tools.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
