In the context of rapid population ageing, digital technologies are increasingly regarded as essential resources for supporting care, autonomy, and quality of life. Nevertheless, in countries such as Italy their diffusion remains limited, revealing a persistent gap between technological potential and real-world adoption. The present paper addresses this gap by introducing the CARES platform as a concrete example of integrated telemonitoring. CARES is a device-agnostic e-health platform that collects physiological data from wearable devices, serving healthcare professionals, patients, and caregivers across both clinical and home-care settings. From a technological perspective, the system integrates Artificial Intelligence at two complementary levels: Machine Learning techniques are explored for ECG-based anomaly detection, and a conversational system based on Large Language Models (LLMs) is designed to support the interpretation of clinical data through natural language interaction, thereby facilitating access to patient records and enhancing explainability. Despite the technological maturity of platforms such as CARES, their uptake in real-world contexts remains an open challenge, underscoring the persistent distance between technological innovation and its effective adoption in ageing societies.
Silver Tech, Slow Uptake: Digital Innovation and the Care Gap in Ageing Italy
Maselli, Alessio;Guglielmi, Emanuela;Scalabrino, Simone;Oliveto, Rocco;Tomassini, Cecilia
2026-01-01
Abstract
In the context of rapid population ageing, digital technologies are increasingly regarded as essential resources for supporting care, autonomy, and quality of life. Nevertheless, in countries such as Italy their diffusion remains limited, revealing a persistent gap between technological potential and real-world adoption. The present paper addresses this gap by introducing the CARES platform as a concrete example of integrated telemonitoring. CARES is a device-agnostic e-health platform that collects physiological data from wearable devices, serving healthcare professionals, patients, and caregivers across both clinical and home-care settings. From a technological perspective, the system integrates Artificial Intelligence at two complementary levels: Machine Learning techniques are explored for ECG-based anomaly detection, and a conversational system based on Large Language Models (LLMs) is designed to support the interpretation of clinical data through natural language interaction, thereby facilitating access to patient records and enhancing explainability. Despite the technological maturity of platforms such as CARES, their uptake in real-world contexts remains an open challenge, underscoring the persistent distance between technological innovation and its effective adoption in ageing societies.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.


