Self-management of Long-term Conditions by Integrating Artificial Intelligence With Wearable Devices and Internet-of-Thing Technology: A Review

Abstract

The aim of this study was to investigate the impact on the delivery, adoption and effectiveness of Generative Artificial Intelligence integrated wearable devices and internet-of-thing (IoT) for long-term condition monitoring. We adopted PRISMA review methodology and screened a total of 226 articles. After considering the eligibility and selection criteria, we selected 13 articles published between 2020 and 2024. The selection criteria were based on the inclusion of studies that report on the adoption and effectiveness of Generative Artificial Intelligence integrated wearable devices and internet-of-thing (IoT) for long-term condition monitoring. We found wearable health monitoring and personalised patient care plans leveraged Gen AI to predict health events by analysing continuous data from wearables devices and IoT devices like smartwatches, glucose monitors and various health and well-being sensors. Gen AI models provided tailored advice on physical activity, diet, and sleep, leading to improved health outcomes and user satisfaction. Comparative analysis from reviewed studies demonstrates substantial performance improvements: accuracy enhanced from 85.6% to 97.7%, precision improved from 85.1% to 96.8% and computational latency reduced significantly from 320 ms to 120 ms. Moving AI processing closer to the data source (e.g., on the wearable device itself) can reduce latency and improve real-time decision-making. This is particularly useful for critical health and safety applications. Moreover, robust integration with electronic health records (EHRs) and healthcare providers can enhance the usefulness of data collected by wearables, allowing for more comprehensive and coordinated care. Continued advancements in AI algorithms will improve the predictive capabilities of these systems, enabling even more proactive and personalized interventions.