Internet of Medical Things Through Explainable AI at the Edge: A Practical Case Study

Abstract

Explainable Artificial Intelligence (XAI) is emerging as an enabler of trustworthy and human-aligned decision making in next-generation IoT ecosystems. As 6G envisions a highly distributed Global Internet of Things paradigm, embedding explainability of AI models at the network edge will be essential for supporting critical emerging domains such as the Internet of Medical Things (IoMT). In this paper, we explore a practical integration of XAI methods at the edge of 6G IoT architectures and propose novel explainable feature selection and adaptive sample selection strategies that allow low-cost IoT devices to improve data acquisition, on-device processing, and communication efficiency in large-scale deployments. Through a practical case study using an experimental IoMT dataset and comparing different learning models, we show how SHapley Additive exPlanations (SHAP) can be used to interpret patient-related data, improve clinical insight, and significantly boost key performance and value indicators such as learning accuracy, energy consumption, and bandwidth utilization, outperforming traditional dimensionality-reduction techniques.

Ähnliche Arbeiten