Next Generation Healthcare with Explainable AI: IoMT-Edge-Cloud Based Advanced eHealth

This article provides in-depth experimental studies of XAI (EXplainable Artificial Intelligence) in the IoT-Edge-Cloud continuum. Within the different available XAI frameworks, such as Local Interpretable Model-Agnostic Explanations (LIME) and SHapley Additive exPlanations (SHAP) frameworks are utilized here as they are the most suitable feature map-based, model-agnostic, posthoc frameworks that match our requirements for getting real-time prediction explanations in the healthcare domain. In order to evaluate LIME and SHAP in this continuum and to make black box AI (BBAI)-based decisions interpretable, we have considered the real-world electronic health record (EHR)-based large cloud database (which could be a very large database–VLDB) and IoMT based real-time streams as edge databases for the prediction of cardiac arrest in the real-world. We have also verified the effectiveness of automated counterfactual explanations in this context for taking remedial actions. Thus, our proposed model is capable of making significant advancements in the healthcare industry by offering conscious healthcare monitoring automation along with an AI-based self-explanatory system that serves as a personalized health assistant for individuals, paving the way for the next major upgrade in healthcare.