Comprehensive Robotic Automation-Driven IoMT Framework Combining Deep Learning, Temporal Convolutional Networks, Fuzzy Cognitive Maps, and Ensemble Optimization Techniques for Reliable Chronic Kidney Disease Detection

chronic kidney disease (CKD) is a major global health issue that necessitates early and precise diagnosis to treat effectively. This paper discusses an AI-based framework for the detection of CKD using Internet of Medical Things (IoMT) technology for real-time monitoring. The model, which is trained and tested on the August 2023 Chronic Kidney Disease Dataset of the UCI Machine Learning Repository, utilizes Deep Learning, Temporal Convolutional Networks (TCNs), and Fuzzy Cognitive Maps (FCMs) to improve predictive accuracy. Physiological data obtained from IoMT devices are pre-processed, feature-extracted through Convolutional Neural Networks (CNNs), temporal pattern analyzed using TCNs, and causally modeled using FCMs, resulting in better diagnostic reliability. The model attains a classification accuracy of 94.8% and an AUC-ROC of 0.96, which is superior to other CKD detection models. Its clinical feasibility, scalability, and stability ensure that it is a viable AI-IoMT-based solution for real-time CKD diagnosis, enhanced patient care, and more effective healthcare services.