Scalable IoMT-based CKD Prediction using Integrated AI and Robotic Automation

chronic kidney disease (CKD) is a pressing global health challenge that requires timely detection and dependable diagnosis for effective management. Traditional approaches suffer from scalability issues, real-time data processing, and accuracy in forecasting. The integration of the Internet of Medical Things (IoMT) with artificial intelligence is a revolutionary solution that allows constant surveillance and sophisticated predictive analytics to overcome these limitations. The goal of this study was to create a scalable IoMT-based framework for the prediction of CKD. The architecture utilizes DBNs for feature extraction, ANFIS for interpretable decision making, and TCNs for the inspection of sequential data to ensure the robustness of a real-time diagnostic support system. IoMT devices capture physiological data in real-time and then preprocessed and standardized. High-level features are extracted from DBNs while adaptive forecasts are provided through ANFIS and TCNs for modeling the temporal patterns. The outputs from Ensemble AI are combined for robust prediction. Key metrics on which the framework is tested include accuracy, precision, and AUC-ROC. The framework achieves accuracy at 96.2%, precision at 95.8%, recall of 97.1% and AUC-ROC as 0.98%, beating traditional approaches. Its process time at 0.82 seconds shows its scalability with the use in real-time applications of healthcare. This integrated framework demonstrates excellent extensibility, reliability, and exactness in CKD prediction, thus setting the benchmark for IoMT-driven AI in healthcare diagnostics. The scalability is achieved by collecting the data in real-time with the help of IoMT and low-latency processing (0.82s) with the help of modular, parallelizable units such as TCNs and robotic automation of data streams.