Modelling a hybridised Sequential Network model for chronic kidney disease using learning approaches

Chronic Kidney Disease (CKD) continues to be an epidemic despite breakthroughs in clinical treatment and medical care. Researchers globally interested in creating high-performance screening, treatment, and preventative therapy techniques because of rise in CKD in recent. Along with the clinical evaluation, healthcare providers forecast the illness at its earliest stages by analysing the individual’s health information. To construct intelligent systems predicts CKD by analysing healthcare information, the performance of these methods requires further work to be improved. An intelligent classification and forecasting framework predicts kidney-related disorders using an enhanced Progressive Network System (PNets) which is a hybridisation of Sequential Progressive Network (SPNets) and Sequential Progressive Temporal Network (SPTNet) classification algorithm. The analysis of the proposed framework recognise CKD with 98.5% accuracy. Analysing the outcomes reveals that applying novel DL algorithms can assist with medical decision-making and early CKD and associated phase estimation, which slows the course of kidney disease.