Prediction of Overhydration in the Process of Pediatric Hemodialysis using Artificial Neural Network

This paper aims to predict overhydration in the hemodialysis process using Artificial Neural Network. Dehydration has negative impacts on both physical and mental health, as is well-known. Overhydration's possible negative effects are, however, less known. A balanced state of the fluid in the body represents the essence of hemodialysis therapy. The prediction of volume-related adverse events has shown potential when using machine learning techniques. Several factors could influence overhydration, such as weight, blood pressure, lean tissue index, fat tissue index, body mass index, total body water, extracellular water, adipose tissue mass, body cell mass, and bioimpedance. The objective is to use an artificial neural network to estimate overhydration more accurately than current methods, which rely on measurable factors and the physician's judgment. The training and testing processes are explained, as well as the development of the artificial network model. The model achieved satisfactory results.