Machine learning in medicine: calculating the minimum dose of haemodialysis using neural networks

Efficiency of haemodialysis in end-stage renal disease (ESRD) is determined by calculating adequacy. The adequacy of dialysis and its measurement have been debated over the past 20 years by authorities concerned about how much of this life-sustaining treatment is appropriate for patients with ESRD. Currently, the minimum dose of dialysis is assessed by computerised calculation of urea kinetics. Although fairly standard, it is still an approximate method due to the various assumptions made in the development of the final parametric model. Until now artificial intelligence has not been used to study haemodialysis and hence no machine learning approach has been used to model it so far. In this paper, an algorithmic approach is presented for this procedure using generalised radial basis function neural networks (GRNNN) and this research has shown it to be very promising.