Premium
>Reduced‐Dimensional Radial Basis Neural Network for Monitoring Haemodialysis
Author(s) -
Ray Monika,
Qidwai Uvais.
Publication year - 2003
Publication title -
hemodialysis international
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.658
H-Index - 47
eISSN - 1542-4758
pISSN - 1492-7535
DOI - 10.1046/j.1492-7535.2003.01218.x
Subject(s) - medicine , hemodialysis , blood urea nitrogen , urology , surgery , renal function
Efficiency of haemodialysis is determined by calculating adequacy. Current practice utilizes invasive procedures, such as the periodic measurement of blood urea nitrogen levels for monitoring haemodialysis. Medical informatics has not been used to study haemodialysis. Here an algorithmic approach is presented to calculate adequacy using generalised radial basis function neural networks (GRBFN). Previous work by the authors has shown the performance of a GRBFN when compared to the DDQ method. I Comparison between UN removal calculated by DDQ and that predicted by GRBFN.Next, adequacy was measured using those quantities that are non‐invasive. II Comparison between UN removal calculated by DDQ and that predicted by the 2 GRBFN architectures (NEW GRBFN inputs – Time, Weight; OLD GRBFN inputs – Bun, Time, Weight).Time Calculated UNRemoval‐ DDQ Predicted UN Removal (OLD GRBFN) Predicted UN Removal (NEW GRBFN ) % PE (OLD GRBFN) % PE (NEW GRBFN)0 35.08 ± 3.33 34.48 ± 0.48 34.72 ± 0.07 1.70 1.02 60 34.00 ± 3.04 31.48 ± 0.31 31.60 ± 0.03 7.41 7.06 90 28.54 ± 2.72 28.44 ± 0.23 28.48 ± 0.07 0.34 0.23 120 25.88 ± 3.72 25.56 ± 0.25 25.64 ± 0.01 1.23 0.94 150 22.38 ± 1.14 21.83 ± 0.19 21.89 ± 0.03 2.46 2.20 180 20.56 ± 4.09 19.66 ± 0.14 19.70 ± 0.03 4.37 4.21 210 18.68 ± 1.88 17.04 ± 0.15 17.07 ± 0.08 8.80 8.63 240 15.60 ± 3.98 13.40 ± 0.06 13.40 ± 0.02 14.16 14.16This study presents a better and more convenient algorithmic procedure that provides the physician with a better guide to the prescription of haemodialysis.