RT Journal Article
T1 Artificial neural networks for adaptive control of profiled haemodialysis in patients with renal insufficiency
A1 Fernández-de-Cañete-Rodríguez, Francisco Javier
A1 Román, Marta
A1 De Santiago, Rafael
K1 Redes neuronales (Informática)
K1 Hemodiálisis
AB Background and objective: Currently, haemodialysis treatment is performed using an open-loop control approach,with initial settings of parameters such as ultrafiltration rate and dialyser composition being adapted to thecurrent haemodynamic condition of each patient, although unexpected events may require additional adjustmentsto be made.Therefore, an artificial neural network-based approach has been presented to automatically control the ultrafiltrationrate according to the specific patient conditions during the haemodialysis session, in order to regulatebody weight loss, and the elimination of electrolytes and uremic toxins.Methods: This modelling task is performed using a mathematical model of fluid and solute exchange based on firstprinciples, which is used to simulate the process of a haemodialysis session in a specific patient under SIMULINKin order to define the underlying dynamic equations. Alongside this, MATLAB neural network tools are used toadjust the settings of the automatic controller for different body weight loss regulation profiles and variabledialysate sodium conditions during haemodialysis treatment.Results: Computer simulation results show the adequate performance of the body weight loss neuroadaptivecontrol system when submitted to different haemodialysis patterns, uremic toxins and sodium eliminationevolution under changing dialysate sodium conditions.Conclusions: The proposed approach proves to be a valuable tool as a test bench for the assessment of alternatehaemodialysis profiles aimed to improve the treatment of patients by preventing dialysis-induced haemodynamiccomplications. The adaptive nature of the model-based control approach here
PB Elsevier
YR 2023
FD 2023-06-12
LK https://hdl.handle.net/10630/29766
UL https://hdl.handle.net/10630/29766
LA eng
NO Fernandez de Canete, J., Roman, M., & de Santiago, R. (2023). Artificial neural networks for adaptive control of profiled haemodialysis in patients with renal insufficiency. Expert Systems with Applications, 232, 120775.
DS RIUMA. Repositorio Institucional de la Universidad de Málaga
RD 21 ene 2026