Partial Least Squares Regression: A Valuable Method for Modeling Molecular Behavior in Hemodialysis

• Published in: Annals of biomedical engineering Vol. 36; no. 7; pp. 1305 - 1313
• Main Authors: Fernández, E.A., Valtuille, R., Willshaw, P., Balzarini, M.
• Format: Journal Article
• Language: English
• Published: Boston Springer US 01-07-2008; Springer Nature B.V
• Subjects: Biochemistry; Biological and Medical Physics; Biomedical and Life Sciences; Biomedical Engineering and Bioengineering; Biomedicine; Biophysics; Classical Mechanics; Computer Simulation; Data Interpretation, Statistical; Dialysis; Humans; Kidney - blood supply; Kidney - physiopathology; Least-Squares Analysis; Models, Biological; Regression Analysis; Renal Circulation - physiology; Renal Dialysis - methods; Statistical models; Therapy, Computer-Assisted - methods; Urea; Hemodialysis adequacy; Statistical modeling; Equilibrated urea; Kinetic modeling
• ISSN: 0090-6964; 1573-9686
• DOI: 10.1007/s10439-008-9492-1

The aim of this work was to use the Partial Least Squares Regression (PLS) technique to fit simple models for the interpretation of an underlying complex process. In this study, the technique was used to build a statistical model for molecular kinetic data obtained from hemodialyzed patients. By using PLS we derived statistical linear models for the prediction of the equilibrated urea concentration which would be reached 30–60 min after the end of the dialysis session. Models with an average relative prediction error (RPE) of less than 0.05% were achieved. The model predictive accuracy was evaluated in a cross-center study yielding an RPE < 3%. The chosen model was robust to variations such as sampling extraction time demonstrating a high capacity for modeling kinetics. It also was found to be useful for bedside monitoring. Finally, the PLS technique allowed identification of the most important co-variables in the model and of those patients with outlier patterns in their molecular dynamics.