DBPapers

FTIR ANALYSIS AND ARTIFICIAL NEURAL NETWORK IN PREDICTION OF RENAL STONES COMPOSITION

S. POPESCU
Thursday 11 October 2018 by Libadmin2018

ABSTRACT

The Fourier Transform Infrared (FT-IR) spectroscopy is one of the suitable experimental tools for analysis of urinary calculi constituents. However, interpretation of infrared spectra for quantifying urinary calculus constituents in mixtures is difficult, requiring expert knowledge by trained technicians. The development of automated methods for determining the composition of uroconcrements is very important since it can facilitate the determination of the factors which influence the occurrence of calculi in urinary tract and perhaps aid the prevention of their recurrence. A new FT-IR method was developed for urinary calculus analysis. This method uses a computer library and an artificial neural network (ANN) for spectral interpretation. Recent study have shown that more that 80% of the analyzed urinary calculi from the Banat Region of Romania in our laboratory were mainly composed of calcium oxalate (whewellite and weddellite) and/or their mixtures with carbonate apatite, struvite, brushite and uric acid. Then, the focus of this work was the development of methods for analysis of urinary calculi composed of these substances.
The data contained by the library was obtained from the analysis of the pure substances of the calculi constituents, and from 126 mixtures (binary and ternary) of these substances. The ANN was trained and validated with 52 similar mixtures and tested with 33 calculi. The discrepancies between calculated and predicted mass fractions of these constituents were within a range acceptable for use. We conclude that neural networks are promising tools for quantitative determination of urinary calculus composition and for other related types of analyses in the clinical laboratory.

Keywords: ANN, calculi, chemical composition, urolithiasis, FT-IR spectroscopy


Home | Contact | Site Map | Site statistics | Visitors : 0 / 353063

Follow site activity en  Follow site activity INFORMATICS  Follow site activity Papers SGEM2018   ?

CrossRef Member    Indexed in ISI Web Of Knowledge   Indexed in ISI Web Of Knowledge
   

© Copyright 2001 International Multidisciplinary Scientific GeoConference & EXPO SGEM. All Rights Reserved.

Creative Commons License