Infrared Analysis of Urinary Calculi by a Single Reflection Accessory and a Neural Network Interpretation Algorithm

rier transform infrared (FT-IR) analysis of urinary cal-culus composition, is time-consuming and often ham-pered by pellet breakage. We developed a new FT-IR method for urinary calculus analysis. This method makes use of a Golden Gate Single Refection Diamond Attenuated Total Reflection sample holder, a computer library, and an artificial neural network (ANN) for spectral interpretation. Methods: The library was prepared from 25 pure com-ponents and 236 binary and ternary mixtures of the 8 most commonly occurring components. The ANN was trained and validated with 248 similar mixtures and tested with 92 patient samples, respectively. Results: The optimum ANN model yielded root mean square errors of 1.5 % and 2.3 % for the training an