Use of pattern-recognition techniques to analyze chromatographic data

Abstract A pattern-recognition technique has been established using a new class or orthogonal polynomials, developed by Cohen. The method is based on a supervised learning approach, and allows classification of data into two or more categories. In this paper, the usefulness of the method in the analysis of chromatographic data is illustrated by its application to the diagnosis of bacterial infection of patients with liver disorders by use of chromatograms obtained from ascitic fluid withdrawn from the patients.