Point-of-care Vis-SWNIR spectroscopy towards reagent-less hemogram analysis

Abstract

Current chemometrics and artificial intelligence methods are unable to deal with complex multi-scale interference of blood constituents in visible shortwave near-infrared spectroscopy point-of-care technologies. The major difficulty is to access the rich information in the spectroscopy signal, unscrambling and interpreting spectral interference to provide analytical quality quantifications. We present a new self-learning artificial intelligence method for spectral processing based on the search of covariance modes with direct correspondence to the Beer-Lambert law. Dog and cat hemograms were analyzed by impedance flow cytometry and standard laboratory methods (erythrocytes counts, hemoglobin, and hematocrit). Spectral records were performed for the same samples. The methodology was benchmarked against state-of-the-art chemometrics: a multivariate linear model of hemoglobin bands, similarity, partial least squares, local partial least squares, and artificial neural networks.The new method outperforms the state-of-the-art, providing analytical quality quantifications according to desired veterinary pathology guidelines (total errors of 1.69% to 7.14%), whereas chemometric methods cannot. The method finds relevant samples and spectral information that hold the quantitative information for a particular interference mode, in contrast to the current methods that do not hold a relationship with the Beer-Lambert law. It allows the interpretation of interference bands used in quantification, providing the capacity to determine if the composition of an unknown sample is predictable. This research is especially relevant for improving current optical point-of-care technologies that are affected by spectral interference and moving towards micro-sampling and reagent-less technologies in healthcare and veterinary medicine diagnosis.