Multivariate analysis of green to ultraviolet spectra of cell and tissue samples
View Patent ↗This invention relates to methods for processing in vivo skin auto-fluorescence spectra for determining blood glucose levels. The invention also relates to methods of classifying cells or tissue samples or quantifying a component of a cell or tissue using a multivariate classification or quantification model.
1. A method for processing in vivo skin auto fluorescence spectra emitted by a skin surface of a patient to determine a blood glucose level of the patient comprising the steps of:
collecting clinical fluorescence spectra data and corresponding glucose values from a range of individuals, said spectra data responsive to irradiation of tissue at a plurality of wavelengths of energy;
sorting said clinical fluorescence spectra data according to said glucose values;
processing said sorted clinical fluorescence spectra data to reduce effects of noise;
collecting fluorescence spectra data emitted from the skin surface of the patient;
correcting the collected spectra data using multivariate analysis to account for skin surface variables; and
determining a blood glucose level of the patient based on at least said corrected spectra data and said processed clinical fluorescence spectra data.
2. The method of claim 1 wherein the multivariate analysis comprises one or more quantification, classification, or data processing techniques including: partial least squares, principal component regression, linear regression, multiple linear regression, stepwise linear regression, ridge regression, radial basis functions, linear discriminant analysis, cluster analysis, neural network analysis, smoothing filters, laplacian operators, maximum likelihood estimators, maximum entropy, first and second derivatives, peak enhancement, Fourier self-deconvolution, principal components, and varimax rotations.