MEASUREMENT SITE DEPENDENT DATA PREPROCESSING METHOD FOR ROBUST CALIBRATION AND PREDICTION

摘要

A solution for reducing interference in noninvasive spectroscopic measurements of tissue and blood analytes is provided. The noninvasive measurement of blood chemistry involves collecting a tissue measurement (301), preprocessing the measurement for enhancing the analytical signal and attenuating noises (302) applying a basis set to the preprocessed tissue measurement (304) to transform the preprocessed tissue measurement (303), performing an outlier detection (305), making a bias correction term (306), applying a multivariate calibration model to the transformed tissue measurement (307), and determining the measurement of the analyte digitally or/and graphically (308). By applying a basis set representing various tissue components to a collected sample measurement, measurement interferences resulting from the heterogeneity of tissue, sampling site differences, patient-to-patient variation, physiological variation, and instrumental differences are reduced. Consequently, the transformed sample measurements are more suitable for developing calibrations that are robust with respect to sample-to-sample variation, variation through time, and instrument related differences.