Comparison of classification approaches applied to NIR-spectra of clinical study lots.

NIR-spectroscopy combined with pattern recognition approaches is applied to classify samples of clinical study lots in the pharmaceutical industry. The performance of linear discriminant analysis (LDA), quadratic discriminant analysis (QDA) and K-nearest neighbour (KNN) method is evaluated on a tablet data set and a capsule data set. To establish a classification model a strategy is followed, which is described in this work. Frequently, in the pharmaceutical industry, several batches of the same clinical study lot are produced. We tested whether it is possible to merge several batches in one class for modelling or, instead, whether it is necessary to model each batch individually.

[1]  Desire L. Massart,et al.  Assessing the Validity of Near-Infrared Monochromator Calibrations over Time , 1998 .

[2]  Desire L. Massart,et al.  Detection of inhomogeneities in sets of NIR spectra , 1996 .

[3]  T. Fearn,et al.  Principal component outlier detection and SIMCA: a synthesis , 1994 .

[4]  Christopher T. Rhodes,et al.  Pharmaceutical Uses of Near-Infrared Spectroscopy , 1995 .

[5]  Beata Walczak,et al.  Spectral transformation and wavelength selection in near-infrared spectra classification , 1995 .

[6]  R. Barnes,et al.  Standard Normal Variate Transformation and De-Trending of Near-Infrared Diffuse Reflectance Spectra , 1989 .

[7]  D. Massart.  Chemometrics: A Textbook , 1988 .

[8]  Desire L. Massart,et al.  Comparison of regularized discriminant analysis linear discriminant analysis and quadratic discriminant analysis applied to NIR data , 1996 .

[9]  P. A. Gorry.  General least-squares smoothing and differentiation by the convolution (Savitzky-Golay) method , 1990 .

[10]  S. Lonardi,et al.  APPLICATION OF NIRS TO THE CONTROL OF PHARMACEUTICALS IDENTIFICATION AND ASSAY OF SEVERAL PRIMARY MATERIALS , 1992 .

[11]  L. A. Stone,et al.  Computer Aided Design of Experiments , 1969 .

[12]  Desire L. Massart,et al.  Investigation of sources of variance which contribute to NIR-spectroscopic measurement of pharmaceutical formulations , 1997 .

[13]  D. Coomans,et al.  Alternative k-nearest neighbour rules in supervised pattern recognition : Part 1. k-Nearest neighbour classification by using alternative voting rules , 1982 .

[14]  K. Prebble,et al.  Some applications of near-infrared reflectance analysis in the pharmaceutical industry. , 1993, Journal of pharmaceutical and biomedical analysis.

[15]  Desire L. Massart,et al.  Supervised pattern recognition: the ideal method? , 1986 .

[16]  Desire L. Massart,et al.  Artificial neural networks in classification of NIR spectral data: Design of the training set , 1996 .

[17]  P. K. Aldridge,et al.  Identification of Tablet Formulations inside Blister Packages by Near-Infrared Spectroscopy , 1994 .

[18]  Diane D. Wolff,et al.  Pattern Recognition Approach to Data Interpretation , 1983, Springer US.

[19]  F. E. Grubbs,et al.  Extension of Sample Sizes and Percentage Points for Significance Tests of Outlying Observations , 1972 .