×

Robust multivariate diagnostics for PLSR and application on high dimensional spectrally overlapped drug systems. (English) Zbl 07193765

Summary: Statistical methods are effectively used in the evaluation of pharmaceutical formulations instead of laborious liquid chromatography. However, signal overlapping, nonlinearity, multicollinearity and presence of outliers deteriorate the performance of statistical methods. The Partial Least Squares Regression (PLSR) is a very popular method in the quantification of high dimensional spectrally overlapped drug formulations. The SIMPLS is the mostly used PLSR algorithm, but it is highly sensitive to outliers that also effect the diagnostics. In this paper, we propose new robust multivariate diagnostics to identify outliers, influential observations and points causing non-normality for a PLSR model. We study performances of the proposed diagnostics on two everyday use highly overlapping drug systems: Paracetamol-Caffeine and Doxylamine Succinate-Pyridoxine Hydrochloride.

MSC:

62-XX Statistics

Software:

R
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Gergov G, Alin A, Doychinova M, et al. Assessment of different pls algorithms for quantification of three spectrally overlapping drugs. Bulgarian Chem Commun. 2017;49:410-421. [Web of Science ®], [Google Scholar]
[2] Damiani P, Escandar G, Olivieri A, et al. Multivariate calibration: a powerful tool in pharmaceutical analysis. Curr Pharm Anal. 2005;1:145-154. doi: 10.2174/1573412054022725[Crossref], [Web of Science ®], [Google Scholar]
[3] Khoshayand M, Abdollahi H, Shariatpanahi M, et al. Simultaneous spectrophotometric determination of paracetamol, ibuprofen and caffeine in pharmaceuticals by chemometric methods. Spectrochimica Acta Part A. 2008;70:491-499. doi: 10.1016/j.saa.2007.07.033[Crossref], [PubMed], [Web of Science ®], [Google Scholar]
[4] Escandar G, Damiani P, Goicoechea H, et al. A review of multivariate calibration methods applied to biomedical analysis. Microchem J. 2006;82:29-42. doi: 10.1016/j.microc.2005.07.001[Crossref], [Web of Science ®], [Google Scholar]
[5] Goicoechea H, Olivieri A.Wavelength selection by net analyte signals calculated with multivariate factor-based hybrid linear analysis (hla), A theoretical and experimental comparison with partial least-squares (pls). Analyst. 1999;124:725-731. doi: 10.1039/a900325h[Crossref], [Web of Science ®], [Google Scholar]
[6] Aktas AH, Kitis F.Spectrophotometric simultaneous determination of caffeine and paracetemol in commercial pharmaceutical by principal component regression, partial least squares and artificial neural networks chemometric methods. Croatica Chem Acta. 2014;87:69-74. doi: 10.5562/cca2214[Crossref], [Web of Science ®], [Google Scholar]
[7] Ferraro M, Castellano P, Kaufman T.Chemometrics assisted simultaneous determination of atenolol and chlorthalidone in synthetic binary mixtures and pharmaceutical dosage forms. Anal Bioanal Chem. 2003;377:1159-1164. doi: 10.1007/s00216-003-2185-6[Crossref], [PubMed], [Web of Science ®], [Google Scholar]
[8] Bhaskar R, Bhaskar R, Sagar M, et al. Simultaneous determination of verapomil hydrochloride and gliclazide in synthetic binary mixtures and combined tablet preparation by chemometric-assisted spectroscopy. J Analytical Sci Methods Instrument. 2012;2:161-166. [Google Scholar]
[9] Mahsen A, Badawey A, Shehat M, et al. Development and validation of smart spectrophotometric-chemometric methods for the simultaneous determination of chlorpheniramine maleate and etilafrine hydrochloride in bulk powder and in dosage form combinations. Int J Pharm Pharmaceut Sci. 2014;6:595-603. [Google Scholar]
[10] Elkady E.Simultaneous spectrophotometric determination of diclofenac potassium and methocarbamol in binary mixture using chemometric techniques and artificial neural networks. Drug Test Analysis. 2011;3:228-233. doi: 10.1002/dta.216[Crossref], [PubMed], [Web of Science ®], [Google Scholar]
[11] DeLuca M, Oliverio F, Ioele G, et al. Multivariate calibration techniques applied to derivative spectroscopy data for the analysis of pharmaceutical mixtures. Chemometr Intell Lab Syst. 2009;96:14-21. doi: 10.1016/j.chemolab.2008.10.009[Crossref], [Web of Science ®], [Google Scholar]
[12] Palabiyik I, Onur F.Simultaneous spectrophotometric determination of ezetimibe and simvastatin in pharmaceutical preparations using chemometric techniques. Quim Nova. 2008;31:1121-1124. [Web of Science ®], [Google Scholar]
[13] Dinc E, Kanbur M, Baleanu D.Simultaneous spectrophotometric determination of chlorotetracycline and benzocaine in bolus by chemometric methods. Revis Chim. 2007;58:195-198. [Web of Science ®], [Google Scholar]
[14] DeJong SSIMPLS.An alternative approach to partial least squares regression. Chemometr Intell Lab Syst. 1993;18:251-263. doi: 10.1016/0169-7439(93)85002-X[Crossref], [Web of Science ®], [Google Scholar]
[15] Rousseeuw P, Van Zomeren B.Unmasking multivariate outliers and leverage points. J Amer Stat Assoc. 1990;85:633-639. doi: 10.1080/01621459.1990.10474920[Taylor & Francis Online], [Web of Science ®], [Google Scholar]
[16] Liang Y, Kvalheim O.Robust methods for multivariate analysis-a tutorial review. Chemometr Intell Lab Syst. 1996;32:1-10. doi: 10.1016/0169-7439(95)00006-2[Crossref], [Web of Science ®], [Google Scholar]
[17] Singh A.Tutorial: outliers and robust procedures in some chemometric applications. Chemometr Intell Lab Syst. 1996;33:175-100. doi: 10.1016/0169-7439(95)00087-9[Crossref], [Web of Science ®], [Google Scholar]
[18] Daszykowski M, Kaczmorek K, Vander Heyden Y, et al. Robust statistics in data analysis: a review of basic concepts. Chemometr Intell Lab Syst. 2007;85:203-219. doi: 10.1016/j.chemolab.2006.06.016[Crossref], [Web of Science ®], [Google Scholar]
[19] Hubert M, Branden K.Robust methods for partial least squares regression. J Chemom. 2003;17:537-549. doi: 10.1002/cem.822[Crossref], [Web of Science ®], [Google Scholar]
[20] Serrneels S, Croux C, Filzmoser P, et al. Partial robust M-regression. Chemometr Intell Lab Syst. 2005;79:55-64. doi: 10.1016/j.chemolab.2005.04.007[Crossref], [Web of Science ®], [Google Scholar]
[21] Alin A, Agostinelli C.Robust iteratively reweighted SIMPLS. J Chemom. 2017;31(3):e2881. doi: 10.1002/cem.2881[Crossref], [Web of Science ®], [Google Scholar]
[22] Fernández Pierna J, Wahl F, de Noord O, et al. Methods for outlier detection in prediction. Chemometr Intell Lab Syst. 2002;63:27-39. doi: 10.1016/S0169-7439(02)00034-5[Crossref], [Web of Science ®], [Google Scholar]
[23] Fernández Pierna J, Jin L, Daszykowski M, et al. A methodology to detect outliers/inliers in prediction with pls. Chemometr Intell Lab Syst. 2003;68:17-28. doi: 10.1016/S0169-7439(03)00084-4[Crossref], [Web of Science ®], [Google Scholar]
[24] Lletí R, Meléndez E, Ortiz M, et al. Outliers in partial least squares regression: application to calibration of wine grade with mean infrared data. Anal. Chim. Acta. 2005;544:60-70. doi: 10.1016/j.aca.2005.03.075[Crossref], [Web of Science ®], [Google Scholar]
[25] Liu Z, Cai W, Shao X.Outlier detection in near infrared spectroscopic analysis by using Monte Carlo cross-validation. Science China B Chemistry. 2008;51(8):751-759. doi: 10.1007/s11426-008-0080-x[Crossref], [Web of Science ®], [Google Scholar]
[26] Bao X, Dai L.Partial least with outlier detection in spectral analysis: a tool to predict gasoline properties. Fuel. 2009;88:1216-1222. doi: 10.1016/j.fuel.2008.11.025[Crossref], [Web of Science ®], [Google Scholar]
[27] Peng J, Peng S, Hu Y.Partial least squares and random sample consensus in outlier detection. Anal. Chim. Acta. 2012;719:24-29. doi: 10.1016/j.aca.2011.12.058[Crossref], [PubMed], [Web of Science ®], [Google Scholar]
[28] Jóźwiak-Bebenista M, Nowak J.Paracetamol: mechanism of action, applications and safety concern. Acta Pol Pharm. 2014;71:11-23. [PubMed], [Web of Science ®], [Google Scholar]
[29] Cappelletti S, Daria P, Sani G, et al. Caffeine: cognitive and physical performance enhancer or psychoactive drug? Current Neuropharmacol. 2015;13:71-88. doi: 10.2174/1570159X13666141210215655[Crossref], [PubMed], [Web of Science ®], [Google Scholar]
[30] Nuangchamnong N, Niebyl J.Doxylamine succinate-pyridoxine hydrochloride(diclegis) for the management of nausea and vomiting in pregnancy: an overview. Int J Women Health. 2014;6:401-409. [PubMed], [Google Scholar]
[31] Mirza A, Siddiqui F.New, simple and validated uv-spectrophotometric methods for the estimation of pyridoxine hydrochloride in bulk and formulation. Bulgarian Chem Commun. 2015;47:131-134. [Web of Science ®], [Google Scholar]
[32] R Core Team. R: A language and environment for statistical computing. Vienna, Austria: R Foundation for Statistical Computing; 2016. [Google Scholar]
[33] De Maesschalck R, Estienne F, Verdu-Andres J, et al. The development of calibration models for spectroscopic data using principal component regression. Int J Chem. 1999;2(19):00-00. [Google Scholar]
[34] Cook R.Detection of influential observations in linear regression. Technometrics. 1977;19:15-18. [Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0371.62096
[35] Cook R, Weisburg S. Residuals and influence in regression. New York: Chapman and Hall; 1982. [Google Scholar] · Zbl 0564.62054
[36] Osborne B, Fearn T, Miller A, et al. Application of near infrared reflectance spectroscopy to the compositional analysis of biscuits and biscuit dough. J Amer Stat Assoc. 1990;85:633-639. doi: 10.1080/01621459.1990.10474920[Taylor & Francis Online], [Google Scholar]
[37] Wicker J, Bozdogan H. A novel mixture-model cluster analysis with genetic em algorithm and information complexity as the fitness function. Proceedings of 10th IFCs - 2006 Conference on Data Science and Classification; July; 2006 Ljubljana, Slovenia. [Google Scholar]
[38] Akaike H. Information theory and an extension of the maximum likelihood principle. In: Petrov B, Csaki F, editors. Proceedings of the Second International Symposium on Information Theory; 1973 Tsahkadsor, Armenia, U. S. S. R. [Google Scholar] · Zbl 0283.62006
[39] Bozdogan H.Model selection and Akaike’s information criterion (aic): the general theory and its analytical extensions. Psychometrika. 1987;52:345-370. doi: 10.1007/BF02294361[Crossref], [Web of Science ®], [Google Scholar] · Zbl 0627.62005
[40] Bozdogan H.On the information-based measure of covariance complexity and its application to the evaluation of multivariate models. Commun Stat Theory Methods. 1990;19(1):221-278. doi: 10.1080/03610929008830199[Taylor & Francis Online], [Web of Science ®], [Google Scholar] · Zbl 0900.62041
[41] Bozdogan H, Haughton D.Informational complexity criteria for regresssion models. Comput Stat Data Anal. 1998;28:51-76. doi: 10.1016/S0167-9473(98)00025-5[Crossref], [Web of Science ®], [Google Scholar] · Zbl 1042.62504
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.