Classification trees based on infrared spectroscopic data to discriminate between genuine and counterfeit medicines

• Published in: Journal of pharmaceutical and biomedical analysis Vol. 57; no. 5; pp. 68 - 75
• Main Authors: Deconinck, E., Sacré, P.Y., Coomans, D., De Beer, J.
• Format: Journal Article Web Resource
• Language: English
• Published: England Elsevier B.V 05.01.2012; Elsevier Science
• Subjects: Algorithms; CART; Classification; classification, CART; Counterfeit Drugs; Counterfeit medicines; data collection; drugs; Human health sciences; Infrared spectroscopy; PDE-5 inhibitors; Pharmacie, pharmacologie & toxicologie; Pharmacy, pharmacology & toxicology; Raman spectroscopy; regression analysis; Sciences de la santé humaine; Spectroscopy, Fourier Transform Infrared; Spectroscopy, Near-Infrared - methods; Spectrum Analysis, Raman - methods; Infrared spectroscopy; PDE-5 inhibitors; Raman spectroscopy; Counterfeit medicines; Classification; CART
• ISSN: 0731-7085; 1873-264X; 1873-264X
• DOI: 10.1016/j.jpba.2011.08.036

► Spectroscopic data was modelled to discriminate counterfeit medicines. ► CART was evaluated as modelling techniques for discrimination purpose. ► CART was evaluated as classification method for the different classes of counterfeits. ► Different CART models are proposed with ccr = 1 for counterfeit/genuine. ► CART models have high ccr for the different classes of counterfeits. Classification trees built with the Classification And Regression Tree algorithm were evaluated for modelling infrared spectroscopic data in order to discriminate between genuine and counterfeit drug samples and to classify counterfeit samples in different classes following the RIVM classification system. Models were built for two data sets consisting of the Fourier Transformed Infrared spectra, the near infrared spectra and the Raman spectra for genuine and counterfeit samples of respectively Viagra ® and Cialis ®. Easy interpretable models were obtained for both models. The models were validated for their descriptive and predictive properties. The predictive properties were evaluated using both cross validation as an external validation set. The obtained models for both data sets showed a 100% correct classification for the discrimination between genuine and counterfeit samples and 83.3% and 100% correct classification for the counterfeit samples for the Viagra ® and the Cialis ® data set respectively.