Pharmaceutical Raw Material Identification Using Miniature Near-Infrared (MicroNIR) Spectroscopy and Supervised Pattern Recognition Using Support Vector Machine

Abstract

Near-infrared spectroscopy as a rapid and non-destructive analytical technique offers great advantages for pharmaceutical raw material identification (RMID) to fulfill the quality and safety requirements in pharmaceutical industry. In this study, we demonstrated the use of portable miniature near-infrared (MicroNIR) spectrometers for NIR-based pharmaceutical RMID and solved two challenges in this area, model transferability and large-scale classification, with the aid of support vector machine (SVM) modeling. We used a set of 19 pharmaceutical compounds including various active pharmaceutical ingredients (APIs) and excipients and six MicroNIR spectrometers to test model transferability. For the test of large-scale classification, we used another set of 253 pharmaceutical compounds comprised of both chemically and physically different APIs and excipients. We compared SVM with conventional chemometric modeling techniques, including soft independent modeling of class analogy, partial least squares discriminant analysis, linear discriminant analysis, and quadratic discriminant analysis. Support vector machine modeling using a linear kernel, especially when combined with a hierarchical scheme, exhibited excellent performance in both model transferability and large-scale classification. Hence, ultra-compact, portable and robust MicroNIR spectrometers coupled with SVM modeling can make on-site and in situ pharmaceutical RMID for large-volume applications highly achievable.

Portable Spectroscopy

“…6d), based on an LVF and 128-pixel InGaAs array, covering 950-1650 nm (10 526-6060 cm -1 ), with a spectral bandwidth (resolution) of <1.25% of center wavelength yielding a resolution of <12.5 nm at 1000 nm). [247][248][249][250] The handheld instruments are powered via their USB interface; typical measurement times are < 1 s. Siesler has compared a laboratory FT-IR and the Viavi MicroNIR 1700 instruments 251 and found that calibrations for both quantitative predictions and qualitative classifications can be transferred successfully from the laboratory instrument to the portable analyzer. He has also compared the performance of several miniature NIR spectrometers for polymer identification (recycling).…”

Development of a NIR Method for the In-Line Quantification of the Total Polyphenolic Content: A Study Applied on Ajuga genevensis L. Dry Extract Obtained in a Fluid Bed Process

“…This apparatus incorporates a Linear Variable Filter enabling its size reduction and facilitating the device’s direct attachment to the walls of the expansion vessel or to any other manufacturing apparatus, without using a fiber optic probe that could cause signal attenuation or dispersion. Therefore, the spectrometer is more stable and the measurements performed more reliable [ 37 , 38 , 39 , 40 , 41 ].…”

Análise De Amostras De Combustíveis Por Fotometria, Nir Portátil E RMN De 1 H – Uma Comparação Com Os Resultados Encontrados Por Técnicas Normatizadas

“…20,21 Assim, destaca-se o microespectrômetro portátil na região do infravermelho próximo (MicroNIR), no qual a espectroscopia de vibração é realizada no comprimento de onda de 908 a 1.676 nm (11.013 a 5.967 cm -1 ). [22][23][24] O MicroNIR possibilita monitorar e determinar propriedades das amostras no local de coleta, 25 além de possuir diversas outras vantagens como: curto tempo de análise (alguns segundos); baixo custo de aquisição e operação; baixo consumo de energia; baixo ou nenhum uso de reagentes; pouco ou nenhum tratamento da amostra; alta segurança do analisador; fácil operação e eliminação de fontes de erros devido a transportes de amostras. Associado a métodos quimiométricos, o MicroNIR possibilita estimar várias propriedades, simultaneamente, bem como controlar a qualidade dos produtos.…”