Fast, Spectroscopy-Based Prediction of In Vitro Dissolution Profile of Extended Release Tablets Using Artificial Neural Networks.

Galata Galata,Nagy Nagy,Pálos Pálos,Csontos Csontos,Marosi Marosi,Könyves Könyves,Szabó Szabó,Farkas Farkas,Mészáros Mészáros

doi:10.3390/pharmaceutics11080400

Galata Galata, Nagy Nagy + Show 7 more

Open Access

https://doi.org/10.3390/pharmaceutics11080400

Copy DOI

Journal: Pharmaceutics	Publication Date: Aug 9, 2019
Citations: 28	License type: CC BY 4.0

Affiliation: Budapest University of Technology and Economics

Abstract

The pharmaceutical industry has never seen such a vast development in process analytical methods as in the last decade. The application of near-infrared (NIR) and Raman spectroscopy in monitoring production lines has also become widespread. This work aims to utilize the large amount of information collected by these methods by building an artificial neural network (ANN) model that can predict the dissolution profile of the scanned tablets. An extended release formulation containing drotaverine (DR) as a model drug was developed and tablets were produced with 37 different settings, with the variables being the DR content, the hydroxypropyl methylcellulose (HPMC) content and compression force. NIR and Raman spectra of the tablets were recorded in both the transmission and reflection method. The spectra were used to build a partial least squares prediction model for the DR and HPMC content. The ANN model used these predicted values, along with the measured compression force, as input data. It was found that models based on both NIR and Raman spectra were capable of predicting the dissolution profile of the test tablets within the acceptance limit of the f2 difference factor. The performance of these ANN models was compared to PLS models using the same data as input, and the prediction of the ANN models was found to be more accurate. The proposed method accomplishes the prediction of the dissolution profile of extended release tablets using either NIR or Raman spectra.

Highlights

Near-infrared (NIR) and Raman spectroscopy are constantly evolving techniques—their utilization in the pharmaceutical industry is spreading by the day
Recent advancements in spectroscopy and computer technology opened the way to a new era for the pharmaceutical industry, where in-line monitoring of the processes yields a tremendous amount of information
The current work aimed to utilize the data collected by NIR and Raman spectroscopy, along with the compression force measured by the tablet press

Summary

Introduction

Near-infrared (NIR) and Raman spectroscopy are constantly evolving techniques—their utilization in the pharmaceutical industry is spreading by the day. They are fast and non-destructive analytical methods which require no sample preparation [1,2] Since they are based on different physical phenomena (Raman scattering and NIR absorption), these two methods are considered to be complementary, as Raman measurements are more sensitive to compounds with aromatic rings (such as most active pharmaceutical ingredients (APIs)), while NIR spectroscopy is better suited for samples with σ-bond systems (such as most tableting excipients) [1]. NIR and Raman spectroscopy have been applied for determining content uniformity [10,11], monitoring blending processes [12,13,14], for fluidized bed granulation and coating of tablets [15], continuous fluidized bed drying [16], identifying counterfeit drugs [17] and detecting polymorphs [18,19,20] These analytical methods yield a large amount of data, as spectra generally consist of measurements at hundreds of wavelengths. Among the most commonly used are principal component analysis (PCA) [24] and partial least squares (PLS) regression [25]

Objectives

Methods

Results

Conclusion