Real-time release testing of dissolution based on surrogate models developed by machine learning algorithms using NIR spectra, compression force and particle size distribution as input data.

In this work spectroscopic measurements, process data and Critical Material Attributes (CMAs) are used to predict the in vitro dissolution profile of sustained-release tablets with three machine learning methods, Artificial Neural Networks (ANN), Support Vector Machines (SVM) and Ensemble of Regression Trees (ERT). Beside the effect of matrix polymer content and compression force, the influence of active pharmaceutical ingredient (API) and matrix polymer particle size distribution (PSD) on the drug release rate of sustained tablets is studied. The matrix polymer PSD was found to be a significant factor, thus this factor was included in the dissolution prediction experiments. In order to evaluate the importance of the inclusion of PSD data, models without PSD data were also prepared and the results were compared. In the developed models, the API and hydroxypropyl-methylcellulose (HPMC) content is predicted from near-infrared (NIR) spectra, the compression force is measured by the tablet press and HPMC particle size is measured off-line. The predictions of ANN, SVM and ERT were compared to the measured dissolution profiles of the validation tablets, ANN yielded the most accurate results. In the presented work, data provided by Process Analytical Technology (PAT) sensors is combined with CMAs for the first time to realize the Real-Time Release Testing (RTRT) of tablet dissolution.

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

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.