A data-driven approach utilizing a raw material database and machine learning tools to predict the disintegration time of orally fast-disintegrating tablet formulations

Abstract

Orally fast-disintegrating tablets (OFDTs) have seen a significant increase in popularity over the past decade, becoming a rapidly expanding sector in the pharmaceutical market. The aim of the current study is to use machine learning (ML) methods to predict the disintegration time (DT) of OFDTs. In this study, we have developed seven ML models using the TPOT AutoML platform to predict the DT of OFDTs. These models include the decision tree regressor (DTR), gradient boost regressor (GBR), random forest regressor (RFR), extra tree regressor (ETR), least absolute shrinkage and selection operator (LASSO), support vector machine (SVM), and deep learning (DL). The results indicate that ML methods are effective in predicting the DT, especially with ETR. However, after fine-tuning the deep neural network with a 10-point cross-validation scheme, the DL model showed superior performance with an NRMSE of 6.2% and an R2 of 0.79. The key factors influencing the DT of OFDTs were identified using the SHAP method.