Green processing based on supercritical carbon dioxide for preparation of nanomedicine: Model development using machine learning and experimental validation

Solubility data for ANA (Anastrozole) drug in supercritical solvent was investigated in this study, and models were developed to estimate the solubility values. The main aim was to provide a predictive methodology for determination of drug solubility in wide range of operational pa-rameters for advanced green pharmaceutical manufacture. The properties used are temperature and pressure which were considered as the models' inputs. Modeling has been done using three models based on the support vector regression. These models include support vector regression (with polynomial kernel), boosted support vector machine with AdaBoost, and improved support vector machine with bagging. These models were evaluated after optimization, and all three models have a coefficient of determination (R2) higher than 0.98. Also considering RMSE, Ada -Boosted SVR, Bagging SVR, and SVR have error rates of 2.31E-01, 4.31E-01, and 5.01E-01.

Automated summary

This study investigated the solubility data of ANA (Anastrozole) drug in a supercritical solvent and developed models to predict the solubility values. The aim was to provide a predictive methodology for determining drug solubility in various operational parameters for green pharmaceutical manufacturing. The models used temperature and pressure as inputs and employed three different models based on support vector regression. After optimization, all three models showed a coefficient of determination (R2) higher than 0.98. Additionally, considering RMSE, the error rates for Ada-Boosted SVR, Bagging SVR, and SVR were 2.31E-01, 4.31E-01, and 5.01E-01, respectively.