2026-10-13T07:17:17Z https://api.figshare.com/v2/oai

oai:figshare.com:article/33946321 2026-09-21T00:15:44Z category_25258 item_type_3 month_year_09_2026

<b>Predicting Dissolution and Gel Viscosity in Hot-Melt Extruded Polymeric Formulations: A Quality-by-Design Framework</b> Mohammad Ali Riaz (24432677) Computational chemistry hot melt extrusion (HME) <p dir="ltr">Hot-melt extrusion (HME) is a solvent-free, continuous manufacturing technology that is increasingly central to the industrial production of modified-release and abuse-deterrent oral dosage forms. However, the relationships among formulation composition, process conditions, and critical quality attributes (CQAs) such as drug dissolution and gel viscosity remain complex, nonlinear, and costly to resolve by experimentation alone. This study develops and benchmarks tree-based machine-learning (ML) surrogate models, namely Extreme Gradient Boosting (XGBoost), Random Forest (RF), and Gradient Boosting (GB), for predicting the 30-minute aqueous dissolution percentage (water_dissolution_30min_pct) of hot-melt extruded polyethylene oxide (PEO)/hydroxypropyl methylcellulose (HPMC)/carbomer matrices containing pseudoephedrine. Exploratory regression is used in parallel to characterize the dependence of gel viscosity (gel_viscosity_pa_s) on polymer content and drug loading. On a small, curated formulation dataset (42 records; five formulation/process features), RF provided the best held-out predictive performance (test R² = 0.485) among the baseline models, and feature-importance analysis identified pseudoephedrine drug loading as the dominant predictor. Five-fold grid-search hyperparameter optimization did not materially improve held-out accuracy on this limited dataset, and the negative cross-validated R² values reveal the high variance inherent to small samples. Combining a second data source into a merged dataset (96 usable records; 17 features) produced a markedly stronger optimized RF model (R² = 0.984, RMSE = 3.56 %, MAE = 2.17 %, MAPE = 7.54 %). This performance is, however, partly attributable to the inclusion of the 60-minute dissolution endpoint as a predictive feature, which introduces target leakage and must therefore be interpreted cautiously. Shapley Additive Explanations (SHAP) showed that drug content uniformity (% RSD) and the 60-minute dissolution readout dominated the combined model, while residual analysis confirmed near-zero bias with no pronounced heteroscedasticity. Collectively, these results demonstrate a reusable, interpretable, quality-by-design (QbD) workflow for surrogate modeling of HME product quality and highlight the critical roles of data volume, feature-leakage control, and rigorous cross-validation in translating ML from proof of concept to deployment in pharmaceutical process engineering.</p> 2026-09-21T00:15:44Z Dataset Dataset 10.6084/m9.figshare.33946321.v1 https://figshare.com/articles/dataset/_b_Predicting_Dissolution_and_Gel_Viscosity_in_Hot-Melt_Extruded_Polymeric_Formulations_A_Quality-by-Design_Framework_b_/33946321 CC BY 4.0