A Strategy for the Effective Optimization of Pharmaceutical Formulations Based on Parameter-Optimized Support Vector Machine Model

Accelerating 3D printing of pharmaceutical products using machine learning

Three-dimensional printing (3DP) has seen growing interest within the healthcare industry for its ability to fabricate personalized medicines and medical devices. However, it may be burdened by the lengthy empirical process of formulation development. Active research in pharmaceutical 3DP has led to a wealth of data that machine learning could utilize to provide predictions of formulation outcomes. A balanced dataset is critical for optimal predictive performance of machine learning (ML) models, but data available from published literature often only include positive results. In this study, in-house and literature-mined data on hot melt extrusion (HME) and fused deposition modeling (FDM) 3DP formulations were combined to give a more balanced dataset of 1594 formulations. The optimized ML models predicted the printability and filament mechanical characteristics with an accuracy of 84%, and predicted HME and FDM processing temperatures with a mean absolute error of 5.5 °C and 8.4 °C, respectively. The performance of these ML models was better than previous iterations with a smaller and a more imbalanced dataset, highlighting the importance of providing a structured and heterogeneous dataset for optimal ML performance. The optimized models were integrated in an updated web-application, M3DISEEN, that provides predictions on filament characteristics, printability, HME and FDM processing temperatures, and drug release profiles (https://m3diseen.com/predictionsFDM/). By simulating the workflow of preparing FDM-printed pharmaceutical products, the web-application expedites the otherwise empirical process of formulation development, facilitating higher pharmaceutical 3DP research throughput.

Optimization of Asphalt-Mortar-Aging-Resistance-Modifier Dosage Based on Second-Generation Non-Inferior Sorting Genetic Algorithm

The use of steel slag powder instead of filler to prepare asphalt mortar was beneficial to realize the effective utilization of steel slag and improve the performance of asphalt concrete. Nevertheless, the anti-aging properties of steel-slag powder–asphalt mortar need to be further enhanced. This study used antioxidants and UV absorbers in steel-slag powder–asphalt mortar to simultaneously improve its thermal-oxidation and UV-aging properties. The dosage of modifier was optimized by second-generation non-inferior sorting genetic algorithm. Fourier-Transform Infrared Spectroscopy, a dynamic shear rheometer and the heavy-metal-ion-leaching test were used to evaluate the characteristic functional groups, rheological properties and heavy-metal-toxicity characteristics of the steel-slag-powder-modified asphalt mortar, respectively. The results showed that there was a significant correlation between the amount of modifier and G*, δ, and the softening point. When the first peak appeared for G*, δ, and the softening point, the corresponding dosages of x₁ were 2.15%, 1.0%, and 1.1%, respectively, while the corresponding dosage of x₂ were 0.25%, 0.76%, and 0.38%, respectively. The optimal value of the modifier dosage x₁ was 1.2% and x₂ was 0.5% after weighing by the NSGA-II algorithm. The asphalt had a certain physical solid-sealing effect on the release of heavy-metal ions in the steel-slag powder. In addition, the asphalt structure was changed under the synergistic effect of oxygen and ultraviolet rays. Therefore, the risk of leaching heavy-metal ions was increased with the inferior asphalt-coating performance on the steel-slag powder.