Barmpalexis Panagiotis, Partheniadis Ioannis, Mitra Konstantina-Sepfora, Toskas Miltiadis, Papadopoulou Labrini, Nikolakakis Ioannis
Department of Pharmaceutical Technology, School of Pharmacy, Faculty of Health Sciences, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece.
Department of Mineralogy-Petrology-Economic Geology, School of Geology, Faculty of Sciences, Aristotle University of Thessaloniki, 54124 Thessaloniki, Greece.
Pharmaceutics. 2020 Mar 8;12(3):244. doi: 10.3390/pharmaceutics12030244.
Plain or coated pellets of different densities 1.45, 2.53, and 3.61 g/cc in two size ranges, small (380-550 μm) and large (700-1200 μm) (stereoscope/image analysis), were prepared according to experimental design using extrusion/spheronization. Multiple linear regression (MLR) and artificial neural networks (ANNs) were used to predict packing indices and capsule filling performance from the "apparent" pellet density (helium pycnometry). The dynamic packing of the pellets in tapped volumetric glass cylinders was evaluated using Kawakita's parameter and the angle of internal flow . The capsule filling was evaluated as maximum fill weight () and fill weight variation () using a semi-automatic machine that simulated filling with vibrating plate systems. The pellet density influenced the packing parameters and as the main effect and the and as statistical interactions with the coating. The pellet size and coating also displayed interacting effects on and . After coating, both small and large pellets behaved the same, demonstrating smooth filling and a low fill weight variation. Furthermore, none of the packing indices could predict the fill weight variation for the studied pellets, suggesting that the filling and packing of capsules with free-flowing pellets is influenced by details that were not accounted for in the tapping experiments. A prediction could be made by the application of MLR and ANNs. The former gave good predictions for the bulk/tap densities, and (R-squared of experimental vs. theoretical data >0.951). A comparison of the fitting models showed that a feed-forward backpropagation ANN model with six hidden units was superior to MLR in generalizing ability and prediction accuracy. The simplification of the ANN via magnitude-based pruning (MBP) and optimal brain damage (OBD), showed good data fitting, and therefore the derived ANN model can be simplified while maintaining predictability. These findings emphasize the importance of pellet density in the overall capsule filling process and the necessity to implement MLR/ANN into the development of pellet capsule filling operations.
采用挤出滚圆法，根据实验设计制备了不同密度（1.45、2.53和3.61 g/cc）、两种尺寸范围（小尺寸：380 - 550 μm；大尺寸：700 - 1200 μm）（通过体视显微镜/图像分析）的素丸或包衣丸。使用多元线性回归（MLR）和人工神经网络（ANNs），根据“表观”丸剂密度（氦比重瓶法）预测堆积指数和胶囊填充性能。使用川北参数和内部流动角评估丸剂在振实的容量瓶中的动态堆积情况。使用模拟振动板系统填充的半自动机器，将胶囊填充情况评估为最大填充重量（）和填充重量变化（）。丸剂密度作为主要影响因素影响堆积参数和，并且与包衣存在和的统计相互作用。丸剂尺寸和包衣对和也表现出相互作用。包衣后，小丸和大丸的表现相同，填充顺畅且填充重量变化小。此外，对于所研究的丸剂，没有一个堆积指数能够预测填充重量变化，这表明用自由流动丸剂填充胶囊的过程受到振实实验中未考虑的细节的影响。通过应用MLR和ANNs可以进行预测。前者对堆密度/振实密度、和给出了良好的预测（实验数据与理论数据的决定系数>0.951）。拟合模型的比较表明，具有六个隐藏单元的前馈反向传播ANN模型在泛化能力和预测准确性方面优于MLR。通过基于幅度的剪枝（MBP）和最优脑损伤（OBD）对ANN进行简化，显示出良好的数据拟合，因此在保持可预测性的同时可以简化所推导的ANN模型。这些发现强调了丸剂密度在整个胶囊填充过程中的重要性，以及在丸剂胶囊填充操作开发中实施MLR/ANN的必要性。
