The applications of machine learning to predict the forming of chemically stable amorphous solid dispersions prepared by hot-melt extrusion

Amorphous solid dispersion (ASD) is one of the most important strategies to improve the solubility and dissolution rate of poorly water-soluble drugs. As a widely used technique to prepare ASDs, hot-melt extrusion (HME) provides various benefits, including a solvent-free process, continuous manufacturing, and efficient mixing compared to solvent-based methods, such as spray drying. Energy input, consisting of thermal and specific mechanical energy, should be carefully controlled during the HME process to prevent chemical degradation and residual crystallinity. However, a conventional ASD development process uses a trial-and-error approach, which is laborious and time-consuming. In this study, we have successfully built multiple machine learning (ML) models to predict the amorphization of crystalline drug formulations and the chemical stability of subsequent ASDs prepared by the HME process. We utilized 760 formulations containing 49 active pharmaceutical ingredients (APIs) and multiple types of excipients. By evaluating the built ML models, we found that ECFP-LightGBM was the best model to predict amorphization with an accuracy of 92.8%. Furthermore, ECFP-XGBoost was the best in estimating chemical stability with an accuracy of 96.0%. In addition, the feature importance analyses based on SHapley Additive exPlanations (SHAP) and information gain (IG) revealed that several processing parameters and material attributes (i.e., drug loading, polymer ratio, drug's Extended-connectivity fingerprints (ECFP) fingerprints, and polymer's properties) are critical for achieving accurate predictions for the selected models. Moreover, important API's substructures related to amorphization and chemical stability were determined, and the results are largely consistent with the literature. In conclusion, we established the ML models to predict formation of chemically stable ASDs and identify the critical attributes during HME processing. Importantly, the developed ML methodology has the potential to facilitate the product development of ASDs manufactured by HME with a much reduced human workload.

Paliperidone palmitate as model of heat-sensitive drug for long-acting 3D printing application

In this work, two technologies were used to prepare long-acting implantable dosage forms in the treatment of schizophrenia. Hot-melt extrusion (HME) as well as fused deposition modelling (FDM) were used concomitantly to create personalized 3D printed implants. Different formulations were prepared using an amorphous PLA as matrix polymer and different solid-state plasticizers. Paliperidone palmitate (PP), a heat sensitive drug prescribed in the treatment of schizophrenia was chosen as model drug. After extrusion, different formulations were characterized using DSC and XRD. Then, an in vitro dissolution test was carried out to discriminate the formulation allowing a sustained drug release of PP. The formulation showing a sustained drug release of the drug was 3D printed as an implantable dosage form. By modulating the infill, the release profile was related to the proper design of tailored dosage form and not solely to the solubility of the drug. Indeed, different release profiles were achieved over 90 days using only one formulation. In addition, a stability test was performed on the 3D printed implants for 3 months. The results showed the stability of the amorphous state of PP, independently of the temperature as well as the integrity of the matrix and the drug.

Vibrational spectroscopy and microspectroscopy analyzing qualitatively and quantitatively pharmaceutical hot melt extrudates

Since the last decade, more and more Active Pharmaceutical Ingredient (API) candidates have poor water solubility inducing low bioavailability. These molecules belong to the Biopharmaceutical Classification System (BCS) classes II and IV. Thanks to Hot-Melt Extrusion (HME), it is possible to incorporate these candidates in pharmaceutical solid forms. Indeed, HME increases the solubility and the bioavailability of these drugs by encompassing them in a polymeric carrier and by forming solid dispersions. Moreover, in 2004, the FDA's guidance initiative promoted the usefulness of Process Analytical Technology (PAT) tools when developing a manufacturing process. Indeed, the main objective when developing a new pharmaceutical process is the product quality throughout the production chain. The trend is to follow this parameter in real-time in order to react immediately when there is a bias. Vibrational spectroscopic techniques, NIR and Raman, are useful to analyze processes in-line. Moreover, off-line Raman microspectroscopy is more and more used when developing new pharmaceutical processes or when analyzing optimized ones by combining the advantages of Raman spectroscopy and imaging. It is an interesting tool for homogeneity and spatial distribution studies. This review treats about spectroscopic techniques analyzing a HME process, as well off-line as in-line, presenting their advantages and their complementarities.