Machine Learning for Process Monitoring and Control of Hot-Melt Extrusion: Current State of the Art and Future Directions

Physics-Informed Neural Networks in Polymers: A Review

The modeling and simulation of polymer systems present unique challenges due to their intrinsic complexity and multi-scale behavior. Traditional computational methods, while effective, often struggle to balance accuracy with computational efficiency, especially when bridging the atomistic to macroscopic scales. Recently, physics-informed neural networks (PINNs) have emerged as a promising tool that integrates data-driven learning with the governing physical laws of the system. This review discusses the development and application of PINNs in the context of polymer science. It summarizes the recent advances, outlines the key methodologies, and analyzes the benefits and limitations of using PINNs for polymer property prediction, structural design, and process optimization. Finally, it identifies the current challenges and future research directions to further leverage PINNs for advanced polymer modeling.

Exploring the impact of material selection on the efficacy of hot-melt extrusion

Hot-melt extrusion (HME) has emerged as a versatile and efficient technique in pharmaceutical formulation development, particularly for enhancing the solubility and bioavailability of poorly water-soluble drugs. This review delves into the fundamental principles of HME, exploring its application in drug delivery systems. A comprehensive analysis of polymers utilized in HME, such as hydroxypropyl methylcellulose, ethyl cellulose, hydroxypropyl cellulose, and polyvinylpyrrolidone, is presented, highlighting their roles in achieving controlled drug release and improved stability. The incorporation of plasticizers, such as triacetin, poly(propylene glycol), glycerol, and sorbitol, is critical in reducing the glass transition temperature (Tg) of polymer blends, thereby enhancing the processability of HME formulations. A comparison of Tg values for various polymer-plasticizer combinations is discussed using different predictive models. For researchers and industry professionals looking to optimize drug formulation strategies, this article offers valuable insights into the mechanisms through which HME enhances drug solubility and bioavailability two critical factors in oral drug delivery. Furthermore, by reviewing recent patents and marketed formulations, the article serves as a comprehensive resource for understanding both the technical advancements and commercial applications of HME. Readers will gain a deep understanding of the role of polymers and additives in HME, alongside future perspectives on how emerging materials and techniques could further revolutionize pharmaceutical development. This review is essential for those aiming to stay at the forefront of pharmaceutical extrusion technologies and their potential to improve therapeutic outcomes. The review concludes that meticulous material selection is vital for advancing pharmaceutical manufacturing processes and ensuring optimal outcomes in HME applications, thereby enhancing the overall efficacy of drug delivery systems.

ROM-based stochastic optimization for a continuous manufacturing process

This paper proposes a model-based optimization method for the production of automotive seals in an extrusion process. The high production throughput, coupled with quality constraints and the inherent uncertainty of the process, encourages the search for operating conditions that minimize nonconformities. The main uncertainties arise from the process variability and from the raw material itself. The proposed method, which is based on Bayesian optimization, takes these factors into account and obtains a robust set of process parameters. Due to the high computational cost and complexity of performing detailed simulations, a reduced order model is used to address the optimization. The proposal has been evaluated in a virtual environment, where it has been verified that it is able to minimize the impact of process uncertainties. In particular, it would significantly improve the quality of the product without incurring additional costs, achieving a 50% tighter dimensional tolerance compared to a solution obtained by a deterministic optimization algorithm.

In-line NIR coupled with machine learning to predict mechanical properties and dissolution profile of PLA-Aspirin

In the production of polymeric drug delivery devices, dissolution profile and mechanical properties of the drug loaded polymeric matrix are considered important Critical Quality Attributes (CQA) for quality assurance. However, currently the industry relies on offline testing methods which are destructive, slow, labour intensive, and costly. In this work, a real-time method for predicting these CQAs in a Hot Melt Extrusion (HME) process is explored using in-line NIR and temperature sensors together with Machine Learning (ML) algorithms. The mechanical and drug dissolution properties were found to vary significantly with changes in processing conditions, highlighting that real-time methods to accurately predict product properties are highly desirable for process monitoring and optimisation. Nonlinear ML methods including Random Forest (RF), K-Nearest Neighbours (KNN) and Recursive Feature Elimination with RF (RFE-RF) outperformed commonly used linear machine learning methods. For the prediction of tensile strength RFE-RF and KNN achieved R 2 values 98% and 99%, respectively. For the prediction of drug dissolution, two time points were considered with drug release at t = 6 h as a measure of the extent of burst release, and t = 96 h as a measure of sustained release. KNN and RFE-RF achieved R 2 values of 97% and 96%, respectively in predicting the drug release at t = 96 h. This work for the first time reports the prediction of drug dissolution and mechanical properties of drug loaded polymer product from in-line data collected during the HME process.

Supplementary Information

The online version contains supplementary material available at 10.1186/s42252-024-00063-5.

Towards Sustainable and Dynamic Modeling Analysis in Korean Pine Nuts: An Online Learning Approach with NIRS

Due to its advantages such as speed and noninvasive nature, near-infrared spectroscopy (NIRS) technology has been widely used in detecting the nutritional content of nut food. This study aims to address the problem of offline quantitative analysis models producing unsatisfactory results for different batches of samples due to complex and unquantifiable factors such as storage conditions and origin differences of Korean pine nuts. Based on the offline model, an online learning model was proposed using recursive partial least squares (RPLS) regression with online multiplicative scatter correction (OMSC) preprocessing. This approach enables online updates of the original detection model using a small amount of sample data, thereby improving its generalization ability. The OMSC algorithm reduces the prediction error caused by the inability to perform effective scatter correction on the updated dataset. The uninformative variable elimination (UVE) algorithm appropriately increases the number of selected feature bands during the model updating process to expand the range of potentially relevant features. The final model is iteratively obtained by combining new sample feature data with RPLS. The results show that, after OMSC preprocessing, with the number of features increased to 100, the new online model's R2 value for the prediction set is 0.8945. The root mean square error of prediction (RMSEP) is 3.5964, significantly outperforming the offline model, which yields values of 0.4525 and 24.6543, respectively. This indicates that the online model has dynamic and sustainable characteristics that closely approximate practical detection, and it provides technical references and methodologies for the design and development of detection systems. It also offers an environmentally friendly tool for rapid on-site analysis for nut food regulatory agencies and production enterprises.

Development of a Machine Learning Model to Predict the Color of Extruded Thermoplastic Resins

The conventional method for the color-matching process involves the compounding of polymers with pigments and then preparing plaques by using injection molding before measuring the color by an offline spectrophotometer. If the color fails to meet the L*, a*, and b* standards, the color-matching process must be repeated. In this study, the aim is to develop a machine learning model that is capable of predicting offline color using data from inline color measurements, thereby significantly reducing the time that is required for the color-matching process. The inline color data were measured using an inline process spectrophotometer, while the offline color data were measured using a bench-top spectrophotometer. The results showed that the Bagging with Decision Tree Regression and Random Forest Regression can predict the offline color data with aggregated color differences (dE) of 10.87 and 10.75. Compared to other machine learning methods, Bagging with Decision Tree Regression and Random Forest Regression excel due to their robustness, ability to handle nonlinear relationships, and provision of insights into feature importance. This study offers valuable guidance for achieving Bagging with Decision Tree Regression and Random Forest Regression to correlate inline and offline color data, potentially reducing time and material waste in color matching. Furthermore, it facilitates timely corrections in the event of color discrepancies being observed via inline measurements.

Unraveling the influence of solvent composition on Drop-on-Demand binder jet 3D printed tablets containing calcium sulfate hemihydrate

Recently, binder jet printed modular tablets were loaded with three anti-viral drugs via Drop on Demand (DoD) technology where drug solutions prepared in ethanol showed faster release than those prepared in water. During printing, water is used as a binding agent, whereas ethanol is added to maintain the porous structure of the tablets. Thus, the hypothesis is that the porosity would be controlled by manipulating the percentage of water and ethanol. In this study, Rhodamine 6G (R6G) was selected as a model drug due to its high solubility in water and ethanol, visualization function as a fluorescent dye, and potential therapeutic effects for cancer treatment. Approximately, 10 mg/ml R6G solutions were prepared with five different water-ethanol ratios (0-100, 75-25, 50-50, 75-25, 100-0). The ink solutions were printed onto blank binder jet 3D-printed tablets containing calcium sulphate hemihydrate using DoD technology. The tablets were dried at room temperature and then characterized using SEM-EDX, fluorescent microscope, TGA, XRD, FTIR, and DSC as well as in vitro release studies to investigate the impact of water-ethanol ratio on the release profile of R6G. Results indicated that the solution with higher ethanol ratio penetrated the tablets faster than the lower ethanol ratio, while the solution prepared with pure water was first accumulated onto the tablets' surface and then absorbed by the tablets. Moreover, tablets with more water content gained more weight and thickness. The EDX analysis and fluorescent microscope showed the uniform surface distribution of the drug. The SEM images revealed the difference in the tablet surface among the five formulations. Furthermore, the TGA data presents a notable increase in water loss, with XRD analysis suggesting the formation of gypsum in tablets containing elevated water content. The release study exhibited that the fastest release was from WE0-100, whereas the release rate decreases as the content of water increases. The WE0-100 releases more than 40 % drug within the first hour which is almost twice as high of the WE100-0 formulation. This DoD technology could distribute drugs onto the tablet's surface uniformly. The calcium sulfate would transform from hemihydrate to dihydrate form in the presence of water and therefore, those tablets treated with higher water content led to slower release. In conclusion, this study underscores the substantial impact of the water-ethanol ratio on drug release from binder jet printed tablets and highlights the potential of DoD technology for uniform drug distribution and controlled release.

Strategies to improve the stability of amorphous solid dispersions in view of the hot melt extrusion (HME) method

Oral administration of drugs is preferred over other routes for several reasons: it is non-invasive, easy to administer, and easy to store. However, drug formulation for oral administration is often hindered by the drug's poor solubility, which limits its bioavailability and reduces its commercial value. As a solution, amorphous solid dispersion (ASD) was introduced as a drug formulation method that improves drug solubility by changing the molecular structure of the drugs from crystalline to amorphous. The hot melt extrusion (HME) method is emerging in the pharmaceutical industry as an alternative to manufacture ASD. However, despite solving solubility issues, ASD also exposes the drug to a high risk of crystallisation, either during processing or storage. Formulating a successful oral administration drug using ASD requires optimisation of the formulation, polymers, and HME manufacturing processes applied. This review presents some important considerations in ASD formulation, including strategies to improve the stability of the final product using HME to allow more new drugs to be formulated using this method.

Revolutionizing drug formulation development: The increasing impact of machine learning

Over the past few years, the adoption of machine learning (ML) techniques has rapidly expanded across many fields of research including formulation science. At the same time, the use of lipid nanoparticles to enable the successful delivery of mRNA vaccines in the recent COVID-19 pandemic demonstrated the impact of formulation science. Yet, the design of advanced pharmaceutical formulations is non-trivial and primarily relies on costly and time-consuming wet-lab experimentation. In 2021, our group published a review article focused on the use of ML as a means to accelerate drug formulation development. Since then, the field has witnessed significant growth and progress, reflected by an increasing number of studies published in this area. This updated review summarizes the current state of ML directed drug formulation development, introduces advanced ML techniques that have been implemented in formulation design and shares the progress on making self-driving laboratories a reality. Furthermore, this review highlights several future applications of ML yet to be fully exploited to advance drug formulation research and development.

Interpretable Machine Learning Methods for Monitoring Polymer Degradation in Extrusion of Polylactic Acid

This work investigates real-time monitoring of extrusion-induced degradation in different grades of PLA across a range of process conditions and machine set-ups. Data on machine settings together with in-process sensor data, including temperature, pressure, and near-infrared (NIR) spectra, are used as inputs to predict the molecular weight and mechanical properties of the product. Many soft sensor approaches based on complex spectral data are essentially 'black-box' in nature, which can limit industrial acceptability. Hence, the focus here is on identifying an optimal approach to developing interpretable models while achieving high predictive accuracy and robustness across different process settings. The performance of a Recursive Feature Elimination (RFE) approach was compared to more common dimension reduction and regression approaches including Partial Least Squares (PLS), iterative PLS (i-PLS), Principal Component Regression (PCR), ridge regression, Least Absolute Shrinkage and Selection Operator (LASSO), and Random Forest (RF). It is shown that for medical-grade PLA processed under moisture-controlled conditions, accurate prediction of molecular weight is possible over a wide range of process conditions and different machine settings (different nozzle types for downstream fibre spinning) with an RFE-RF algorithm. Similarly, for the prediction of yield stress, RFE-RF achieved excellent predictive performance, outperforming the other approaches in terms of simplicity, interpretability, and accuracy. The features selected by the RFE model provide important insights to the process. It was found that change in molecular weight was not an important factor affecting the mechanical properties of the PLA, which is primarily related to the pressure and temperature at the latter stages of the extrusion process. The temperature at the extruder exit was also the most important predictor of degradation of the polymer molecular weight, highlighting the importance of accurate melt temperature control in the process. RFE not only outperforms more established methods as a soft sensor method, but also has significant advantages in terms of computational efficiency, simplicity, and interpretability. RFE-based soft sensors are promising for better quality control in processing thermally sensitive polymers such as PLA, in particular demonstrating for the first time the ability to monitor molecular weight degradation during processing across various machine settings.

Data-Driven Prediction of the Formation of Co-Amorphous Systems

Co-amorphous systems (COAMS) have raised increasing interest in the pharmaceutical industry, since they combine the increased solubility and/or faster dissolution of amorphous forms with the stability of crystalline forms. However, the choice of the co-former is critical for the formation of a COAMS. While some models exist to predict the potential formation of COAMS, they often focus on a limited group of compounds. Here, four classes of combinations of an active pharmaceutical ingredient (API) with (1) another API, (2) an amino acid, (3) an organic acid, or (4) another substance were considered. A model using gradient boosting methods was developed to predict the successful formation of COAMS for all four classes. The model was tested on data not seen during training and predicted 15 out of 19 examples correctly. In addition, the model was used to screen for new COAMS in binary systems of two APIs for inhalation therapy, as diseases such as tuberculosis, asthma, and COPD usually require complex multidrug-therapy. Three of these new API-API combinations were selected for experimental testing and co-processed via milling. The experiments confirmed the predictions of the model in all three cases. This data-driven model will facilitate and expedite the screening phase for new binary COAMS.

Novel 3D Printed Modular Tablets Containing Multiple Anti-Viral Drugs: a Case of High Precision Drop-on-Demand Drug Deposition

3D printed drug delivery systems have gained tremendous attention in pharmaceutical research due to their inherent benefits over conventional systems, such as provisions for customized design and personalized dosing. The present study demonstrates a novel approach of drop-on-demand (DoD) droplet deposition to dispense drug solutions precisely on binder jetting-based 3D printed multi-compartment tablets containing 3 model anti-viral drugs (hydroxychloroquine sulfate - HCS, ritonavir and favipiravir). The printing pressure affected the printing quality whereas the printing speed and infill density significantly impacted the volume dispersed on the tablets. Additionally, the DoD parameters such as nozzle valve open time and cycle time affected both dispersing volume and the uniformity of the tablets. The solid-state characterization, including DSC, XRD, and PLM, revealed that all drugs remained in their crystalline forms. Advanced surface analysis conducted by microCT imaging as well as Artificial Intelligence (AI)/Deep Learning (DL) model validation showed a homogenous drug distribution in the printed tablets even at ultra-low doses. For a four-hour in vitro drug release study, the drug loaded in the outer layer was released over 90%, and the drug incorporated in the middle layer was released over 70%. In contrast, drug encapsulated in the core was only released about 40%, indicating that outer and middle layers were suitable for immediate release while the core could be applied for delayed release. Overall, this study demonstrates a great potential for tailoring drug release rates from a customized modular dosage form and developing personalized drug delivery systems coupling different 3D printing techniques.

NIR-Based Intelligent Sensing of Product Yield Stress for High-Value Bioresorbable Polymer Processing

PLA (polylactide) is a bioresorbable polymer used in implantable medical and drug delivery devices. Like other bioresorbable polymers, PLA needs to be processed carefully to avoid degradation. In this work we combine in-process temperature, pressure, and NIR spectroscopy measurements with multivariate regression methods for prediction of the mechanical strength of an extruded PLA product. The potential to use such a method as an intelligent sensor for real-time quality analysis is evaluated based on regulatory guidelines for the medical device industry. It is shown that for the predictions to be robust to processing at different times and to slight changes in the processing conditions, the fusion of both NIR and conventional process sensor data is required. Partial least squares (PLS), which is the established 'soft sensing' method in the industry, performs the best of the linear methods but demonstrates poor reliability over the full range of processing conditions. Conversely, both random forest (RF) and support vector regression (SVR) show excellent performance for all criteria when used with a prior principal component (PC) dimension reduction step. While linear methods currently dominate for soft sensing of mixture concentrations in highly conservative, regulated industries such as the medical device industry, this work indicates that nonlinear methods may outperform them in the prediction of mechanical properties from complex physicochemical sensor data. The nonlinear methods show the potential to meet industrial standards for robustness, despite the relatively small amount of training data typically available in high-value material processing.