Development and comparison of machine learning models for in-vitro drug permeation prediction from microneedle patch.

The field of machine learning (ML) is advancing to a larger extent and finding its applications across numerous fields. ML has the potential to optimize the development process of microneedle patch by predicting the drug release pattern prior to its fabrication and production. The early predictions could not only assist the in-vitro and in-vivo experimentation of drug release but also conserve materials, reduce cost, and save time. In this work, we have used a dataset gleaned from the literature to train and evaluate different ML models, such as stacking regressor, artificial neural network (ANN) model, and voting regressor model. In this study, models were developed to improve prediction accuracy of the in-vitro drug release amount from the hydrogel-type microneedle patch and the in-vitro drug permeation amount through the micropores created by solid microneedles on the skin. We compared the performance of these models using various metrics, including R-squared score (R2 score), root mean squared error (RMSE), and mean absolute error (MAE). Voting regressor model performed better with drug permeation percentage as an outcome feature having RMSE value of 3.24. In comparison, stacking regressor have a RMSE value of 16.54, and ANN model has shown a RMSE value of 14. The value of permeation amount calculated from the predicted percentage is found to be more accurate with RMSE of 654.94 than direct amount prediction, having a RMSE of 669.69. All our models have performed far better than the previously developed model before this research, which had a RMSE of 4447.23. We then optimized voting regressor model's hyperparameter and cross validated its performance. Furthermore, it was deployed in a webapp using Flask framework, showing a way to develop an application to allow other users to easily predict drug permeation amount from the microneedle patch at a particular time period. This project demonstrates the potential of ML to facilitate the development of microneedle patch and other drug delivery systems.

Advancements in microneedle fabrication techniques: artificial intelligence assisted 3D-printing technology.

Microneedles (MNs) are micron-scale needles that are a painless alternative to injections for delivering drugs through the skin. MNs find applications as biosensing devices and could serve as real-time diagnosis tools. There have been numerous fabrication techniques employed for producing quality MN-based systems, prominent among them is the three-dimensional (3D) printing. 3D printing enables the production of quality MNs of tuneable characteristics using a variety of materials. Further, the possible integration of artificial intelligence (AI) tools such as machine learning (ML) and deep learning (DL) with 3D printing makes it an indispensable tool for fabricating microneedles. Provided that these AI tools can be trained and act with minimal human intervention to control the quality of products produced, there is also a possibility of mass production of MNs using these tools in the future. This work reviews the specific role of AI in the 3D printing of MN-based devices discussing the use of AI in predicting drug release patterns, its role as a quality control tool, and in predicting the biomarker levels. Additionally, the autonomous 3D printing of microneedles using an integrated system of the internet of things (IoT) and machine learning (ML) is discussed in brief. Different categories of machine learning including supervised learning, semi-supervised learning, unsupervised learning, and reinforced learning have been discussed in brief. Lastly, a brief section is dedicated to the biosensing applications of MN-based devices.

Fabrication of dual drug-loaded polycaprolactone-gelatin composite nanofibers for full thickness diabetic wound healing.

Aim: Design of moxifloxacin and ornidazole co-loaded polycaprolactone and gelatin nanofiber dressing for diabetic wounds. Materials & methods: The composite nanofibers were prepared using electrospinning technique and characterized for in vitro drug release, antibacterial activity, laser doppler and in vivo wound healing. Results: The optimized nanofiber demonstrated an interconnected bead free nanofiber with average diameter <200 nm. The in vitro drug release & antimicrobial studies revealed that optimized nanofiber provided drug release for >120 h, thereby inhibiting growth of Escherichia coli and Stapyhlococcus aureus. An in vivo wound closure study on diabetic rats found that optimized nanofiber group had a significantly higher wound closure rate than marketed formulation. Conclusion: The nanofiber provided prolonged drug release and accelerated wound healing, making it a promising candidate for diabetic wound care.

This article is about making a wound dressing material of tiny fibres that have antibiotic properties to kill microbes at the wound site and make wounds heal faster. This is particularly important for people with diabetes, whose wounds often take longer to heal. The designed nanofibrous dressing releases antibiotic drugs at the wound site for more than 120 h, killing harmful microbes and thus avoiding their invasion at wound site. Also, animal experiments showed that the nanofibers shorten the time wounds take to heal by providing a suitable surface and a favourable environment for wound healing. The study concludes that the fabricated nanofiber dressing helps complex wounds heal faster, and could be a strong new dressing material for diabetic wound care.

Cocrystals by Design: A Rational Coformer Selection Approach for Tackling the API Problems.

Active pharmaceutical ingredients (API) with unfavorable physicochemical properties and stability present a significant challenge during their processing into final dosage forms. Cocrystallization of such APIs with suitable coformers is an efficient approach to mitigate the solubility and stability concerns. A considerable number of cocrystal-based products are currently being marketed and show an upward trend. However, to improve the API properties by cocrystallization, coformer selection plays a paramount role. Selection of suitable coformers not only improves the drug's physicochemical properties but also improves the therapeutic effectiveness and reduces side effects. Numerous coformers have been used till date to prepare pharmaceutically acceptable cocrystals. The carboxylic acid-based coformers, such as fumaric acid, oxalic acid, succinic acid, and citric acid, are the most commonly used coformers in the currently marketed cocrystal-based products. Carboxylic acid-based coformers are capable of forming the hydrogen bond and contain smaller carbon chain with the APIs. This review summarizes the role of coformers in improving the physicochemical and pharmaceutical properties of APIs, and deeply explains the utility of afore-mentioned coformers in API cocrystal formation. The review concludes with a brief discussion on the patentability and regulatory issues related to pharmaceutical cocrystals.

Current Trends in API Co-Processing: Spherical Crystallization and Co-Precipitation Techniques.

Active Pharmaceutical Ingredients (APIs) do not always exhibit processable physical properties, which makes their processing in an industrial setup very demanding. These issues often lead to poor robustness and higher cost of the drug product. The issue can be mitigated by co-processing the APIs using suitable solvent media-based techniques to streamline pharmaceutical manufacturing operations. Some of the co-processing methods are the amalgamation of API purification and granulation steps. These techniques also exhibit adequate robustness for successful adoption by the pharmaceutical industry to manufacture high quality drug products. Spherical crystallization and co-precipitation are solvent media-based co-processing approaches that enhances the micromeritic and dissolution characteristics of problematic APIs. These methods not only improve API characteristics but also enable direct compression into tablets. These methods are economical and time-saving as they have the potential for effectively circumventing the granulation step, which can be a major source of variability in the product. This review highlights the recent advancements pertaining to these techniques to aid researchers in adopting the right co-processing method. Similarly, the possibility of scaling up the production of co-processed APIs by these techniques is discussed. The continuous manufacturability by co-processing is outlined with a short note on Process Analytical Technology (PAT) applicability in monitoring and improving the process.

Co-Crystallization Approach to Enhance the Stability of Moisture-Sensitive Drugs.

Stability is an essential quality attribute of any pharmaceutical formulation. Poor stability can change the color and physical appearance of a drug, directly impacting the patient's perception. Unstable drug products may also face loss of active pharmaceutical ingredients (APIs) and degradation, making the medicine ineffective and toxic. Moisture content is known to be the leading cause of the degradation of nearly 50% of medicinal products, leading to impurities in solid dose formulations. The polarity of the atoms in an API and the surface chemistry of API particles majorly influence the affinity towards water molecules. Moisture induces chemical reactions, including free water that has also been identified as an important factor in determining drug product stability. Among the various approaches, crystal engineering and specifically co-crystals, have a proven ability to increase the stability of moisture-sensitive APIs. Other approaches, such as changing the salt form, can lead to solubility issues, thus making the co-crystal approach more suited to enhancing hygroscopic stability. There are many reported studies where co-crystals have exhibited reduced hygroscopicity compared to pure API, thereby improving the product's stability. In this review, the authors focus on recent updates and trends in these studies related to improving the hygroscopic stability of compounds, discuss the reasons behind the enhanced stability, and briefly discuss the screening of co-formers for moisture-sensitive drugs.