Machine Learning and Machine Vision Accelerate 3D Printed Orodispersible Film Development

The role of artificial intelligence in generating original scientific research

Artificial intelligence (AI) is a revolutionary technology that is finding wide application across numerous sectors. Large language models (LLMs) are an emerging subset technology of AI and have been developed to communicate using human languages. At their core, LLMs are trained with vast amounts of information extracted from the internet, including text and images. Their ability to create human-like, expert text in almost any subject means they are increasingly being used as an aid to presentation, particularly in scientific writing. However, we wondered whether LLMs could go further, generating original scientific research and preparing the results for publication. We taskedGPT-4, an LLM, to write an original pharmaceutics manuscript, on a topic that is itself novel. It was able to conceive a research hypothesis, define an experimental protocol, produce photo-realistic images of 3D printed tablets, generate believable analytical data from a range of instruments and write a convincing publication-ready manuscript with evidence of critical interpretation. The model achieved all this is less than 1 h. Moreover, the generated data were multi-modal in nature, including thermal analyses, vibrational spectroscopy and dissolution testing, demonstrating multi-disciplinary expertise in the LLM. One area in which the model failed, however, was in referencing to the literature. Since the generated experimental results appeared believable though, we suggest that LLMs could certainly play a role in scientific research but with human input, interpretation and data validation. We discuss the potential benefits and current bottlenecks for realising this ambition here.

Rising role of 3D-printing in delivery of therapeutics for infectious disease

Modern drug delivery to tackle infectious disease has drawn close to personalizing medicine for specific patient populations. Challenges include antibiotic-resistant infections, healthcare associated infections, and customizing treatments for local patient populations. Recently, 3D-printing has become a facilitator for the development of personalized pharmaceutic drug delivery systems. With a variety of manufacturing techniques, 3D-printing offers advantages in drug delivery development for controlled, fine-tuned release and platforms for different routes of administration. This review summarizes 3D-printing techniques in pharmaceutics and drug delivery focusing on treating infectious diseases, and discusses the influence of 3D-printing design considerations on drug delivery platforms targeting these diseases. Additionally, applications of 3D-printing in infectious diseases are summarized, with the goal to provide insight into how future delivery innovations may benefit from 3D-printing to address the global challenges in infectious disease.

3D printing of biologics-what has been accomplished to date?

Three-dimensional (3D) printing is a promising approach for the stabilization and delivery of non-living biologics. This versatile tool builds complex structures and customized resolutions, and has significant potential in various industries, especially pharmaceutics and biopharmaceutics. Biologics have become increasingly prevalent in the field of medicine due to their diverse applications and benefits. Stability is the main attribute that must be achieved during the development of biologic formulations. 3D printing could help to stabilize biologics by entrapment, support binding, or crosslinking. Furthermore, gene fragments could be transited into cells during co-printing, when the pores on the membrane are enlarged. This review provides: (i) an introduction to 3D printing technologies and biologics, covering genetic elements, therapeutic proteins, antibodies, and bacteriophages; (ii) an overview of the applications of 3D printing of biologics, including regenerative medicine, gene therapy, and personalized treatments; (iii) information on how 3D printing could help to stabilize and deliver biologics; and (iv) discussion on regulations, challenges, and future directions, including microneedle vaccines, novel 3D printing technologies and artificial-intelligence-facilitated research and product development. Overall, the 3D printing of biologics holds great promise for enhancing human health by providing extended longevity and enhanced quality of life, making it an exciting area in the rapidly evolving field of biomedicine.

Virtually Possible: Enhancing Quality Control of 3D-Printed Medicines with Machine Vision Trained on Photorealistic Images

Three-dimensional (3D) printing is an advanced pharmaceutical manufacturing technology, and concerted efforts are underway to establish its applicability to various industries. However, for any technology to achieve widespread adoption, robustness and reliability are critical factors. Machine vision (MV), a subset of artificial intelligence (AI), has emerged as a powerful tool to replace human inspection with unprecedented speed and accuracy. Previous studies have demonstrated the potential of MV in pharmaceutical processes. However, training models using real images proves to be both costly and time consuming. In this study, we present an alternative approach, where synthetic images were used to train models to classify the quality of dosage forms. We generated 200 photorealistic virtual images that replicated 3D-printed dosage forms, where seven machine learning techniques (MLTs) were used to perform image classification. By exploring various MV pipelines, including image resizing and transformation, we achieved remarkable classification accuracies of 80.8%, 74.3%, and 75.5% for capsules, tablets, and films, respectively, for classifying stereolithography (SLA)-printed dosage forms. Additionally, we subjected the MLTs to rigorous stress tests, evaluating their scalability to classify over 3000 images and their ability to handle irrelevant images, where accuracies of 66.5% (capsules), 72.0% (tablets), and 70.9% (films) were obtained. Moreover, model confidence was also measured, and Brier scores ranged from 0.20 to 0.40. Our results demonstrate promising proof of concept that virtual images exhibit great potential for image classification of SLA-printed dosage forms. By using photorealistic virtual images, which are faster and cheaper to generate, we pave the way for accelerated, reliable, and sustainable AI model development to enhance the quality control of 3D-printed medicines.

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.

Preparation and Evaluation of Caffeine Orodispersible Films: The Influence of Hydrotropic Substances and Film-Forming Agent Concentration on Film Properties

This study aimed to develop caffeine (CAF) orodispersible films (ODFs) and verify the effects of different percentages of film-forming agent and hydrotropic substances (citric acid-CA or sodium benzoate-SB) on various film properties. Hydroxypropyl methylcellulose E 5 (HPMC E 5) orodispersible films were prepared using the solvent casting method. Four CAF-ODF formulations were prepared and coded as CAF1 (8% HPMC E 5, CAF), CAF2 (8% HPMC E 5 and CAF:CA-1:1), CAF3 (9% HPMC E 5 and CAF:CA-1:1), and CAF4 (9% HPMC E 5 and CAF:SB-1:1). The CAF-ODFs were evaluated in terms of disintegration time, folding endurance, thickness, uniformity of mass, CAF content, thickness-normalized tensile strength, adhesiveness, dissolution, and pH. Thin, opaque, and slightly white CAF-ODFs were obtained. All the formulations developed exhibited disintegration times less than 3 min. The dissolution test revealed that CAF1, CAF2, and CAF3 exhibited concentrations of active pharmaceutical ingredients (APIs) released at 30 min that were close to 100%, whilst CAF4 showed a faster dissolution behaviour (100% of the CAF was released at 5 min). Thin polymeric films containing 10 mg of CAF/surface area (3.14 cm²) were prepared.

Energy Consumption and Carbon Footprint of 3D Printing in Pharmaceutical Manufacture

Achieving carbon neutrality is seen as an important goal in order to mitigate the effects of climate change, as carbon dioxide is a major greenhouse gas that contributes to global warming. Many countries, cities and organizations have set targets to become carbon neutral. The pharmaceutical sector is no exception, being a major contributor of carbon emissions (emitting approximately 55% more than the automotive sector for instance) and hence is in need of strategies to reduce its environmental impact. Three-dimensional (3D) printing is an advanced pharmaceutical fabrication technology that has the potential to replace traditional manufacturing tools. Being a new technology, the environmental impact of 3D printed medicines has not been investigated, which is a barrier to its uptake by the pharmaceutical industry. Here, the energy consumption (and carbon emission) of 3D printers is considered, focusing on technologies that have successfully been demonstrated to produce solid dosage forms. The energy consumption of 6 benchtop 3D printers was measured during standby mode and printing. On standby, energy consumption ranged from 0.03 to 0.17 kWh. The energy required for producing 10 printlets ranged from 0.06 to 3.08 kWh, with printers using high temperatures consuming more energy. Carbon emissions ranged between 11.60-112.16 g CO₂ (eq) per 10 printlets, comparable with traditional tableting. Further analyses revealed that decreasing printing temperature was found to reduce the energy demand considerably, suggesting that developing formulations that are printable at lower temperatures can reduce CO₂ emissions. The study delivers key initial insights into the environmental impact of a potentially transformative manufacturing technology and provides encouraging results in demonstrating that 3D printing can deliver quality medicines without being environmentally detrimental.

Machine learning in additive manufacturing & Microfluidics for smarter and safer drug delivery systems

A new technological passage has emerged in the pharmaceutical field, concerning the management, application, and transfer of knowledge from humans to machines, as well as the implementation of advanced manufacturing and product optimisation processes. Machine Learning (ML) methods have been introduced to Additive Manufacturing (AM) and Microfluidics (MFs) to predict and generate learning patterns for precise fabrication of tailor-made pharmaceutical treatments. Moreover, regarding the diversity and complexity of personalised medicine, ML has been part of quality by design strategy, targeting towards the development of safe and effective drug delivery systems. The utilisation of different and novel ML techniques along with Internet of Things sensors in AM and MFs, have shown promising aspects regarding the development of well-defined automated procedures towards the production of sustainable and quality-based therapeutic systems. Thus, the effective data utilisation, prospects on a flexible and broader production of "on demand" treatments. In this study, a thorough overview has been achieved, concerning scientific achievements of the past decade, which aims to trigger the research interest on incorporating different types of ML in AM and MFs, as essential techniques for the enhancement of quality standards of customised medicinal applications, as well as the reduction of variability potency, throughout a pharmaceutical process.

Machine learning using multi-modal data predicts the production of selective laser sintered 3D printed drug products

Three-dimensional (3D) printing is drastically redefining medicine production, offering digital precision and personalized design opportunities. One emerging 3D printing technology is selective laser sintering (SLS), which is garnering attention for its high precision, and compatibility with a wide range of pharmaceutical materials, including low-solubility compounds. However, the full potential of SLS for medicines is yet to be realized, requiring expertise and considerable time-consuming and resource-intensive trial-and-error research. Machine learning (ML), a subset of artificial intelligence, is an in silico tool that is accomplishing remarkable breakthroughs in several sectors for its ability to make highly accurate predictions. Therefore, the present study harnessed ML to predict the printability of SLS formulations. Using a dataset of 170 formulations from 78 materials, ML models were developed from inputs that included the formulation composition and characterization data retrieved from Fourier-transformed infrared spectroscopy (FT-IR), X-ray powder diffraction (XRPD) and differential scanning calorimetry (DSC). Multiple ML models were explored, including supervised and unsupervised approaches. The results revealed that ML can achieve high accuracies, by using the formulation composition leading to a maximum F1 score of 81.9%. Using the FT-IR, XRPD and DSC data as inputs resulted in an F1 score of 84.2%, 81.3%, and 80.1%, respectively. A subsequent ML pipeline was built to combine the predictions from FT-IR, XRPD and DSC into one consensus model, where the F1 score was found to further increase to 88.9%. Therefore, it was determined for the first time that ML predictions of 3D printability benefit from multi-modal data, combining numeric, spectral, thermogram and diffraction data. The study lays the groundwork for leveraging existing characterization data for developing high-performing computational models to accelerate formulation development.

Buccal films: A review of therapeutic opportunities, formulations & relevant evaluation approaches

The potential of the mucoadhesive film technology is hard to ignore, owing to perceived superior patient acceptability versus buccal tablets, and significant therapeutic opportunities compared to conventional oral drug delivery systems, especially for those who suffer from dysphagia. In spite of this, current translation from published literature into the commercial marketplace is virtually non-existent, with no authorised mucoadhesive buccal films available in the UK and very few available in the USA. This review seeks to provide an overview of the mucoadhesive buccal film technology and identify key areas upon which to focus scientific efforts to facilitate the wider adoption of this patient-centric dosage form. Several indications and opportunities for development were identified, while discussing the patient-related factors influencing the use of these dosage forms. In addition, an overview of the technologies behind the manufacturing of these films was provided, highlighting manufacturing methods like solvent casting, hot melt extrusion, inkjet printing and three-dimensional printing. Over thirty mucoadhesive polymers were identified as being used in film formulations, with details surrounding their mucoadhesive capabilities as well as their inclusion alongside other key formulation constituents provided. Lastly, the importance of physiologically relevant in vitro evaluation methodologies was emphasised, which seek to improve in vivo correlations, potentially leading to better translation of mucoadhesive buccal films from the literature into the commercial marketplace.

Modernising Orodispersible Film Characterisation to Improve Palatability and Acceptability Using a Toolbox of Techniques

Orodispersible films (ODFs) have been widely used in paediatric, geriatric and dysphagic patients due to ease of administration and precise and flexible dose adjustments. ODF fabrication has seen significant advancements with the move towards more technologically advanced production methods. The acceptability of ODFs is dependent upon film composition and process of formation, which affects disintegration, taste, texture and mouthfeel. There is currently a lack of testing to accurately assess ODFs for these important acceptability sensory perceptions. This study produced four ODFs formed of polyvinyl alcohol and sodium carboxymethylcellulose using 3D printing. These were assessed using three in vitro methods: Petri dish and oral cavity model (OCM) methods for disintegration and bio-tribology for disintegration and oral perception. Increasing polymer molecular weight (MW) exponentially increased disintegration time in the Petri dish and OCM methods. Higher MW films adhered to the OCM upper palate. Bio-tribology analysis showed that films of higher MW disintegrated quickest and had lower coefficient of friction, perhaps demonstrating good oral perception but also stickiness, with higher viscosity. These techniques, part of a toolbox, may enable formulators to design, test and reformulate ODFs that both disintegrate rapidly and may be better perceived when consumed, improving overall treatment acceptability.

Advancing pharmacy and healthcare with virtual digital technologies

Digitalisation of the healthcare sector promises to revolutionise patient healthcare globally. From the different technologies, virtual tools including artificial intelligence, blockchain, virtual, and augmented reality, to name but a few, are providing significant benefits to patients and the pharmaceutical sector alike, ranging from improving access to clinicians and medicines, as well as improving real-time diagnoses and treatments. Indeed, it is envisioned that such technologies will communicate together in real-time, as well as with their physical counterparts, to create a large-scale, cyber healthcare system. Despite the significant benefits that virtual-based digital health technologies can bring to patient care, a number of challenges still remain, ranging from data security to acceptance within the healthcare sector. This review provides a timely account of the benefits and challenges of virtual health interventions, as well an outlook on how such technologies can be transitioned from research-focused towards real-world healthcare and pharmaceutical applications to transform treatment pathways for patients worldwide.