Dexamethasone-releasing cochlear implant coatings: application of artificial neural networks for modelling of formulation parameters and drug release profile

Recent Advances in the Application of Artificial Intelligence in Otorhinolaryngology-Head and Neck Surgery

This study presents an up-to-date survey of the use of artificial intelligence (AI) in the field of otorhinolaryngology, considering opportunities, research challenges, and research directions. We searched PubMed, the Cochrane Central Register of Controlled Trials, Embase, and the Web of Science. We initially retrieved 458 articles. The exclusion of non-English publications and duplicates yielded a total of 90 remaining studies. These 90 studies were divided into those analyzing medical images, voice, medical devices, and clinical diagnoses and treatments. Most studies (42.2%, 38/90) used AI for image-based analysis, followed by clinical diagnoses and treatments (24 studies). Each of the remaining two subcategories included 14 studies. Machine learning and deep learning have been extensively applied in the field of otorhinolaryngology. However, the performance of AI models varies and research challenges remain.

Machine Learning and Cochlear Implantation-A Structured Review of Opportunities and Challenges

OBJECTIVE

The use of machine learning technology to automate intellectual processes and boost clinical process efficiency in medicine has exploded in the past 5 years. Machine learning excels in automating pattern recognition and in adapting learned representations to new settings. Moreover, machine learning techniques have the advantage of incorporating complexity and are free from many of the limitations of traditional deterministic approaches. Cochlear implants (CI) are a unique fit for machine learning techniques given the need for optimization of signal processing to fit complex environmental scenarios and individual patients' CI MAPping. However, there are many other opportunities where machine learning may assist in CI beyond signal processing. The objective of this review was to synthesize past applications of machine learning technologies for pediatric and adult CI and describe novel opportunities for research and development.

DATA SOURCES

The PubMed/MEDLINE, EMBASE, Scopus, and ISI Web of Knowledge databases were mined using a directed search strategy to identify the nexus between CI and artificial intelligence/machine learning literature.

STUDY SELECTION

Non-English language articles, articles without an available abstract or full-text, and nonrelevant articles were manually appraised and excluded. Included articles were evaluated for specific machine learning methodologies, content, and application success.

DATA SYNTHESIS

The database search identified 298 articles. Two hundred fifty-nine articles (86.9%) were excluded based on the available abstract/full-text, language, and relevance. The remaining 39 articles were included in the review analysis. There was a marked increase in year-over-year publications from 2013 to 2018. Applications of machine learning technologies involved speech/signal processing optimization (17; 43.6% of articles), automated evoked potential measurement (6; 15.4%), postoperative performance/efficacy prediction (5; 12.8%), and surgical anatomy location prediction (3; 7.7%), and 2 (5.1%) in each of robotics, electrode placement performance, and biomaterials performance.

CONCLUSION

The relationship between CI and artificial intelligence is strengthening with a recent increase in publications reporting successful applications. Considerable effort has been directed toward augmenting signal processing and automating postoperative MAPping using machine learning algorithms. Other promising applications include augmenting CI surgery mechanics and personalized medicine approaches for boosting CI patient performance. Future opportunities include addressing scalability and the research and clinical communities' acceptance of machine learning algorithms as effective techniques.

Use of artificial neural networks for analysis of the factors affecting particle size in mebudipine nanoemulsion

In this study, a nanoemulsion containing mebudipine [composed of ethyl oleate (oil phase), Tween 80 (T80), Span 80 (S80) (surfactants), polyethylene glycol 400, ethanol (cosurfactants), and deionized water] was prepared with the aim of improving its bioavailability for an effective antihypertensive therapy. Particle size of the formulation was measured by dynamic light scattering. Then, artificial neural networks were used in identifying factors that influence the particle size of the nanoemulsion. Three variables, namely, amount of surfactant system (T80 + S80), amount of polyethylene glycol, and amount of ethanol as cosurfactants, were considered as input values and the particle size was used as output. The developed model showed that all the three inputs had some degrees of effect on particles size: increasing the value of each input decreased the size. Furthermore, amount of surfactant was found to be the dominant factor in controlling the final particle size of nanoemulsion. Communicated by Ramaswamy H. Sarma.

How to adjust dexamethasone mobility in silicone matrices: A quantitative treatment

Silicone-based drug delivery systems offer a great potential to improve the therapeutic efficacy and safety of a large variety of medical treatments, e.g. allowing for local long-term delivery of active agents to the inner ear. Different formulation parameters can be varied to adjust desired drug release kinetics. However, often only qualitative information is available on their effects, and product optimization is cumbersome. The aim of this study was to provide a quantitative analysis, allowing also for theoretical predictions of the impact of the device design on system performance. Dexamethasone was incorporated into thin films based on different types of silicones (e.g. varying in the type of side chains and contents of amorphous silica), optionally containing different types and amounts of poly(ethylene glycol) (PEG) (5% or 10%). Furthermore, the initial drug content was altered (from 10% to 50%). In most cases, an analytical solution of Fick's second law could be used to describe the resulting drug release kinetics from the films and to determine the respective "apparent" diffusion coefficient of the drug (which varied from 2×10(-14) to 2×10(-12)cm(2)/s, depending on the system's composition). Thus, the impact of the investigated formulation parameters on drug mobility in the polymeric matrices could be quantitatively described. Importantly, the knowledge of the "apparent" drug diffusivity can be used to theoretically predict the resulting release kinetics from dosage forms of arbitrary size and shape. For instance, dexamethasone release was theoretically predicted from cylindrical extrudates based on a selection of different silicone types. Interestingly, these predictions could be confirmed by independent experiments. Hence, this type of quantitative analysis can replace time-consuming and cost-intensive series of trial-and-error experiments during product optimization. This is particularly helpful, if long-term drug release (e.g., during several weeks, months or years) is targeted.

Artificial neural networks for bilateral prediction of formulation parameters and drug release profiles from cochlear implant coatings fabricated as porous monolithic devices based on silicone rubber

Objectives

The coating of cochlear implants for topical delivery of drugs, for example, corticosteroids, or antibiotics is a novel approach to manage post-surgical complications associated with cochlear implantation surgery like inflammation or infections. Many variables, including formulation parameters, can be changed to modulate the amount and duration of drug release from these devices. Mathematical modeling of drug release profile from a delivery system may be helpful to accelerate formulations in a more cost-efficient way. To attain specific in vitro drug release characteristics, a model should be capable to provide good estimates on the initial formulation parameters, for example, composition, geometry and drug loading vice versa. Here, artificial neural networks (ANNs) are used to predict dexamethasone (DEX) release profile and formulation parameters, bilaterally, from cochlear implant coatings designed as porous, monolithic silicone rubber-based matrices.

Methods

The devices were fabricated as monolithic dispersions of DEX in a silicone rubber matrix containing porogens. A newly developed mathematical function was fitted on the experimental DEX release curves, and the function coefficients were fed into the network as input variables to simulate drug release profile from the porous devices. Formulation variables consisted of drug loading percentage (0.05–0.5% w/w), porogen type (dextran (dext) or sodium chloride particles) and porogen content (5–40% w/w). The ANN was also examined to determine optimal levels of the formulation parameters to provide a specifically desired drug release profile.

Key findings

The results showed that DEX release profile from porous cochlear implant devices can be modelled accurately and precisely using ANN in order to predict optimal levels for the formulation parameters to provide a specific drug release profile vice versa.

Conclusions

The developed ANNs were used to achieve shorter formulation development process, and to provide tailor-made drug delivery regimens. ANNs were also successfully simulated non-linear relationships present between the initial formulation variable(s) and predict the subsequent drug release patterns.