Filtering by
- All Subjects: Machine Learning
Polymer drug delivery system offers a key to a glaring issue in modern administration routes of drugs and biologics. Poly(lactic-co-glycolic acid) (PLGA) can be used to encapsulate drugs and biologics and deliver them into the patient, which allows high local concentration (compared to current treatment methods), protection of the cargo from the bodily environment, and reduction in systemic side effects. This experiment used a single emulsion technique to encapsulate L-tyrosine in PLGA microparticles and UV spectrophotometry to analyze the drug release over a period of one week. The release assay found that for the tested samples, the released amount is distinct initially, but is about the same after 4 days, and they generally follow the same normalized percent released pattern. The experiment could continue with testing more samples, test the same samples for a longer duration, and look into higher w/w concentrations such as 20% or 50%.
Colorimetric assays are an important tool in point-of-care testing that offers several advantages to traditional testing methods such as rapid response times and inexpensive costs. A factor that currently limits the portability and accessibility of these assays are methods that can objectively determine the results of these assays. Current solutions consist of creating a test reader that standardizes the conditions the strip is under before being measured in some way. However, this increases the cost and decreases the portability of these assays. The focus of this study is to create a machine learning algorithm that can objectively determine results of colorimetric assays under varying conditions. To ensure the flexibility of a model to several types of colorimetric assays, three models were trained on the same convolutional neural network with different datasets. The images these models are trained on consist of positive and negative images of ETG, fentanyl, and HPV Antibodies test strips taken under different lighting and background conditions. A fourth model is trained on an image set composed of all three strip types. The results from these models show it is able to predict positive and negative results to a high level of accuracy.