Theses and Dissertations

Neurological manifestations may be more prominent and have a larger role in ankylosing spondylitis than previously thought. Ankylosing Spondylitis is a rheumatic disease primarily identified by its autoinflammatory characteristics and is highly associated with the HLA-B27 gene. While it’s cause is not yet fully understood and it’s symptoms widely vary, neurological impairment is not uncommon. The neurological manifestations of Ankylosing Spondylitis include but are not limited to pain sensitization, altered brain phenotype, and disrupted cardiac conduction. Central and peripheral nervous system involvement may be more significant than previously thought and have the potential to cause demyelinating diseases, spinal cord, and nerve root injuries. Altered connectivity throughout various regions within the brain further exemplify the need for a better understanding of the disease and better treatment development. Higher instances of depression and dementia were also reported and coincide with not only a less active lifestyle, but altered brain activity. Studies on cardiac conduction and arrhythmias in AS patients revealed parasympathetic and sympathetic nervous system dysregulation. These studies have explored the possibility of new targets for treatment involving cardiac mechanisms. Treatments for diseases of a similar suspected pathology, new prospective targets for therapy, and a more thorough understanding of current treatments for the disease may be the key in providing more substantial relief. By further investigation in the role of the nervous system in Ankylosing Spondylitis, the disease may become more manageable for patients and greatly increase quality of life in the future.

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.