The purpose of this study, which was done in conjunction with the Arizona Heart Foundation, was to evaluate whether pyridoxine accelerates ulcer wound healing in diabetic patients with ulcers in the lower extremities. In this study, 100 mg of pyridoxine per day was given to patients in the experimental group (while they receive normal wound treatment) while patients in the control group received normal treatment of wounds without the pyridoxine. Over time, wound healing was evaluated by photographing and then measuring the size of patients' ulcer wounds on the photographs. Results from the experimental group were compared with those of the control group to evaluate the efficacy of the pyridoxine treatment. In addition, comparisons of the healing rates were made with respect to whether the patients smoked, had hypertension or hypotension, and the patients' body mass indexes. It has been found that there was no statistically significant difference in the mean healing rates between the control groups and experimental groups. In addition, it has been found that smoking, BMI and blood pressure did not have a statistically appreciable effect on the difference in mean healing rates between the control and experimental groups. This is evidence that pyridoxine did not have a statistically significant effect on wound healing rates.

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.

Carbohydrate counting has been shown to improve HbA1c levels for people with diabetes. However, the learning curve and inconvenience of carbohydrate counting make it difficult for patients to adhere to it. A deep learning model is proposed to identify food from an image, where it can help the user manage their carbohydrate counting. This early model has a 68.3% accuracy of identifying 101 different food classes. A more refined model in future work could be deployed into a mobile application to identify food the user is about to consume and log it for easier carbohydrate counting.

Protein and gene circuit level synthetic bioengineering can require years to develop a single target. Phage assisted continuous evolution (PACE) is a powerful new tool for rapidly engineering new genes and proteins, but the method requires an automated cell culture system, making it inaccessible to non industrial research programs. Complex protein functions, like specific binding, require similarly dynamic PACE selection that can be alternatively induced or suppressed, with heat labile chemicals like tetracycline. Selection conditions must be controlled continuously over days, with adjustments made every few minutes. To make PACE experiments accessible to the broader community, we designed dedicated cell culture hardware and integrated optogenetically controlled plasmids. The low cost and open source platform allows a user to conduct PACE with continuous monitoring and precise control of evolution using light.

Although relatively new technology, machine learning has rapidly demonstrated its many uses. One potential application of machine learning is the diagnosis of ailments in medical imaging. Ideally, through classification methods, a computer program would be able to identify different medical conditions when provided with an X-ray or other such scan. This would be very beneficial for overworked doctors, and could act as a potential crutch to aid in giving accurate diagnoses. For this thesis project, five different machine-learning algorithms were tested on two datasets containing 5,856 lung X-ray scans labeled as either “Pneumonia” or “Normal”. The goal was to determine which algorithm achieved the highest accuracy, as well as how preprocessing the data affected the accuracy of the models. The following supervised-learning methods were tested: support vector machines, logistic regression, decision trees, random forest, and a convolutional neural network. Each model was adjusted independently in order to achieve maximum performance before accuracy metrics were generated to pit the models against each other. Additionally, the effect of resizing images on model performance was investigated. Overall, a convolutional neural network proved to be the superior model for pneumonia detection, with a 91% accuracy. After resizing to 28x28, CNN accuracy decreased to 85%. The random forest model performed second best. The 28x28 PneumoniaMNIST dataset achieved higher accuracy using traditional machine learning models than the HD Chest X-Ray dataset. Resizing the Chest X-ray images had minimal effect on traditional model performance when resized to 28x28 or larger.