This honors thesis explores using machine learning technology to assist a patient's return to activity following a significant injury, specifically an anterior cruciate ligament (ACL) tear. The goal of the project was to determine if a machine learning model trained with ACL reconstruction (ACLR) applicable injury data would be able to correctly predict which phase of return to sport a patient would be classified in when introduced to a new data set.

This study investigates the impact of technology and social media on religious practices and beliefs concerning death and the afterlife. As the concept of a "Digital Afterlife" becomes more prevalent, questions surrounding its compatibility with religious belief systems and implications on privacy arise. The COVID-19 pandemic has intensified the issue, prompting social media platforms to develop digital wills, although their usage remains limited. This research seeks to explore how the Information Age is shaping the concept of the afterlife, its alignment with major religious belief systems, and perceptions of the digital afterlife across various societal groups. Furthermore, the study examines the role of social media in redefining religious values, norms, and boundaries, highlighting the importance of engaging in an ongoing conversation about the complex and evolving intersection of religion, technology, and death.

Health service quality is understood to be a crucial determinant in successful patient-physician encounters and patient health. One common feeling that patients have reported experiencing during appointments is shame. We hypothesized that patients who experience appearance-based shame during an appointment are not likely to return to the same physician and that patients who do not experience appearance-based shame are likely to return to the same physician. This was assessed by conducting an anonymous online survey of 13 questions that served to establish a general foundation for understanding the participants' physical characteristics such as race, age, weight, and gender identity as well as their overall patient-physician relationship and experiences of shame, if applicable. 119 participants were recruited from Arizona State University and a case study was performed individually for five participants of interest. The data analyzed from this study suggests that while appearance-based shame does exist in healthcare spaces, it is not a significant determining factor in patients returning to their physicians. In addition, there was no significant evidence to suggest that patients who do not experience appearance-based shame are either likely or more likely to return to their physician. We hypothesize this could be due to confounding variables such as convenience, accessibility, or insurance limitations which patients may prioritize over feeling ashamed during an appointment. However, more research needs to be conducted to confirm these hypotheses.

Phoenix Police officers are required to wear Body-Worn Cameras while out on patrol and must have the cameras turned on when interacting with the public. The Body-Worn Camera (BWC) Policy was initially established as a means of accruing evidence and increasing police accountability when in the presence of the public. However, BWC technology has the ability to perform many other useful functions. The information provided by the cameras could be used to reduce the paperwork done by police officers while on duty, thus allowing them to spend more time taking calls from dispatch. The versatility of the body-worn camera and its components also make it an ideal pairing for an electrocardiograph (ECG) device to aid in the health of officers and law enforcement retention.

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.

The ability to externally stimulate gold nanoparticles (GNPs) that are linked to drugs can improve targeted drug delivery to help patients with Parkinson’s disease to increase the activity levels of their basal ganglia to regain motor skills that were once lost. This paper analyzes 5 nm GNPs due to their biocompatibility and ability to cross the blood-brain barrier (BBB). Studies have shown GNPs heat up when exposed to radiofrequency (RF) electromagnetic fields which could be used to release dopamine-related drugs directly in a patient’s basal ganglia to increase activity. However, GNP stimulation often requires a high power output which could damage tissues. A series of methods were used to first characterize the GNPs to ensure the size and viability of the sample. Then, different stimulation tests were run to evaluate the temperature change of GNPs to determine if stimulation is possible in a frequency range that does not require a high power output. The most successful stimulation method utilized a waveguide, which was able to consistently heat GNPs 0.4 C in 15 minutes more than the negative control. The methodology was then tested within the brain of a perfused rat by using magnetic resonance thermometry (MRT). Two scans were taken at different times to solve for the differential pixel value to evaluate whether the brain cooled down over time after being theoretically stimulated initially. While the initial results of these scans were inconclusive, there was much to be improved throughout the process, warranting further research.

Polymeric nanoparticles (NP) consisting of Poly Lactic-co-lactic acid - methyl polyethylene glycol (PLLA-mPEG) or Poly Lactic-co-Glycolic Acid (PLGA) are an emerging field of study for therapeutic and diagnostic applications. NPs have a variety of tunable physical characteristics like size, morphology, and surface topography. They can be loaded with therapeutic and/or diagnostic agents, either on the surface or within the core. NP size is an important characteristic as it directly impacts clearance and where the particles can travel and bind in the body. To that end, the typical target size for NPs is 30-200 nm for the majority of applications. Fabricating NPs using the typical techniques such as drop emulsion, microfluidics, or traditional nanoprecipitation can be expensive and may not yield the appropriate particle size. Therefore, a need has emerged for low-cost fabrication methods that allow customization of NP physical characteristics with high reproducibility. In this study we manufactured a low-cost (<$210), open-source syringe pump that can be used in nanoprecipitation. A design of experiments was utilized to find the relationship between the independent variables: polymer concentration (mg/mL), agitation rate of aqueous solution (rpm), and injection rate of the polymer solution (mL/min) and the dependent variables: size (nm), zeta potential, and polydispersity index (PDI). The quarter factorial design consisted of 4 experiments, each of which was manufactured in batches of three. Each sample of each batch was measured three times via dynamic light scattering. The particles were made with PLLA-mPEG dissolved in a 50% dichloromethane and 50% acetone solution. The polymer solution was dispensed into the aqueous solution containing 0.3% polyvinyl alcohol (PVA). Data suggests that none of the factors had a statistically significant effect on NP size. However, all interactions and relationships showed that there was a negative correlation between the above defined input parameters and the NP size. The NP sizes ranged from 276.144 ± 14.710 nm at the largest to 185.611 ± 15.634 nm at the smallest. In conclusion, the low-cost syringe pump nanoprecipitation method can achieve small sizes like the ones reported with drop emulsion or microfluidics. While there are trends suggesting predictable tuning of physical characteristics, significant control over the customization has not yet been achieved.

Advancing the understanding and treatment of many neurological disorders can be achieved by improving methods of neuronal detection at increased depth in the mammalian brain. Different cell subtypes cannot be detected using non-invasive techniques beyond 1 mm from cortical surface, in the context of targeting particular cell types in vivo (Wang, 2012). These limitations in the depth of imaging and targeting are due to optical scattering (Ntziachristos, 2010). In order to overcome these restrictions, longer wavelength fluorescent proteins have been utilized by researchers to see tagged cells at depth. Optical techniques such as two-photon and confocal microscopy have been used in combination with fluorescent proteins to expand depth, but are still limited by the penetration depth of light due to optical scattering (Lee, 2015). This research aims to build on other detection methods, such as the photoacoustic effect and automated fluorescence-guided electrophysiology, to overcome this limitation.