“ … Kidney Stone Disease Through Models and Machine Learning Ally Atkins *, Advisor: Jue Wang† *Department of … ”
Abstract
Kidney stone (KS) disease is the most common disease of the urinary tract. Over 1.3 million individuals visit emergency departments (ED) for stone-related symptoms, which is projected to increase. Since most lab tests are misinterpreted, leading to an incorrect diagnosis, diagnostic predictive tools are useful to most accurately calculate an individual's likelihood, or risk, of having KS disease. We investigate which predictive model would yield the highest accuracy and sensitivity by extracting information from a clinical database containing patient data and utilize various machine learning and statistical analysis to analyze the performance of each model. With using confusion matrices, logistic regression, and ROC curves, it has been found that including all domains in a predictive model (demographics, laboratory tests, ICD-9 diagnoses, etc.) demonstrated the highest performance.
“ … Vision Assessment (BCI)-Based Color Vision Assessment Ally Atkins Follow this and additional works at: https://digitalworks.union.edu/theses … 1 ABSTRACT Atkins,ALLY Determining Optimal Frequency for Brain-Computer … ”
Abstract
Color vision deficiencies (CVDs) affect over 20% of the population (Delpero et al., 2005). Thus, it is essential to test for CVDs in occupational and academic settings, especially for people with other disabilities. The goal of the present study was to identify the optimal stimulation frequency for BCI-based color vision assessment that enables the assessment of both luminance and hue differences between the light sources. To identify this optimal frequency, settings of the stimulator were chosen from the following criteria: equal luminance but a different hue; equal hue but a different luminance; equal in hue and luminance (i.e., were metamers); elicited an SSVEP of maximum size. Stimulation frequencies ranging from 2-38 Hz were tested. To verify the relationship between SSVEP amplitudes and hue/luminance, this set of test source settings included settings of similar luminances but different hues in addition to settings of different luminances but similar hues. Results suggest that SSVEP size is influenced by hue differences at low frequencies, and SSVEP size at high frequencies is influenced by luminance differences. Additionally, 16 Hz was identified as the optimal frequency for metamer detection. These findings should be used to increase the speed of BCI systems and improve their use in people with color vision deficits.
