Artificial intelligence (AI) had a few false starts – the AI winters of the 1970s and 1980s. We are now in what looks like an AI summer. There are many useful applications of AI in the field. But there are still unfulfilled promises and outright failures. From self-driving cars that work only in constrained cases, to medical image analysis products that would replace radiologists but never did, we still struggle to translate successful research into successful real-world applications. The software engineering community has accumulated a large body of knowledge over the decades on how to develop, release, and maintain products. AI products, being software products, benefit from some of that accumulated knowledge, but not all of it. AI products diverge from traditional software products in fundamental ways: their main component is not a specific piece of code, written for a specific purpose, but a generic piece of code, a model, customized by a training process driven by hyperparameters and a dataset. Datasets are usually large and models are opaque. We cannot directly inspect them as we can inspect the code of traditional software products. We need other methods to detect failures in AI products. / Includes bibliography. / Thesis (M.S.)--Florida Atlantic University, 2020. / FAU Electronic Theses and Dissertations Collection

No description available.

No description available.

Introduction: Remote Area Medical (RAM), a non-profit organization serving underserved populations, partnered with East Tennessee State University to provide a unique learning opportunity for student volunteers at a clinic in rural Appalachia. Interprofessional student teams were established with undergraduate and graduate students in multiple professions. This study examined the impact on attitudes of students who participated and the impact of student teams on the event, hypothesizing that a positive impact would be seen on both. COVID-19 adjustments made were also evaluated. Methods: Surveys of student participants were conducted electronically utilizing REDCap before and after participation in the event. Surveys included demographic questions, validated surveys, and open-ended questions. Demographic questions gauged personal background, level of education, and history of interprofessional education or events. The previously validated surveys utilized were the Interprofessional Collaborative Competency Attainment Scale-Revised (ICAAS-R) and the Student Perceptions of Interprofessional Clinical Education-Revised Instrument Version 2 (SPICE-R2). Quantitative data was analyzed with SPSS version 25. Qualitative data was analyzed with deductive coding. Interventions were tallied by student teams during the event. Results: Eighty-nine students participated logging 1,213 interventions and 84 completed portions of the survey (94% response rate). ICAAS-R (n=79) displayed mean increases from 4.19 out of 5 in the pre-survey to 4.58 in the post-survey (p Conclusion: Statistically significant quantitative findings and qualitative themes supported the hypothesis that working in interprofessional teams at a RAM event would positively impact student attitudes towards interprofessional practice, and that student teams would have a positive impact on the event. COVID-19 adjustments made were well perceived. Findings can be summarized with the I.M.P.A.C.T. neumonic.

Introduction: About one in four seniors have periodontal disease and significant disparities have been shown to exist between some population groups. This study aimed to ascertain if differences exist in oral health conditions among statistical zones in Tennessee divided into east, middle and western zones. We also sought to explore factors predicting poor oral health outcomes in these zones. We postulated that oral health would differ between at least two zones in Tennessee and socio-demographic and socio-economic factors would predict oral health outcome. Methods: We combined data from the Behavioral Risk Surveillance System using Data from years 2010, 2012, 2014, 2016 (n= 5181). Outcome variable was number of permanent teeth removed which was ordered as- none, one to five, six or more but not all and all. Zones were divided into East Tennessee comprising- Kingsport-Bristol-Bristol Tennessee-Virginia metropolitan statistical area, Knoxville, Tennessee Metropolitan Statistical Area. Middle/Central Tennessee comprising Chattanooga, Tennessee-Georgia, Metropolitan Statistical Area, Nashville-Davidson-Murfreesboro-Franklin, Tennessee Metropolitan Statistical Area and West Tennessee including Memphis, Tennessee-Memphis-Arizona, Metropolitan Statistical Area. Other independent variables included in our models were general health, could not see a doctor because of cost, history of diabetes, smoked at least 100 cigarettes, use of smokeless tobacco products, adults who had visited a dentist and poor physical health. Covariates were income level, education level, employment status, race/ethnicity, year and marital status. Descriptive statistics and initial univariate analysis were done. Variables significant at alpha level of 0.05 were included in the final adjusted Ordinal Logistic regression model with logit link function. Results: From our sample, 37.1% were males and 67.9% were females. Most (43.4%) were married, most had a high school level of education (34%), most were retired (73.5%) and a higher percentage (12.4%) earned less than 25,000 per annum from all sources. A higher number were White (62.7%), and smokers (51.4%) and 31% had at least one permanent tooth removed. All variables and covariates except poor physical and mental health were significantly associated with the outcome variable (P<0.05). On adjusting for covariates, sex, income, employment status and zone of residence in Tennessee were significantly associated with a difference in the number of permanent teeth removed. The observed difference between the Eastern part of Tennessee and the Western part of Tennessee was significantly. Conclusion: Zone of residence, sex, employment status and income predict oral health outcomes in Tennessee. People in East Tennessee are more likely to have increased permanent teeth removed compared to those in the west.

A research report submitted in partial fulfillment of the degree of MSc. Med (Bioethics & Health Law) Steve Biko Centre for Bioethics, Faculty of Health Sciences, University of the Witwatersrand (Wits), Johannesburg November 2017. / Most literature on commercialisation of healthcare reports on the effects of the continuing commodification of healthcare on the doctor-patient relationship. It suggests that the commodification of healthcare as a management practice has the potential to alter the power balance between doctor and patient, and affect the care relationship. This has resulted with the global rebranding of patients as healthcare consumers, in the process impacting on the caring value that characterises the healthcare doctor-patient relationship. In contrast, however, these concerns have not been widely investigated in relation to the nurse-patient relationship. This relationship, grounded as it is in care ethics, has the potential to be severely altered by the pressures of healthcare commodification – particularly as nurses continue to be the primary caregivers in hospital settings. Thus, the study aimed to address this by empirically identifying and exploring areas of ethical tension relating to nurse-patient relationships in a commodified healthcare environment. The objectives of the study were to offer an empirically-based care ethics discussion on nursing care in private healthcare facilities. This study plays a part in addressing the current absence of both theoretical and empirical studies that examine the impact of commodification of healthcare on the actions of nurses. The study used a qualitative, explorative and descriptive approach to thematically analyse data collected from interviews with 16 nurses working in a private healthcare facility in Johannesburg. The findings support the argument that the commodification of healthcare transforms the nature of healthcare provision resulting with the replacement of professional ethics with marketplace ethics. This is harmful to the mutual trust and respect between the nurses and their patients. Hence, it is critical to rethink the value of compassionate and humane care as an integral part of ethical nursing practice. / LG2018

No description available.

Sometimes referred to as “the stethoscope of the future,” ultrasound has many advantages over other imaging techniques which make it ideal for use in primary care. With a unique combination of portability, dynamic imaging, affordability, and real-time interpretation point of care ultrasound (POCUS) is ideal for use in many practice settings. The use of POCUS as the primary imaging modality for many diseases can drastically shorten the time to definitive treatment, and as such is the preferred modality for some presentations. The purpose of this project was to investigate means to improve resident physician knowledge of POCUS and to evaluate if increased knowledge would lead to increased utilization in our outpatient clinic. We started with a pre-test survey covering basic POCUS knowledge as well as a question concerning current utilization of ultrasound imaging in the clinic. We followed that with an educational lecture about the basics of POCUS and some hands-on practice. Afterward a posttest survey was conducted. We found that there was a significant increase in both basic knowledge and the number of residents who intended to use POCUS in the clinic compared to the pre-test. These findings confirm that education on point of care ultrasound can increase both knowledge and utilization in the outpatient clinic. Further education and research could be done to see if there is an actual increase in utilization with continued education.

Staff scheduling is one of the most important challenges that every healthcare organization faces. Long wait times due to the lack of care providers, high salary costs, rigorous work regulations, decreasing workforce availability, and other similar difficulties make it necessary for healthcare decision-makers to pay special attention to this crucial part of their management activities. Staff scheduling decisions can be very difficult. At inpatient clinics, there is not always a good estimate of the demand for services and patients can be discharged at any given time, consequently affecting staff requirements. Moreover, there are many other unpredictable factors affecting the decision process. For example, various seasonal patterns or possible staff leaves due to sickness, vacations, etc. This research describes a solution approach for staff scheduling problems at inpatient clinics where demand for services and patient discharges are considered to be stochastic. The approach is comprehensive enough to be generalizable to a wide range of different inpatient settings with different staff requirements, patient types, and workplace regulations. We first classify patients into a number of patient groups with known care-provider requirements and then develop a predictive model that captures patients’ flow and arrivals for each patient category in the inpatient clinic. This model provides a prediction of the number of patients of each type on each specific day of the planning horizon. Our predictive modelling methodology is based on a Discrete Time Markov model with the number of patients of different types as the state of the system. The predictive model generates a potentially large set of possible scenarios for the system utilization over the planning horizon. We use Monte Carlo Simulation to generate samples of these scenarios and a well known Stochastic Optimization algorithm, called the Sample Average Approximation (SAA) to find a robust solution for the problem across all possible scenarios. The algorithm is linked with a Mixed-Integer Programming (MIP) model which seeks to find the optimal staff schedule over the planning horizon while ensuring maximum demand coverage and cost efficiency are achieved. To check the validity of the proposed approach, we simulated a number of scenarios for different inpatient clinics and evaluated the model’s performance for each of them.

This research study began with an interest in understanding how social workers address poverty and/or low income in hospital settings. It discusses the ways in which hospital social workers address poverty in front line practice, while connecting how the experience of poverty and/or low income can further complicate one’s health and access to healthcare. This paper also discusses the ways that macro political ideologies, structural barriers and societal stigma impact how social workers address poverty in frontline hospital practice. Poverty is a social determinant of health, which is why understanding how hospital social workers address poverty in front line practice is important. Given the influence of neoliberalism and its impact on the growing gap between the rich and poor, it is suggested that poverty and low/income will continue throughout Canadian society. This paper also discusses, how accessing healthcare and navigating the system may become difficult for those experiencing poverty. This study is based on a thematic analysis of the findings from six semi-structured interviews with individuals practicing as social workers in two large teaching hospitals in southern Ontario. The data is interpreted and discussed using a critical framework, specifically, anti-oppressive practice and Marx theory. The subsequent findings indicate that in practice front-line social workers address poverty in practical ways. Major themes that emerged from this research include: addressing stigma, navigating “the system”, systemic and structural barriers, no family, no friends, and connecting with resources. / Thesis / Master of Social Work (MSW)