ABSTRACT
Background and objective The coronavirus disease 2019 (COVID-19) vaccination rates and predictors of vaccine uptake among patients with chronic obstructive pulmonary disease (COPD) in the United States are unknown. In light of this, we assessed COVID-19 vaccination rates in this population and evaluated predictors of vaccine uptake. Methods Using 2022 survey data from the National Health Interview Survey (NHIS), 1486 adults with COPD who responded with "yes/no" to whether they had received the COVID-19 vaccine were identified, including those who had received booster doses. A chi-square test was used to ascertain differences between those who had received the vaccine and those who had not, as well as between those who had received booster doses and those who had not. A logistic regression was used to evaluate predictors of COVID-19 vaccination uptake. Results A total of 1195 individuals among 1486 respondents with chronic pulmonary disease (78.4%) had been vaccinated against COVID-19, and 789/1195 (62.5%) had received booster shots. The majority of individuals were aged 65 years and above, exceeded the 1+ threshold for the ratio of family income to poverty (RFIP), and were covered by insurance. Positive predictors of COVID-19 vaccination were as follows: age 40 - 64 years (OR: 2.34, 95% CI: 1.31 - 4.19; p=0.004) and 65 years and above (OR: 1.93, 95% CI: 1.36 - 2.72; p<0.001), RFIP threshold of ≥1 (OR: 2.02, 95% CI: 1.42 - 2.88; p<0.001), having a college degree (OR: 1.92, 95% CI: 1.92 - 3.26, p=0.016), and being insured (OR: 3.12, 95% CI: 1.46 - 6.66, p=0.003). The current smoking habit negatively predicted the uptake (OR: 0.54, 95% CI: 0.33 - 0.87, p=0.012). The positive predictors of COVID-19 vaccination boosters were as follows: age 40 - 64 years (OR: 2.72, 95% CI: 1.39 - 5.30, p=0.003) and 65 years and above (OR: 4.85, 95% CI: 2.45 - 9.58, p<0.001). Being from the non-Hispanic (NH) black ethnicity negatively predicted receiving the COVID-19 booster (OR: 0.55, 95% CI: 0.36 - 0.85, p=0.007). Conclusions While COVID-19 vaccination rates are fairly satisfactory in COPD patients, the uptake of booster vaccines is relatively lower in this population. Socioeconomic and behavioral factors are associated with poor vaccine uptake, and targeted interventions should be implemented to address these factors.
ABSTRACT
Embedded systems technology is undergoing a phase of transformation owing to the novel advancements in computer architecture and the breakthroughs in machine learning applications. The areas of applications of embedded machine learning (EML) include accurate computer vision schemes, reliable speech recognition, innovative healthcare, robotics, and more. However, there exists a critical drawback in the efficient implementation of ML algorithms targeting embedded applications. Machine learning algorithms are generally computationally and memory intensive, making them unsuitable for resource-constrained environments such as embedded and mobile devices. In order to efficiently implement these compute and memory-intensive algorithms within the embedded and mobile computing space, innovative optimization techniques are required at the algorithm and hardware levels. To this end, this survey aims at exploring current research trends within this circumference. First, we present a brief overview of compute intensive machine learning algorithms such as hidden Markov models (HMM), k-nearest neighbors (k-NNs), support vector machines (SVMs), Gaussian mixture models (GMMs), and deep neural networks (DNNs). Furthermore, we consider different optimization techniques currently adopted to squeeze these computational and memory-intensive algorithms within resource-limited embedded and mobile environments. Additionally, we discuss the implementation of these algorithms in microcontroller units, mobile devices, and hardware accelerators. Conclusively, we give a comprehensive overview of key application areas of EML technology, point out key research directions and highlight key take-away lessons for future research exploration in the embedded machine learning domain.
