Predictors of Mpox vaccine uptake among sexual and gender minority young adults living in Illinois: Unvaccinated vs. double vs. single dose vaccine recipients.

INTRODUCTION: The 2022 global outbreak of Monkeypox virus (Mpox), which has primarily spread through the sexual networks of sexual and gender minority (SGM) individuals, has introduced new public health challenges. While an efficacious Mpox vaccine is in active circulation, few Mpox vaccine studies have examined its uptake among SGM groups. The aims of this study were to investigate (a) the prevalence of Mpox vaccine uptake among SGM and (b) the contextual, Mpox-disease specific, and Mpox-vaccine specific factors associated with Mpox vaccine among SGM. METHODS: We conducted a cross-sectional survey in Illinois, USA in September 2022; 320 young SGM completed self-administered questionnaires. Multinomial logistic regression was used to assess the contextual, Mpox-disease specific, and Mpox-vaccine specific factors associated with Mpox vaccine uptake. Adjusted Odds Ratios (aORs) and 95 % Confidence Intervals (CI) are reported. RESULTS: Approximately 50 % of the SGM participants included in this study had received at least their first dose of the Mpox vaccine. Multinomial regression analysis showed that individuals who had recently experienced food insecurity, had higher degrees of fear of social rejection due to Mpox acquisition, and were more Mpox-vaccine hesitant were more likely to be unvaccinated. Conversely, knowing people who have contracted Mpox, having higher formal educational attainment, having higher degrees of Mpox-related internalized heterosexism, and being more concerned about one's safety regarding Mpox morbidity were more likely to be double-dosers. CONCLUSION: Approximately 50 % of the SGMs included in this study received at least their first dose of the Mpox vaccine; however, only one-quarter of participants completed the recommended 2-dose Mpox regimen. Our findings indicate that socioeconomic stability, fear of social rejection due to disease acquisition, and Mpox-specific vaccine hesitancy may be important structural targets to consider when developing vaccine-uptake prevention and intervention strategies tailored to the needs of sexual and gender minorities.

Deep learning models for COVID-19 chest x-ray classification: Preventing shortcut learning using feature disentanglement.

In response to the COVID-19 global pandemic, recent research has proposed creating deep learning based models that use chest radiographs (CXRs) in a variety of clinical tasks to help manage the crisis. However, the size of existing datasets of CXRs from COVID-19+ patients are relatively small, and researchers often pool CXR data from multiple sources, for example, using different x-ray machines in various patient populations under different clinical scenarios. Deep learning models trained on such datasets have been shown to overfit to erroneous features instead of learning pulmonary characteristics in a phenomenon known as shortcut learning. We propose adding feature disentanglement to the training process. This technique forces the models to identify pulmonary features from the images and penalizes them for learning features that can discriminate between the original datasets that the images come from. We find that models trained in this way indeed have better generalization performance on unseen data; in the best case we found that it improved AUC by 0.13 on held out data. We further find that this outperforms masking out non-lung parts of the CXRs and performing histogram equalization, both of which are recently proposed methods for removing biases in CXR datasets.

Effective deep learning approaches for predicting COVID-19 outcomes from chest computed tomography volumes.

The rapid evolution of the novel coronavirus disease (COVID-19) pandemic has resulted in an urgent need for effective clinical tools to reduce transmission and manage severe illness. Numerous teams are quickly developing artificial intelligence approaches to these problems, including using deep learning to predict COVID-19 diagnosis and prognosis from chest computed tomography (CT) imaging data. In this work, we assess the value of aggregated chest CT data for COVID-19 prognosis compared to clinical metadata alone. We develop a novel patient-level algorithm to aggregate the chest CT volume into a 2D representation that can be easily integrated with clinical metadata to distinguish COVID-19 pneumonia from chest CT volumes from healthy participants and participants with other viral pneumonia. Furthermore, we present a multitask model for joint segmentation of different classes of pulmonary lesions present in COVID-19 infected lungs that can outperform individual segmentation models for each task. We directly compare this multitask segmentation approach to combining feature-agnostic volumetric CT classification feature maps with clinical metadata for predicting mortality. We show that the combination of features derived from the chest CT volumes improve the AUC performance to 0.80 from the 0.52 obtained by using patients' clinical data alone. These approaches enable the automated extraction of clinically relevant features from chest CT volumes for risk stratification of COVID-19 patients.