RESUMEN
The new emerging Coronavirus disease (COVID-19) is a pandemic disease due to its enormous infectious capability. Generally affecting the lungs, COVID-19 engenders fever, dry cough, and tiredness. However, some patients may not show symptoms. An imaging test, such as a chest X-ray or a chest CT scan, is therefore requested for reliable detection of this pneumonia type. Despite the decreasing trends both in the new and death reported cases, there is an extent need for quick, accurate, and inexpensive new methods for diagnosis. In this framework, we propose two machine learning (ML) algorithms: linear regression and logistic regression for effective COVID-19 detection in the abdominal Computed Tomography (CT) dataset. The ML methods proposed in this paper, effectively classify the data into COVID-19 and normal classes without recourse to image preprocessing or analysis. The effectiveness of these algorithms was shown through the use of the performance measures: accuracy, precision, recall, and F1-score. The best classification accuracy was obtained as 96% with logistic regression using the saga solver with no added penalty against 95.3% with linear regression. As for precision, recall, and F1-score the value of 0.89 was reached by logistic regression for all these metrics, as well as the value of 0.87 by linear regression. © 2022 IEEE.
RESUMEN
Background: People experiencing homelessness (PEH) are vulnerable to COVID-19 transmission due to substance use, congregate living conditions, and underlying medical conditions. Yet, little is known about factors impacting drug use disorder among PEH during COVID-19 pandemic. The purpose of this study was to identify correlates associated with substance use disorder among PEH, both those who were diagnosed with COVID-19 and those who tested negative or never tested. Methods: A cross-sectional, structured survey was administered to PEH (N = 102) who were recruited from sheltered and unsheltered settings. Descriptive analysis, t-tests, Fisher's exact test or chi-squared test, and bivariate and multiple linear regression were conducted. Results: PEH with a COVID-19 diagnosis included male gender, and Latino race/ethnicity (p <.05). Moreover, substance use disorder scores (p -.037) and days on the street were negatively associated with COVID-19 (p <.001). Multivariable analyses revealed a significant positive relationship between days slept on the street and substance use disorder (p <.001), and a significant negative relationship with alcohol use (p <.05);COVID-19 remained negatively associated with substance use disorder, but it was not significant. Conclusions: This study provides evidence about correlates of drug use disorder among PEH. More studies are needed to understand successful individual and system-level strategies for reducing drug-related problems during COVID-19. © 2023 The Author(s). Published with license by Taylor & Francis Group, LLC.
RESUMEN
Background. Federal mandate requires NHs to perform weekly COVID-19 testing of staff. Testing is effective due to barriers to disclosing mild illness, but it is unclear how long the mandate will last. We explored if environmental samples can be used to signal staff COVID-19 cases as an alternative screening tool in NHs. Methods. We conducted a cross sectional study to assess the value of environmental sampling as a trigger for COVID-19 testing of NH staff using data from currently performed weekly staff sweeps. We performed 35 sampling sweeps across 21 NHs from 6/2020-2/2021. For each sweep, we sampled up to 24 high touch objects in NH breakrooms (N=226), entryways (N=216), and nursing stations (N=194) assuming that positive samples were due to contamination from infected staff. Total staff and positive staff counts were tallied for the staff testing sweeps performed the week of and week prior to environmental sampling. Object samples were processed for SARSCoV-2 using PCR (StepOnePlus) with a 1 copy/mL limit of detection. We evaluated concordance between object and staff positivity using Cohen's kappa and calculated the positive and negative predictive value (PPV, NPV) of environmental sweeps for staff positivity, including the attributable capture of positive staff. We tested the association between the proportion of staff positivity and object contamination by room type in a linear regression model when clustering by NH. Results. Among 35 environmental sweeps, 49% had SARS-CoV-2 positive objects and 69% had positive staff in the same or prior week. Mean positivity was 16% (range 0-83%) among objects and 4% (range 0-22%) among staff. Overall, NPV was 61% and Cohen's kappa was 0.60. PPV of object sampling as an indicator of positive staff was 100% for every room type, with an attributable capture of positive staff of 76%, with values varying by room type (Table). Breakroom samples were the strongest indicator of any staff cases. Each percent increase in object positivity was associated with an increase in staff positivity in entryways (7.2% increased staff positivity, P=0.01) and nursing stations (5.7% increased staff positivity, P=0.05). Conclusion. If mandatory weekly staff testing ends in NHs, environmental sampling may serve as an effective tool to trigger targeted COVID-19 testing sweeps of NH staff.