Surveillance of device associated infections in intensive care units at a Saudi Arabian Hospital, 2017-2020.

BACKGROUND: Device-associated infections (DAIs) are important components of healthcare associated infection and are associated with increased morbidity and mortality. This study describes DAIs across different intensive care units (ICUs) in a hospital in Saudi Arabia. METHODS: The study was conducted between 2017 and 2020 and followed the definitions of National Healthcare Safety Network (NHSN) for DAIs. The calculated the rates of ventilator-associated events (VAE), catheter-associated urinary tract infections (CAUTI) and central line-associated blood stream infections (CLABSI) followed NHSN definitions. RESULTS: During the study period, there were 82 DAIs in adult ICUs and of these 16 (19.5%) were CLABSI, 26 (31.7%) were CAUTI and 40 (48.7%) were VAE. The overall rates for adult ICUs were 1.6, 1.9, 3.8 per 1000 device-days for CAUTI, CLABSI and VAE, respectively. The device-utilization ratio was 0.5, 0.6, and 0.48 for urinary catheters, central lines, and ventilators, respectively. VAE rates for medical and surgical ICU were about 2.8 times the rate in the coronary care unit and the rates were high in 2020 corresponding with the COVID-19 pandemic. Of the adult ICUS, medical ICU had a CLABSI rate of 2.13/1000 device-days and was about double the rate in surgical and cardiac ICU. For CAUTI, the rates per 1000 device-days were 2.19, 1.73, and 1.65 for medical, surgical, and coronary ICUs, respectively. The rate of CLABSI per 1000 device-days for pediatric and neonatal ICUs were 3.38 and 2.28, respectively. CONCLUSIONS: CAUTI was the most common infections among adult ICUs and medical ICU had higher rates than other adult ICUs. VAE rate was higher in the first year of the COVID-19 pandemic, indicating increased device-use, change in patients characteristics as well as possible change in practices across the ICUs.

The Disproportionate Impact of COVID-19 Pandemic on Healthcare-Associated Infections in Community Hospitals: Need for Expanding the Infectious Disease Workforce.

BACKGROUND: The COVID-19 pandemic had a considerable impact on US healthcare systems, straining hospital resources, staff, and operations. However, a comprehensive assessment of the impact on healthcare associated infections (HAIs) across different hospitals with varying level of infectious disease (ID) physician expertise, resources, and infrastructure is lacking. METHODS: This retrospective longitudinal multi-center cohort study included central-line-associated bloodstream infections (CLABSIs), catheter-associated urinary tract infections (CAUTIs), C. difficile infections (CDIs), and ventilator-associated events (VAEs) from 53 hospitals (academic and community) in Southeastern United States from January 1, 2018 to March 31, 2021. Segmented negative binomial regression generalized estimating equations models estimated changes in monthly incidence rates in the baseline (01/2018 - 02/2020) compared to the pandemic period (03/2020 - 03/2021, further divided into three pandemic phases). RESULTS: CLABSIs and VAEs increased by 24% and 34% respectively during the pandemic period. VAEs increased in all phases of the pandemic, while CLABSIs increased in later phases of the pandemic. CDI trend increased by 4.2% per month in the pandemic period. On stratifying the analysis by hospital characteristics, the impact of the pandemic on healthcare-associated infections was more significant in smaller sized and community hospitals. CAUTIs did not change significantly during the pandemic across all hospital types. CONCLUSIONS: CLABSIs, VAEs, and CDIs increased significantly during the pandemic, especially in smaller community hospitals, most of which lack ID physician expertise. Future efforts should focus on better understanding challenges faced by community hospitals, strengthening infection prevention infrastructure, and expanding the ID workforce, particularly to community hospitals.

An efficient deep neural network framework for COVID-19 lung infection segmentation.

Since the outbreak of Coronavirus Disease 2019 (COVID-19) in 2020, it has significantly affected the global health system. The use of deep learning technology to automatically segment pneumonia lesions from Computed Tomography (CT) images can greatly reduce the workload of physicians and expand traditional diagnostic methods. However, there are still some challenges to tackle the task, including obtaining high-quality annotations and subtle differences between classes. In the present study, a novel deep neural network based on Resnet architecture is proposed to automatically segment infected areas from CT images. To reduce the annotation cost, a Vector Quantized Variational AutoEncoder (VQ-VAE) branch is added to reconstruct the input images for purpose of regularizing the shared decoder and the latent maps of the VQ-VAE are utilized to further improve the feature representation. Moreover, a novel proportions loss is presented for mitigating class imbalance and enhance the generalization ability of the model. In addition, a semi-supervised mechanism based on adversarial learning to the network has been proposed, which can utilize the information of the trusted region in unlabeled images to further regularize the network. Extensive experiments on the COVID-SemiSeg are performed to verify the superiority of the proposed method, and the results are in line with expectations.

Coverage Prediction of Novel Coronavirus Vaccine Based on Deep Learning Time Series Analysis

Since the beginning of 2020, COVID-19 has swept the world, bringing many inconveniences and even threats to human life. Through medical scientists' constant study, the vaccine was finally developed earlier this year. According to mathematical and medical modelling, if novel coronavirus transmission is counted as three (i.e., one patient can infect three), 70% of the vaccinations will be required for protection to be substantially achieved. To tackle the issue of vaccine coverage prediction, this paper proposed three-time series analysis models, which can be utilized to analyze and predict the COVID-19 Vaccine coverage worldwide with the application of machine learning. For a long time, statistical methods have mostly solved time series prediction problems (AR, AM, ARMA, ARIMA). Mathematicians try to constantly refine these techniques to constrain stationary and non-stationary time series, but the results are often not very good. In this paper, we propose a method based on deep learning, using CNN-LSTM, VAE-LSTM, DeepAR, and other models to analyze and predict the data of vaccine coverage rate. The experimental results demonstrated that the RMSE of LSTM, CNN-LSTM, VAE-LSTM and DeepAR are 9.295522e+07, 1.028151e+07, 1.857031e+06 and 1.961001e+07 separately. © 2021 IEEE.

Time series forecasting of new cases and new deaths rate for COVID-19 using deep learning methods.

The first known case of Coronavirus disease 2019 (COVID-19) was identified in December 2019. It has spread worldwide, leading to an ongoing pandemic, imposed restrictions and costs to many countries. Predicting the number of new cases and deaths during this period can be a useful step in predicting the costs and facilities required in the future. The purpose of this study is to predict new cases and deaths rate one, three and seven-day ahead during the next 100 days. The motivation for predicting every n days (instead of just every day) is the investigation of the possibility of computational cost reduction and still achieving reasonable performance. Such a scenario may be encountered in real-time forecasting of time series. Six different deep learning methods are examined on the data adopted from the WHO website. Three methods are LSTM, Convolutional LSTM, and GRU. The bidirectional extension is then considered for each method to forecast the rate of new cases and new deaths in Australia and Iran countries. This study is novel as it carries out a comprehensive evaluation of the aforementioned three deep learning methods and their bidirectional extensions to perform prediction on COVID-19 new cases and new death rate time series. To the best of our knowledge, this is the first time that Bi-GRU and Bi-Conv-LSTM models are used for prediction on COVID-19 new cases and new deaths time series. The evaluation of the methods is presented in the form of graphs and Friedman statistical test. The results show that the bidirectional models have lower errors than other models. A several error evaluation metrics are presented to compare all models, and finally, the superiority of bidirectional methods is determined. This research could be useful for organisations working against COVID-19 and determining their long-term plans.