Purpose The novel coronavirus 2019 (COVID-19) is widely spreading all over the world, causing mental health problems for most people. The medical staff is also under considerable psychological pressure. This study aimed to review all research carried out on the mental health status of health care workers (HCWs) to bring policymakers and managers’ attention. Methods A literature search conducted through e-databases, including PubMed, EMBASE, Scopus, and Web of Science (WoS) from December 2019 up to April 12th 2020. All cross- sectional studies published in English which assessed the health workers’ psychological well-being during the SARS-CoV-2 pandemic included. Study quality was analyzed using NHLBI Study Quality assessment tools. Results One hundred relevant articles were identified through systematic search; of which eleven studies were eligible for this review. Their quality score was acceptable. The lowest reported prevalence of anxiety, depression, and stress among HCWs was 24.1%, 12.1%, and 29.8%, respectively. In addition, the highest reported values for the aforementioned parameters were 67.55%, 55.89%, and 62.99%, respectively. Nurses, female workers, front-line health care workers, younger medical staff, and workers in areas with higher infection rates reported more severe degrees of all psychological symptoms than other health care workers. Moreover, vicarious traumatization in non-front-line nurses and the general public was higher than that of the front-line nurses. Conclusion During SARS-CoV-2 outbreak, the health care workers face aggravated psychological pressure and even mental illness. It would be recommended to the policymakers and managers to adopt the supportive, encouragement & motivational, protective, and training & educational interventions, especially through information and communication platform.

Anomaly detection (AD) is a challenging problem in computer vision. Particularly in the field of medical imaging, AD poses even more challenges due to a number of reasons, including insufficient availability of ground truth (annotated) data. In recent years, AD models based on generative adversarial networks (GANs) have made significant progress. However, their effectiveness in biomedical imaging remains underexplored. In this paper, we present an overview of using GANs for AD, as well as an investigation of state-of-the-art GAN-based AD methods for biomedical imaging and the challenges encountered in detail. We have also specifically investigated the advantages and limitations of AD methods on medical image datasets, conducting experiments using 3 AD methods on 7 medical imaging datasets from different modalities and organs/tissues. Given the highly different findings achieved across these experiments, we further analyzed the results from both data-centric and model-centric points of view. The results showed that none of the methods had reliable performance for detecting abnormalities in medical images. Factors such as the number of training samples, the subtlety of the anomaly, and the dispersion of the anomaly in the images are among the phenomena that highly impact the performance of the AD models. The obtained results were highly variable (AUC: 0.475-0.991; Sensitivity: 0.17-0.98; Specificity: 0.14-0.97). In addition, we provide recommendations for deployment of AD models in medical imaging and foresee important research directions.

Obtaining data is challenging for researchers, especially when it comes to medical data. Moreover, using medical data as there are concerns about privacy and confidentiality issues requires specific considerations. Generative models aim to learn data distribution via various statistical learning approaches. Among generative models, a machine learning-based approach named Generative Adversarial Networks (GANs) has proved their potential in the implicit density estimation of high dimensional data. Therefore, we suggest an approach that each healthcare organization, especially hospitals, could create and share their own GAN model, entitled Hospital-Based GANs (H-GANs), instead of sharing raw data of patients.

BackgroundEvidence showed that partial or complete loss of smell and taste might be a possible primary symptom of the 2019 novel coronavirus (COVID-19). This study aimed to systematically review and pool all available evidence on the olfactory and gustatory dysfunction in COVID-19 patients. MethodsIn this systematic review, a comprehensive search was carried out systematically through e-databases including PubMed, EMBASE, Scopus, and Web of Science (WoS); that was limited to English-language studies published from 2019 up to 6th May 2020. Afterward, all studies reported the taste and smell dysfunction in the COVID-19 patients were included. The quality of the studies was assessed by the Mixed Methods Appraisal Tool (MMAT). The pooled prevalence of olfactory and gustatory dysfunction was estimated using the random effects meta-analysis method.ResultsAmong 28 eligible included studies in this systematic review, finally, 22 studies met the eligibility criteria and were included in the meta-analysis. According to the random effect meta-analysis, the global pooled prevalence (95% confidence interval) of any olfactory dysfunction, anosmia, and hyposmia was 55% (40%-70%), 40% (22%-57%), and 40% (20%-61%) respectively. The pooled estimated prevalence of any gustatory dysfunction, ageusia, and dysgeusia was 41% (23%-59%), 31% (3%-59%), and 34% (19%-48%) respectively. ConclusionOlfactory and gustatory dysfunction is prevalent among COVID-19 patients. Therefore, olfactory and gustatory dysfunction seems to be part of important symptoms and notify for the diagnosis of COVID-19, especially in the early phase of the infection.