Search

Handcrafted and deep learning (DL) radiomics are popular techniques used to develop computed tomography (CT) imaging-based artificial intelligence models for COVID-19 research. However, contrast heterogeneity from real-world datasets may impair model performance. Contrast-homogenous datasets present a potential solution. We developed a 3D patch-based cycle-consistent generative adversarial network (cycle-GAN) to synthesize non-contrast images from contrast CTs, as a data homogenization tool. We used a multi-centre dataset of 2078 scans from 1,650 patients with COVID-19. Few studies have previously evaluated GAN-generated images with handcrafted radiomics, DL and human assessment tasks. We evaluated the performance of our cycle-GAN with these three approaches. In a modified Turing-test, human experts identified synthetic vs acquired images, with a false positive rate of 67% and Fleiss' Kappa 0.06, attesting to the photorealism of the synthetic images. However, on testing performance of machine learning classifiers with radiomic features, performance decreased with use of synthetic images. Marked percentage difference was noted in feature values between pre- and post-GAN non-contrast images. With DL classification, deterioration in performance was observed with synthetic images. Our results show that whilst GANs can produce images sufficient to pass human assessment, caution is advised before GAN-synthesized images are used in medical imaging applications., (© 2023. The Author(s).)

Background: The outbreak of coronavirus disease 2019 (COVID-19) dates back to December 2019 in China. Iran has been among the most prone countries to the virus. The aim of this study was to report demographics, clinical data, and their association with death and CFR., Methods: This observational cohort study was performed from 20th March 2020 to 18th March 2021 in three tertiary educational hospitals in Tehran, Iran. All patients were admitted based on the WHO, CDC, and Iran's National Guidelines. Their information was recorded in their medical files. Multivariable analysis was performed to assess demographics, clinical profile, outcomes of disease, and finding the predictors of death due to COVID-19., Results: Of all 5318 participants, the median age was 60.0 years, and 57.2% of patients were male. The most significant comorbidities were hypertension and diabetes mellitus. Cough, dyspnea, and fever were the most dominant symptoms. Results showed that ICU admission, elderly age, decreased consciousness, low BMI, HTN, IHD, CVA, dialysis, intubation, Alzheimer disease, blood injection, injection of platelets or FFP, and high number of comorbidities were associated with a higher risk of death related to COVID-19. The trend of CFR was increasing (WPC: 1.86) during weeks 25 to 51., Conclusions: Accurate detection of predictors of poor outcomes helps healthcare providers in stratifying patients, based on their risk factors and healthcare requirements to improve their survival chance., Competing Interests: The authors declare that they have no conflicts of interest., (Copyright © 2022 Hamidreza Hatamabadi et al.)

Objective: The coronavirus disease 2019 (COVID-19) outbreak is the most threatening public health challenge in the 21th century, and more than 200 countries are affected. Considering that Iran was one of the first countries influenced by the COVID-19 pandemic, this study aimed to explain the crisis management strategies during the COVID-19 pandemic in Ardabil province., Methods: This study used a qualitative method using content analysis in which 12 health-care managers or decision-makers involved in the management of the COVID-19 crisis were recruited through purposeful sampling. In-depth, semi-structured interviews were used to collect data, which continued until data saturation., Results: Data analysis led to nine categories, including prior preparation for the COVID-19 crisis; challenges and management of workforce shortages; benefiting from the participation of volunteer staff; challenges and strategies for physical space, supplies, and personal protective equipment (PPE); designation of referral centers for COVID-19; protocolized patient transport; benefiting from donations and charity support; management of information about COVID-19; and learning from the prior stages of crisis., Conclusion: This study revealed that, in critical situations, managers use multiple and, to some extent, unique strategies for decision-making and crisis control. Therefore, the health system can use the findings of the current study for proper response to similar crises and training of future managers.