A cross-sectional study factors associated with resilience among medical staff in radiology departments during COVID-19, Riyadh, Kingdom of Saudi Arabia.

OBJECTIVES: This study aims to assess the level of resilience of medical workers in radiology departments in Riyadh, Kingdom of Saudi Arabia, during the COVID-19 outbreak and to explore associated factors. SETTING: Medical staff, including nurses, technicians, radiology specialists and physicians, working in radiology departments at government hospitals in Riyadh, Saudi Arabia during the COVID-19 outbreak. DESIGN: A cross-sectional study. PARTICIPANTS: The study was conducted among 375 medical workers in radiology departments in Riyadh, Kingdom of Saudi Arabia. The data collection took place from 15 February 2022 to 31 March 2022. RESULTS: The total resilience score was 29.37±6.760 and the scores of each dimension showed that the higher mean score was observed in the domain of 'flexibility', while the lowest was observed in 'maintaining attention under stress'. Pearson's correlation analysis showed that there was a significant negative correlation between resilience and perceived stress (r=-0.498, p<0.001). Finally, based on multiple linear regression analysis, factors affecting resilience among participants are the availability of psychological hotline (available, B=2.604, p<0.050), knowledge of COVID-19 protective measures (part of understanding, B=-5.283, p<0.001), availability of adequate protective materials (partial shortage, B=-2.237, p<0.050), stress (B=-0.837, p<0.001) and education (postgraduate, B=-1.812, p<0.050). CONCLUSIONS: This study sheds light on the level of resilience and the factors that contribute to resilience in radiology medical staff. Moderate levels of resilience call for health administrators to focus on developing strategies that can effectively help cope with workplace adversities.

Virtual Interviewing for Radiology Residency: Pluses, Minuses, and A Review of the Literature.

This article reviews current medical literature to assess the benefits and drawbacks of virtual interviews for radiology residencies as well as the downstream effects of these changes, best practices, and potential future recruitment methods. Topics covered include the effects of remote recruitment in promoting accessibility and applicant diversity and equality as well as fiscal, environmental, and time savings in combination with technical challenges, the complications of over application, challenges in assessment of program culture and location, impact on morale, and hidden financial and emotional costs. Learnings from other medical specialties are highlighted in addition to the process of signaling, guidelines for conducting and participating in virtual interviews, and matters for future consideration.

Publications on COVID-19 in radiology journals in 2020 and 2021: bibliometric citation and co-citation network analysis.

OBJECTIVES: The pandemic caused by SARS-CoV-2 has led to the rapid publication of numerous radiology articles, primarily focused on disease diagnosis. The objective of this study is to analyze the intellectual structure of radiology research on COVID-19 using a citation and co-citation analysis. METHODS: We identified all documents about COVID-19 published in radiology journals included in the Web of Science in the period 2020-2021, conducting a citation analysis. Then we identified all bibliographic references that were cited by these documents, generating a co-citation matrix that was used to perform a co-citation network. RESULTS: Of the 3418 documents indexed in WoS, 857 were initially "Early Access," 2223 had citations, 393 had more than 20 citations, and 83 had more than 100 citations. The USA had the highest number of publications (32.62%) and China had the highest rate of funded studies (45.38%). The three authors with the most publications were affiliated with Italian institutions, while the five most cited authors were Chinese. A total of 647 publications were co-cited at least 12 times and were published in 206 different journals, with 49% of the documents found in radiology journals. The institutions with the greatest presence among these co-cited articles were Chinese and American. CONCLUSION: This co-citation analysis is the first to focus exclusively on radiology articles on COVID-19. Our study confirms the existence of interrelated thematic clusters with different specific weights. KEY POINTS: • As the pandemic caused by SARS-Cov-2 has led to the rapid publication of numerous radiology studies in a short time period, a bibliometric review based on citation and co-citation analysis has been conducted. • The co-citation analysis supported the identification of key themes in the study of COVID-19 in radiology publications. • Many of the most co-cited articles belong to a heterogeneous group of publications, with authors from countries that are far apart and even from different disciplines.

A proactive learning approach toward building adaptive capacity during COVID-19: A radiology case study.

The COVID-19 pandemic has challenged organizations to adapt under uncertainty and time pressure, with no pre-existing protocols or guidelines available. For organizations to learn to adapt effectively, there is a need to understand the perspectives of the frontline workforce involved in everyday operations. This study implemented a survey-tool to elicit narratives of successful adaptation based on the lived experiences frontline radiology staff at a large multispecialty pediatric hospital. Fifty-eight members of the radiology frontline staff responded to the tool between July and October of 2020. Qualitative analysis of the free-text data revealed five categories of themes that underpinned adaptive capacity of the radiology department during the pandemic: information flow, attitudes and initiative, new and adjusted workflows, availability and utilization of resources, and collaboration and teamwork. Enablers of adaptive capacity included timely and clear communication about procedures and policies from the leadership to frontline staff, and revised workflows with flexible work arrangements, such as remote patient screening. Responses to multiple choice questions in the tool helped identify the main categories of challenges faced by staff, factors that enabled successful adaptation, and resources used. The study demonstrates the use of a survey-tool to proactively identify frontline adaptations. The paper also reports a system-wide intervention resulting directly from a discovery enabled by the findings based on the use of RETIPS in the radiology department. In general, the tool could be used in concert with existing learning mechanisms, such as safety event reporting systems, to inform leadership-level decisions to support adaptive capacity.

Work From Home in Academic Radiology Departments: Advantages, Disadvantages and Strategies for the Future.

To achieve necessary social distancing during the Covid-19 pandemic, working from home was introduced at most if not all academic radiology departments. Although initially thought to be a temporary adaptation, the popularity of working from home among faculty has made it likely that it will remain a component of radiology departments for the long term. This paper will review the potential advantages and disadvantages of working from home for an academic radiology department and suggest strategies to try to preserve the advantages and minimize the disadvantages.

Breast Imaging During a Cyberattack and Global Pandemic: What We Did to Pick Up the Pieces.

Cybersecurity in healthcare is a very real threat with the potential to severely disrupt patient care, place extra burden on an already strained system, and result in significant financial losses for a hospital or healthcare network. In October 2020, on the backdrop of the ongoing COVID-19 pandemic, our institution experienced one of the most significant cyberattacks on a healthcare system to date, lasting for nearly 40 days. By sharing our experience in radiology, and specifically in breast imaging, including the downtime procedures we relied upon and the lessons that we learned emerging from this cyberattack, we hope to help future victims of a healthcare cyberattack successfully weather such an experience.

COVID-19 Contingency Planning Among Radiologic Science Programs.

PURPOSE: To examine radiologic science programs' contingency planning related to the COVID-19 pandemic. METHODS: Using a mixed-methods approach, educators in magnetic resonance, medical dosimetry, radiation therapy, and radiography programs were surveyed to identify curricular changes, policy implementation, and financial implications related to pandemic recovery efforts. Quantitative data were summarized using descriptive statistics and percentages. Thematic analyses were performed on the qualitative responses. RESULTS: Continued curricular changes involved using technology to teach in the online environment and ensuring the safety and protection of students during clinical rotations. Institutional policies implemented because of the pandemic included social distancing guidelines, mask requirements, and availability of vaccine. The greatest financial implication witnessed among the sample of educators at their respective institutions was the halting of employer-related travel. Faced with the spontaneous shift to online learning while not being equipped with the appropriate training, most of the educator participants experienced COVID-19 fatigue and burnout related to teaching online. DISCUSSION: Social distancing guidelines make it difficult for large classes to meet in person, so virtual lectures using video conferencing platforms were an essential part of teaching during the pandemic. Most educators in this study selected recording technology for lectures as the most useful educational technology tool integrated into the didactic portion of their program. For many educators, having administration realize the adoption of technology is integral to and viable for radiologic science programs was a positive outcome of COVID-19. The pandemic caused educators in the study to experience fatigue and burnout related to online learning; however, the educators also expressed a high degree of comfort with using technology in the online learning environment. This implies that the source of fatigue and burnout was likely not associated with the technology, but with the focused and swift transition to predominately online learning. CONCLUSION: Although educators in this sample felt moderately prepared to handle future viral outbreaks and extremely comfortable using technology in the virtual classroom, additional research is needed to develop viable contingency plans and explore pedagogical approaches to content delivery beyond the traditional, in-person structure.

Artificial intelligence for assistance of radiology residents in chest CT evaluation for COVID-19 pneumonia: a comparative diagnostic accuracy study.

BACKGROUND: In hospitals, it is crucial to rule out coronavirus disease 2019 (COVID-19) timely and reliably. Artificial intelligence (AI) provides sufficient accuracy to identify chest computed tomography (CT) scans with signs of COVID-19. PURPOSE: To compare the diagnostic accuracy of radiologists with different levels of experience with and without assistance of AI in CT evaluation for COVID-19 pneumonia and to develop an optimized diagnostic pathway. MATERIAL AND METHODS: The retrospective, single-center, comparative case-control study included 160 consecutive participants who had undergone chest CT scan between March 2020 and May 2021 without or with confirmed diagnosis of COVID-19 pneumonia in a ratio of 1:3. Index tests were chest CT evaluation by five radiological senior residents, five junior residents, and an AI software. Based on the diagnostic accuracy in every group and on comparison of groups, a sequential CT assessment pathway was developed. RESULTS: Areas under receiver operating curves were 0.95 (95% confidence interval [CI]=0.88-0.99), 0.96 (95% CI=0.92-1.0), 0.77 (95% CI=0.68-0.86), and 0.95 (95% CI=0.9-1.0) for junior residents, senior residents, AI, and sequential CT assessment, respectively. Proportions of false negatives were 9%, 3%, 17%, and 2%, respectively. With the developed diagnostic pathway, junior residents evaluated all CT scans with the support of AI. Senior residents were only required as second readers in 26% (41/160) of the CT scans. CONCLUSION: AI can support junior residents with chest CT evaluation for COVID-19 and reduce the workload of senior residents. A review of selected CT scans by senior residents is mandatory.

Medical image captioning via generative pretrained transformers.

The proposed model for automatic clinical image caption generation combines the analysis of radiological scans with structured patient information from the textual records. It uses two language models, the Show-Attend-Tell and the GPT-3, to generate comprehensive and descriptive radiology records. The generated textual summary contains essential information about pathologies found, their location, along with the 2D heatmaps that localize each pathology on the scans. The model has been tested on two medical datasets, the Open-I, MIMIC-CXR, and the general-purpose MS-COCO, and the results measured with natural language assessment metrics demonstrated its efficient applicability to chest X-ray image captioning.

A systematic review on the use of explainability in deep learning systems for computer aided diagnosis in radiology: Limited use of explainable AI?

OBJECTIVES: This study aims to contribute to an understanding of the explainability of computer aided diagnosis studies in radiology that use end-to-end deep learning by providing a quantitative overview of methodological choices and by discussing the implications of these choices for their explainability. METHODS: A systematic review was executed using the preferred reporting items for systemic reviews and meta-analysis guidelines. Primary diagnostic test accuracy studies using end-to-end deep learning for radiology were identified from the period January 1st, 2016, to January 20th, 2021. Results were synthesized by identifying the explanation goals, measures, and explainable AI techniques. RESULTS: This study identified 490 primary diagnostic test accuracy studies using end-to-end deep learning for radiology, of which 179 (37%) used explainable AI. In 147 out of 179 (82%) of studies, explainable AI was used for the goal of model visualization and inspection. Class activation mapping is the most common technique, being used in 117 out of 179 studies (65%). Only 1 study used measures to evaluate the outcome of their explainable AI. CONCLUSIONS: A considerable portion of computer aided diagnosis studies provide a form of explainability of their deep learning models for the purpose of model visualization and inspection. The techniques commonly chosen by these studies (class activation mapping, feature activation mapping and t-distributed stochastic neighbor embedding) have potential limitations. Because researchers generally do not measure the quality of their explanations, we are agnostic about how effective these explanations are at addressing the black box issues of deep learning in radiology.