Purpose: To develop a deep learning model that predicts active inflammation from sacroiliac joint radiographs and to compare the success with radiologists. Materials and Methods: A total of 1,537 (augmented 1752) grade 0 SIJs of 768 patients were retrospectively analyzed. Gold-standard MRI exams showed active inflammation in 330 joints according to ASAS criteria. A convolutional neural network model (JointNET) was developed to detect MRI-based active inflammation labels solely based on radiographs. Two radiologists blindly evaluated the radiographs for comparison. Python, PyTorch, and SPSS were used for analyses. P<0.05 was considered statistically significant. Results: JointNET differentiated active inflammation from radiographs with a mean AUROC of 89.2 (95% CI:86.8%, 91.7%). The sensitivity was 69.0% (95% CI:65.3%, 72.7%) and specificity 90.4% (95% CI:87.8 % 92.9%). The mean accuracy was 90.2% (95% CI: 87.6%, 92.8%). The positive predictive value was 74.6% (95% CI: 72.5%, 76.7%) and negative predictive value was 87.9% (95% CI: 85.4%, 90.5%) when prevalence was considered 1%. Statistical analyses showed a significant difference between active inflammation and healthy groups (p<0.05). Radiologists accuracies were less than 65% to discriminate active inflammation from sacroiliac joint radiographs. Conclusion: JointNET successfully predicts active inflammation from sacroiliac joint radiographs, with superior performance to human observers.
5 April 2021 in Canadian Journal of Neurological Sciences / Journal Canadien des Sciences Neurologiques
Objective To explore the prevalence and contributing factors of resident burnout in a University Hospital before and during the COVID 19 pandemic. Methods Thirty Faculty of Medicine departments were included in the survey, where 400 university hospital residents filled out the Maslach Burnout Inventory (MBI) in January 2018 and April 2020. Related scores of emotional exhaustion (EE), decreased accomplishment (DA) and depersonalization (DP) were calculated and compared between the different groups. Correlation between scores and possible contributing factors, including demographics, work-life circumstances, exposure to workplace violence, were investigated. Contributing factors were compared between the time points. Results The EE and DA scores were significantly higher in junior residents than in senior residents. Both scores were higher among residents who had experienced abuse or violence. The emergency medicine residents had significantly higher DP scores, while the EE scores of radiology residents were lower than others. Thirty percent of all residents smoked cigarettes. This percentage was even higher among the residents of the departments of surgery and emergency medicine (45-50%). A significant correlation was demonstrated between the scores of MBI and smoking, while analysis with other demographics did not yield any relation. According to the study results, basic science residents had significantly increased scores in all MBI subgroups during the pandemic. Conclusion Resident physician burnout was found to be related to the work environment, smoking cigarettes and exposure to violence at workplace.
Introduction: Taking into account radiology trainees will lead development and progress of the field in following years, the main purpose of our work was to understand barriers towards academic activity within this group. As secondary goal in this work, we investigated factors influencing neuroradiology subspecialty selection. Methods: A 35-question survey was distributed worldwide