Enhancing thoracic disease detection using chest X-rays from PubMed Central Open Access.

Large chest X-rays (CXR) datasets have been collected to train deep learning models to detect thorax pathology on CXR. However, most CXR datasets are from single-center studies and the collected pathologies are often imbalanced. The aim of this study was to automatically construct a public, weakly-labeled CXR database from articles in PubMed Central Open Access (PMC-OA) and to assess model performance on CXR pathology classification by using this database as additional training data. Our framework includes text extraction, CXR pathology verification, subfigure separation, and image modality classification. We have extensively validated the utility of the automatically generated image database on thoracic disease detection tasks, including Hernia, Lung Lesion, Pneumonia, and pneumothorax. We pick these diseases due to their historically poor performance in existing datasets: the NIH-CXR dataset (112,120 CXR) and the MIMIC-CXR dataset (243,324 CXR). We find that classifiers fine-tuned with additional PMC-CXR extracted by the proposed framework consistently and significantly achieved better performance than those without (e.g., Hernia: 0.9335 vs 0.9154; Lung Lesion: 0.7394 vs. 0.7207; Pneumonia: 0.7074 vs. 0.6709; Pneumothorax 0.8185 vs. 0.7517, all in AUC with p< 0.0001) for CXR pathology detection. In contrast to previous approaches that manually submit the medical images to the repository, our framework can automatically collect figures and their accompanied figure legends. Compared to previous studies, the proposed framework improved subfigure segmentation and incorporates our advanced self-developed NLP technique for CXR pathology verification. We hope it complements existing resources and improves our ability to make biomedical image data findable, accessible, interoperable, and reusable.

Hyperferritinemia and the Extent of Mucormycosis in COVID-19 Patients.

Introduction Coronavirus disease 2019 (COVID-19) disease attributed to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) has shown associations with various fungal opportunistic infections such as mucormycosis, invasive candidiasis, and aspergillosis, which have contributed to the mortality of the disease. In India, the incidence of mucormycosis had risen rapidly during the second wave. There is ample literature demonstrating the role of iron in the pathogenesis of mucormycosis. The hyperferritinemia associated with COVID-19 may have played a significant role in promoting the invasion and extent of the fungus. Aims and objectives The study aimed to analyze the association between serum ferritin levels and the extent of involvement of mucormycosis in patients affected with COVID-19. Methodology A single-center cross-sectional study was conducted using retrospective hospital record data. G*Power statistical analysis software was used to compute the sample size of 62 (31+31). The radiological data were used to determine the extent of involvement. Results A statistically significant difference was seen in levels of serum ferritin (p = 0.008) between the radiologically judged two groups of the mild extent of invasion of mucormycosis (rhinosinusitis) and severe extent of invasion (rhino-orbital/cerebral mucormycosis), with a severe extent seen with the group having higher levels of serum ferritin. Severe extent of invasion was seen in 53.6% of patients with diabetes mellitus and 62.5% of patients with both diabetes and hypertension. Conclusion The hyperferritinemia not only presents as a marker of the systemic inflammatory process in COVID-19 but also indicates increased free iron, which thereby aids the growth and extent of involvement by the fungus (R hizopus oryzae). In individuals with diabetes and hypertension, the severity was greater. Controlling catastrophic outcomes in individuals with high serum ferritin levels necessitates extra caution.

EFFECT OF WORK FROM HOME ON WORKPLACE ROMANCE: A SOCIO-ECONOMIC PERSPECTIVE

There has been a lot of research work on Covid, but hardly any on impact of work from home (WfH) on workplace romance (WR). WR in organizations has been a controversial and debatable topic since early days. From the literature it was visible that researchers tried to analyze the impact of WR on organizational settings. In India the relationship is considered to be a forbidden taboo, especially in academic sector, where teachers are compared to the divine trinity - Brahma, Vishnu and Maheswar. But, with growing westernization and mushrooming of professional institutions with long working hours, the forbidden relationship was booming. Our study was carried out to examine the antecedents and consequences of workplace romance on various socio-economic variables, in Odisha before, during and post WfH scenario. A set of standard questionnaire on antecedents and consequences of WR was circulated. Data was collected from 230 samples consisting of 103 female and 127 male respondents from academic sector of Odisha. Descriptive statistics were used for analysis of the data. The results of the study revealed that individuals got involved in workplace romance because of job insecurity (mostly in private institutes). Long working hour and outdoor activities promoted it. In the second phase that is during work from home same respondents were asked to predict whether work from home increases or decreases workplace romance. To which their reply was that it may reduce the workplace response. In the third and final phase i.e. post work from home the academicians (samples) were asked about the existing situation of Workplace romance. It was found out that employees continued to be engaged in workplace romance after work from home, as workplace romance was not only because of long working hours but also for their own life preferences. There was no positive relationship between workplace romance and efficiency/productivity, as many institutes were not able to capitalize on the relationship.