Improving classification of low-resource COVID-19 literature by using Named Entity Recognition.

Automatic document classification for highly interrelated classes is a demanding task that becomes more challenging when there is little labeled data for training. Such is the case of the coronavirus disease 2019 (COVID-19) Clinical repository-a repository of classified and translated academic articles related to COVID-19 and relevant to the clinical practice-where a 3-way classification scheme is being applied to COVID-19 literature. During the 7th Biomedical Linked Annotation Hackathon (BLAH7) hackathon, we performed experiments to explore the use of named-entity-recognition (NER) to improve the classification. We processed the literature with OntoGene's Biomedical Entity Recogniser (OGER) and used the resulting identified Named Entities (NE) and their links to major biological databases as extra input features for the classifier. We compared the results with a baseline model without the OGER extracted features. In these proof-of-concept experiments, we observed a clear gain on COVID-19 literature classification. In particular, NE's origin was useful to classify document types and NE's type for clinical specialties. Due to the limitations of the small dataset, we can only conclude that our results suggests that NER would benefit this classification task. In order to accurately estimate this benefit, further experiments with a larger dataset would be needed.

Italian Survey for the Evaluation of the Effects of Coronavirus Disease 2019 (COVID-19) Pandemic on Alopecia Areata Recurrence.

INTRODUCTION: The inflammation storm involved in coronavirus disease 2019 (COVID-19) infection and worsening and the psychological stress derived from current quarantine conditions can affect the course of many skin and scalp conditions. This study examined the possible effects of COVID-19 on alopecia areata (AA) relapse in patients suffering from these scalp conditions during the pandemic. METHODS: The study was carried out in the form of an observational cross-sectional type using a questionnaire sent by mail to a cohort of patients affected by AA during the pandemic from March 2020 to October 2020. RESULTS: During the pandemic, AA relapse was reported in 42.5% of the participants who also declared COVID-19 infection, confirmed by nasopharyngeal swab or hematological analysis. The relapse was reported about 2 months later COVID-19 infection (median of 2.14 months) and 74.0% of these participants continue to experience AA symptoms when the survey was proposed. Only 12.5% of participants reported AA relapse in the absence of COVID-19 infection. CONCLUSIONS: The present study reported a significant relapse in patients suffering from AA and infected by COVID-19. This phenomenon could be attributed to the inflammation storm typical of COVID-19 infection and the psychological stress derived from quarantine conditions.