TY - JOUR T1 - Coronavirus Disease (COVID-19): A Machine Learning Bibliometric Analysis JF - In Vivo JO - In Vivo SP - 1613 LP - 1617 DO - 10.21873/invivo.11951 VL - 34 IS - 3 suppl AU - FRANCESCA DE FELICE AU - ANTONELLA POLIMENI Y1 - 2020/06/01 UR - http://iv.iiarjournals.org/content/34/3_suppl/1613.abstract N2 - Background/Aim: To evaluate the research trends in coronavirus disease (COVID-19). Materials and Methods: A bibliometric analysis was performed using a machine learning bibliometric methodology. Information regarding publication outputs, countries, institutions, journals, keywords, funding and citation counts was retrieved from Scopus database. Results: A total of 1883 eligible papers were returned. An exponential increase in the COVID-19 publications occurred in the last months. As expected, China produced the majority of articles, followed by the United States of America, the United Kingdom and Italy. There is greater collaboration between highly contributing authors and institutions. The “BMJ” published the highest number of papers (n=129) and “The Lancet” had the most citations (n=1439). The most ubiquitous topic was COVID-19 clinical features. Conclusion: This bibliometric analysis presents the most influential references related to COVID-19 during this time and could be useful to improve understanding and management of COVID-19. ER -