Consensus study of risk factors and symptoms of SARS-CoV-2 (COVID-19) using biomedical literature and social media data

Jeon, J.; Baruah, G.; Sarabadani, S.; Palanica, A.

Background In December 2019, Coronavirus disease 2019 (COVID-19) outbreak started in China and rapidly spread around the world. Lack of any vaccine or optimized intervention raised the importance of characterizing risk factors and symptoms for the early identification and successful treatment of COVID-19 patients. Methods We systematically integrated and analyzed published biomedical literature and public social media data to expand our landscape of clinical and demographic variables of COVID-19. Through semantic analysis, 45 retrospective cohort studies, which evaluated 303 clinical and demographic variables across 13 different outcomes of COVID-19, and 84,140 tweet posts from 1,036 COVID-19 positive users were collected. In total, 59 symptoms were identified across both datasets. Findings Approximately 90% of clinical and demographic variables showed inconsistency across outcomes of COVID-19. From the consensus analysis, we identified clinical and demographic variables that were specific for individual outcomes of COVID-19. Also, 25 novel symptoms that have been not previously well characterized, but were mentioned in social media. Furthermore, we observed that there were certain combinations of symptoms that were frequently mentioned together among COVID-19 patients. Interpretation Identified outcome-specific clinical and demographic variables, symptoms, and combinations of symptoms may serve as surrogate indicators to identify COVID-19 patients and predict their clinical outcomes providing appropriate treatments.