“BCG Vaccine— COVID-19” AI Hackathon

Finding a treatment for COVID-19 will be a long-term and difficult process, and research into new vaccines can take several years. Researchers have suggested that a century old vaccine BCG can cause a boost of the immune system and possibly, this could be the reason for the relatively low COVID-19-attributed death rates in some countries. However, these findings come from ecological study designs, which are fraught with potential sources of bias; thus, further evidence is needed from alternative study designs that can account for these sources of potential bias, such as randomized controlled trials and prospective cohort studies. A number of clinical trials with BCG have started already, but the results will not be available for many months.

The studies of the BCG vaccine relationship to COVID-19 have used data from the BCG World Atlas project, started nearly a decade ago. The Atlas is neither perfect nor complete, but it is the only available database of this kind.

A group of more than 30 volunteers, including scientist, researches, IT specialists and Data Scientists have worked for 2 months to gather BCG vaccine and COVIDd-19 related data in order to organise a hackathon with two main tasks. The first one is to try to augment the BCG Atlas data with the help of Natural Language Processing (NLP) and Text Mining (Question Answering, Machine Reading). The second task is to try to find new insights for BCG — COVID-19 clinical trials.

Some of the volunteers who worked in their spare time in order to organise the initiative are from University of Ottawa / BCG World Atlas; Qatar Computing Research Institute, HBKU; Elsevier and Estafet.

The deadline is July 18, 2020 and more information can be found on https://www.kaggle.com/bcgvaccine/hackathon