Back

A Public Health Hackathon For Medical Students In Africa: Process, Outcome And Recommendations

Babatunde, A. O.; Brimmo, F. O.; Arama, U. O.; Onyinyechi, M. G.; Josephat, K. A.; Osiene, A. O.

2023-01-31 public and global health
10.1101/2023.01.28.23284802 medRxiv
Show abstract

Africa has a dual burden of disease, which causes preventable morbidities and fatalities. This is a result of our healthcare systems deficiencies, which has suffered a serious decline since the COVID-19 pandemic. However, this opened up the possibilities for digital health interventions, which innovators could utilize to provide solutions to these public health issues. Health hackathons, which offer an environment for innovators to brainstorm and collaborate, are rare in Africa. This paper outlines the planning and execution of a virtual hackathon and explores its implications for the promotion of public health in Africa. Over the course of a month, we collaborated with innovation hubs in Africa to hold an open call, a training session, a design sprint, as well as a 48-hour virtual hackathon. We received 68 submissions from 13 African nations. Following the selection of 10 teams, design thinking was employed to develop solutions to a public health problem in Africa. The theme for the hackathon was Promoting Health Equity with Digital Technology in Africa and areas of focus were non-communicable diseases; infectious disease epidemiology and surveillance; and health information and data management. All ten teams developed prototypes, the top three teams were offered the opportunity to continue on to the start-up accelerator program, while the winning team also received a cash prize. In conclusion, the public health hackathon challenged African medical students to develop innovations for healthcare problems. There is a need for further study to evaluate the solutions developed.

Matching journals

The top 3 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.