Predictive Analytics for AMR Stewardship

The aim of this project is for the presentation of machine learning for antimicrobial resistance stewardship to the public and policy makers in a way the public and policy members can readily understand.

Winston Grace

Antimicrobial resistance (AMR) affects a range of industries, ranging from medicine to agricultures. AMR solutions can save lives.

There is need to forecast the effects of antibiotics in terms of possible future AMR resistance outcomes. However, a great deal of the machine learning results on bacterial infections, AMR, and AMR stewardship can be challenging for an entire community to understand. 

Primarily, the solution would serve rural, agrarian communities.

It directly informs the public about the issue.

It can create a tangible benefits for local medical communities, public education, as well as for informed policy makers.

The online would scale up over the next year to three years if the project is successful.

The metric would be questions at the end of the online course to assess understanding.

The main barrier would be reaching students in areas affected by AMR issues. The goal is to overcome this barrier by providing the courses in different languages.

I am applying to this challenge because the solution could help a lot of people. Solutions for the issue of microbial resistance can save lives. The barrier is getting this solution to as many people who deal with this issue as possible.