VETERINARY MEDICINE  SAFETY PROJECT

THE PROBLEM
Since 1987, almost 1 million adverse event reports have been collected on Veterinary Drugs and sent to FDA CVM. The safety signal for the data is currently done with a manual process. 

THE SOLUTION
Using AWS, Python and Tableau, I created a machine learning model for the  Center for Veterinary Medicine at the FDA. The goal is to automate the detection of safety signals. 

I started with downloading the data using the OPEN FDA AI and unziing the files using python. 

1. What problem were you trying to solve?
2. Was the problem well defined from the start or did you have to define it more clearly? How did you do that?
3. What difficulties did you encounter in solving the problem and how did you overcome them?
4. How did solving this problem/project change how you think about this type of problem? Does your learning extend to other problems of a similar nature?

RESULTS(Insert screenshots as needed)

1. What problem were you trying to solve?

2. Was the problem well defined from the start or did you have to define it more clearly? How did you do that?

3. What difficulties did you encounter in solving the problem and how did you overcome them?

4. How did solving this problem/project change how you think about this type of problem? Does your learning extend to other problems of a similar nature?

 

PROJECT WEBSITE
For more details, check out the project's website here.

"This project was supported in part by an appointment to the Research Participation Program at the U.S. Food and Drug Administration administered by the Oak Ridge Institute for Science and Education through an interagency agreement between the U.S. Department of Energy and the U.S. Food and Drug Administration."