I led a team to use Selenium to scrape the internet for AMR-related stories around from regions of interest then apply public large language models to extract relevant information from the articles (type of threat, location, number of people affected, antibiotics administered etc.) for storage in a global AMR surveillance spreadsheet

Project Overview

Motivation	Local news has the potential to aid in detection of antimicrobial resistance (AMR) risks, however, articles may be in local languages or be too numerous for humans to read in full
Data	Produced a database on AMR-related reports from Indian news and developed an open source LLM-based web crawler
Client	Public health researchers and policymakers
Status	Complete
Outcome	TBD