Drug safety signal detector

The brief

Pharmacovigilance teams look for safety signals: drug and side-effect pairs reported more often than chance would explain. Using public adverse-event reports, calculate disproportionality measures (PRR and ROR) for a set of medicines, rank the strongest signals, and check them against what the label already lists. Good looks like: correct counts and measures with confidence intervals, a ranked signal table, and a sensible comparison with the label.

What you will build

1. Download adverse-event reports for chosen medicines
2. Count drug and reaction pairs and build 2×2 tables
3. Calculate PRR and ROR with confidence intervals
4. Rank signals and remove known label reactions
5. Present new signals for a safety review

Free, open data to build it with

• openFDA adverse event reports (FAERS) ↗ U.S. Food and Drug Administration

Check each dataset's licence before you publish your work. Your mentor gives your team its own version of the brief (data, scope or region), so every team's project is its own.