Notes
Writing
Learning in public — building data skills for drug safety, one project at a time.
Subscribe on Substack →Latest
What 1.2 million reports of "drug ineffective" taught me about FAERS
Digging into the most common reaction in FDA adverse-event data and what it actually tells us.
Read on Substack ↗- Coming August 2026Five projects ago, I'd barely written Python How five data projects changed what I can do — and how I think about learning in public.
- Coming August 2026I turned a LinkedIn reply into a signal detector Taking a pharmacovigilance idea from a LinkedIn comment and turning it into a working signal detector.
- Coming August 2026The week my degree and my code agreed with each other The week a pharmacology lecture and a data project pointed at exactly the same finding.
- Coming July 2026The query was never the hard part: learning SQL on drug-safety data What building a SQL database over FAERS data taught me — and why the query was the easy part.
- Coming July 2026I turned my data project into a tool Taking a personal analysis script and building it into a Streamlit tool anyone can use.
- Coming July 2026Most-reported isn't most-dangerous: what the drugs themselves reveal Why the most frequently reported drugs in FAERS aren't the ones with the worst safety signals.