Curious about how medicine works — and what its data can tell us.
Now — first year at King's, teaching myself statistics and R, and turning each project I build into something I write about.
01
A pharmacovigilance disproportionality analysis — PRR, ROR, chi-squared, and Evans criteria — over the full FAERS database via the openFDA API, validated on the known warfarin-haemorrhage signal (PRR ~5) and checked against negative controls.
A live interactive Streamlit dashboard over the FDA Adverse Event Reporting System. Pick any drug and see its top reported reactions, reports per year, and age/sex demographics — with a built-in panel on why these counts measure attention, not harm.
Loaded ~3,000 FAERS reports from the openFDA API into a SQLite database (one row per drug-reaction pair) and queried it with SQL — GROUP BY, WHERE, COUNT(DISTINCT). Key lesson: how sampling choices shape conclusions.
Used Synthea synthetic patient records (CSV) loaded into SQLite to learn the relational structure of EHR data via JOINs and subquery cohorts — including building a hypertension cohort and examining its medications as a real-world-evidence exercise.
A machine-learning model predicting hypertension from Synthea EHR features — logistic regression and random forest, with honest treatment of data leakage, the precision/recall threshold trade-off, and the limits of synthetic-data performance.
02
Happy to talk pharmacovigilance, health data, or finding a way into the field — reach me at belal4606@gmail.com, or on LinkedIn and GitHub.