Systems · 2025
Biosurveillance “Digital Immune System”
An interactive early-warning dashboard that fuses wastewater viral load, hospital admissions, and air-quality signals into a single biosecurity risk index with tiered alerts.
Role: Founder & Project Lead — Gordian Knot Center for National Security Innovation
Overview
Biological threats often emerge before they're formally detected. Founded and led at Stanford's Gordian Knot Center for National Security Innovation, this “digital immune system” inverts that pattern by detecting weak anomalies early across multiple public-health signals. The interactive dashboard — built in Python with Streamlit — ingests wastewater viral load, hospital admissions, and environmental air-quality data, computes rolling z-scores against recent baselines, and fuses them with adjustable weights into a unified risk score with High/Medium alert tiers. Users can upload their own CSVs or explore predefined outbreak and bioterror scenarios; planned extensions add machine learning and automated data ingestion.
Highlights
- Fused wastewater, hospital-admission, and air-quality streams into a unified risk index using rolling z-scores and adjustable weights.
- Built an interactive Streamlit dashboard with CSV upload, scenario simulation (baseline / outbreak / bioterror), trend and standardized plots, and tiered alerts.
- Standardized heterogeneous signals to surface weak early-warning anomalies before they become obvious.
Tech & topics
- Python
- Streamlit
- Anomaly Detection
- Time-Series
- Data Fusion
- Biosecurity
- Data Visualization