COVID-19 Outbreak Drivers

Python XGBoost & SHAP

Demo

Explore how ICU breach risk changes over time, and what’s driving it.

  • Wait for the status pill to show the demo is ready (cold starts can take a moment).
  • Drag the date slider to move through time.
  • Hover or click a state to see its risk score, top drivers, and recent trend.
  • Use the hotspots list to quickly jump to the highest-risk locations.

STAR Summary

  • Cleaned and enriched 50k+ rows from the HHS hospital-capacity time series; added rolling stats, trends, and 1/3/7/14-day lag features.
  • Trained an XGBoost classifier with class-imbalance weighting and a strict time-based train/test split.
  • Used SHAP to highlight the top drivers and embedded an interactive plot in the report.
  • Top driver was the share of ICU beds occupied by COVID patients.
  • Exported daily, per-state risk scores (probability of breaching 90% ICU utilization within 7 days).

Notes

The model is a 7-day state-level ICU breach risk scorer based on HHS hospital-capacity data, not a clinical forecast.

Other Projects