Context: Cases API lacked demographic breakdowns and per-diagnosis
monthly seasonality data for epidemiological analysis.
Approach:
- Two new GET endpoints with typed Pydantic response models
- Demographics uses get_inpatient_data() (outpatient lacks gender/age)
- Disease-seasonality uses get_combined_data() grouped by diagnosis+month
- pandas groupby/value_counts for vectorized aggregation
Changes:
- Models: AgeBin, GenderSplit, GenderSplitData,
AgeDiagnosisMatrixItem, DemographicsResponse
- Models: DiseaseSeasonalityPoint, DiseaseSeasonalityResponse
- GET /api/cases/demographics: age distribution (0-17), gender split,
age-diagnosis matrix (5 age groups)
- GET /api/cases/disease-seasonality: top 10 diagnoses by month
(120 entries with 1月-12月 labels)
Impact: Enables frontend demographic charts and disease seasonality
heatmaps. All 42 existing API tests continue passing.
Context: Build a spatial risk assessment system correlating air quality
data with children's respiratory disease incidence across Wuhan.
Approach: FastAPI backend serving PostGIS spatial queries, React
frontend with Deck.gl maps, and a PyTorch SpatialTemporalGCN pipeline
for multi-day (1d/3d/7d) risk prediction.
Changes:
- backend/ — FastAPI API with auth (JWT), alerts, risk analysis,
geocoded case data, grid statistics, and report endpoints
- frontend/ — React dashboard with interactive risk maps, alert
monitoring, district comparison charts, and timeline player
- models/ — SpatialTemporalGCN model with trained weights and ONNX
export for inference
- scripts/ — ETL pipeline for weather + medical data, grid generation,
feature engineering, training, and daily inference
- deploy/ — Docker Compose configs for backend, frontend, and MLflow
- docs/ — API docs, deployment guide, user guide, and code review
Impact: Enables spatial risk visualization, alert monitoring, and
ML-driven health risk forecasting for environmental health teams.
