How sakshamgupta2008/team-ares works
PreventiQ is a preventive-health decision-support dashboard: decision-makers explore district/state screening gaps and risk, compare locations, inspect disease trends, and try resource-deployment scenarios. The backend calculates risk and serves geographic and disease data; the Python service loads health data, trains and caches predictions, and exposes ML summaries. The dashboard also offers an Anthropic-powered district chat. README capabilities such as expected-care modeling and multi-month trend filtering are documented, but their implementations are not established by the sampled source. UI-to-backend wiring beyond the documented application workflow is not shown in the excerpts.
Main entry points: server.js HTTP API · Dashboard.jsx Dashboard shell · aiService.js Chat reasoning · AIChatPanel.jsx AI chat panel
Components 15
Decision Dashboard
- Dashboard shell
frontend/src/Dashboard.jsx - District comparison
frontend/src/components/CityComparison.jsx - AI chat panel
frontend/src/components/AIChatPanel.jsx - Chat reasoning
frontend/src/services/aiService.js
Risk Data API
- HTTP API
Backend/server.js - Risk scoring
Backend/risk.js - District coverage data
Backend/data.js - Disease histories
Backend/districtDiseaseData.js - India state data
Backend/indiaStateData.js
Predictive Analytics
- ML service
ML/ml_service.py - Health dataset
final_health_data.xlsx
Intervention Planning
- Deployment simulator
frontend/src/components/InterventionSimulator.jsx - Scenario simulation
frontend/src/utils/simulationData.js
Other components
- Health decision-makers
- Anthropic API
Connections 14
- Health decision-makers → Dashboard shell: use dashboard
- Dashboard shell → District comparison: open comparison
- Dashboard shell → Deployment simulator: open simulator
- Dashboard shell → AI chat panel: open chat
- HTTP API → District coverage data: reads coverage
- HTTP API → Disease histories: reads histories
- HTTP API → India state data: reads state data
- HTTP API → Risk scoring: calculates risk
- HTTP API → ML service: requests ML data
- Health dataset → ML service: loads dataset
- Deployment simulator → Scenario simulation: runs scenario
- AI chat panel → Chat reasoning: requests reasoning
- Chat reasoning → Anthropic API: sends chat context
- Anthropic API → Chat reasoning: returns response