Chronic and episodic health conditions—anxiety, IBS, migraines, sleep disorders—don't announce themselves with a single dramatic event. They surface through subtle, scattered signals spread across days and weeks. The problem is that most people aren't tracking those signals, and even when they do, they can't see the patterns. By the time they visit a doctor, they're describing symptoms from memory.
- Project
- AI Nurse
- Year
- 2024
- Type
- AI Health Q&A Agent
- Stack
- Frontend, Backend, AI/ML, Database, Visualization, Localization
- Services used
What was in the way
- 01
Logging symptoms took too much effort
- 02
Symptoms are subtle and intermittent
- 03
No history, so no patterns
- 04
Chatbots couldn't see the user's own data
- 05
Chinese-speaking users needed full localization
How we built it
- 01
Frictionless symptom logging & daily check-ins
- 40+ symptom dimensions
- One-tap severity rating
- Context tags for richer AI input
- 02
AI trend forecasting & cross-risk correlation
- 7-day per-user forecasting
- Health Risk Matrix heatmap
- Automated cross-risk warnings
- 03
Health Q&A agent with tools over personal data
- Tool calls over personal data
- Medical knowledge retrieval
- Full Chinese localization
What changed
Users can now visualize symptom patterns across weeks and months—data they never had access to before
7-day forecasting gives advance warning of likely symptom recurrence periods
Cross-risk correlations surface non-obvious connections between symptom types
Users get answers based on their own logs and forecasts, backed by a curated medical knowledge base
Full Chinese localization delivered—core market served natively