Project Themes:
- Outbreak Monitoring and Tracking
Team Name: Waiting for Gadot
Team Lead(s):
- Name: Nicholas Chia
- Affiliation: ANL
- Email: chia@ANL.gov
Suggested Team Members and Roles [4-6 members]
| Name | Affiliation | Role / Expertise |
|---|---|---|
| ???? | ||
Project Summary
Goals and Objectives
- Goal 1: Identify sources and APIs for pulling data by date, i.e., google search statistics, xweets, facebook, google scholar, news, case reports, CDC, WHO
- Goal 2: Define report data expected and reporting format
- Goal 3: Prototype summary and extraction workflow for relevant outbreak data
Approach
- Text extraction, text chunking, figure parsing, tabular data processing, APIs
- Prototype of reporting tool
Data and Resources Required
| Resource Type | Source / Link | Description / Purpose |
|---|---|---|
| Data | Internet (Broad), Social media | Data mining for infection data |
| Tools / Services | APIs to all major data services (might need to set up before hand) | Data mining |
| LLMs / AI Models | FireCrawl, OpenAI, Claude, Gemini | Data extraction and summary |
| Compute / Storage | <1TB for prototype | Store downloaded files and extracted (cleaned) data |
Expected Outcomes / Deliverables
- Prototype of outbreak tracking with outcome
Potential Impact and Next Steps
- Infectious disease research or surveillance: The project is infectious disease surveillance
- AI/ML automation and interpretability: The project is infectious disease surveillance using AI and output in interpretable sentences
- Public health preparedness or education: The project is infectious disease surveillance using AI and output in interpretable sentences with a mind to eventually be good enough for public health preparedness
Technical Support Needed
- API keys (ideally set up before project start)
- Mentor support
Additional Comments
API keys would ideally be set up before project start