How it works

About GlobalID

GlobalID is an automated infectious disease surveillance system that collects, processes, and visualises data from official public health authorities around the world.

How the Pipeline Works

1

Data Collection

Automated scrapers fetch monthly disease reports and bulletins from official national health authorities such as the China CDC, WHO, and ECDC.

2

Parsing & Normalisation

Raw HTML, PDF, and API responses are parsed, cleaned, and normalised into a unified schema covering disease name, case counts, deaths, and time period.

3

AI Analysis

A large language model analyses trends, compares data against historical baselines, and generates structured epidemiological reports in both English and Chinese.

4

Visualisation & Publishing

Reports, charts, and statistics are published to this website automatically via a static-site build process, ensuring data is always up to date.

System Architecture

Health Authorities CDC / WHO / ECDC
Scrapers Python / Playwright
Parser + DB PostgreSQL
AI Report Engine LLM Analysis
This Website Astro SSG

Key Features

Real-time Updates

Data is refreshed monthly as new bulletins are published by health authorities.

Multi-country Coverage

Track disease trends across multiple countries with standardised comparison metrics.

Trend Analysis

Interactive charts reveal seasonal patterns and outbreak signals against historical baselines.

AI-generated Reports

Detailed epidemiological summaries are written by a large language model, available in English and Chinese.

Open Data

All underlying data is sourced from official public health authorities and is freely accessible.

Bilingual Interface

The entire site supports both English and Chinese, with a single click to switch language.

Open Source Project

Free & Open Source

GlobalID is fully open source under the MIT licence. The entire pipeline — from data collection and AI analysis to frontend visualisation — is available for inspection, reuse, and contribution.

Author

👨‍🔬

Kangguo Li

Epidemiologist & developer. Building tools that make infectious disease data more accessible and actionable.

Data Sources

China CDC

Monthly notifiable infectious disease reports for China.

www.chinacdc.cn →

World Health Organization (WHO)

Disease outbreak news and global surveillance reports.

www.who.int →

ECDC

European communicable disease surveillance data.

www.ecdc.europa.eu →

Start Exploring

Dive into disease surveillance reports, interactive charts, and AI-powered trend analysis.