🛡️ TrustAlert: Health News Classifier & ICD9 Similarity Search
Welcome! 👋
This demo is part of the TrustAlert: Empowering Public Health with Real-Time Insights and Future Preparedness project, where we're exploring how to detect and monitor potential disease outbreaks — just by analyzing news articles from the GDELT database.
AI for early health alerts, powered by natural language processing.
🔍 What This Demo Does
- 📰 News Classification
Enter a news article and the system will predict its societal domains (e.g. health, business, politics) using a sentence transformer model (all-mpnet-base-v2) and similarity matching. - 🧬 ICD9 Code Matching
If the article is about health, we’ll search for the 10 most relevant ICD9 medical codes that match the article — helping link news to clinical terminology.
🔍 How the Pipeline Works
The pipeline begins with the IPTC Annotation System, which classifies news articles into societal domains such as health, business, and politics using an MPNET encoder. Articles classified under the health domain are then processed by the ICD9 Annotation System. This system matches the content of the health-related articles to the most relevant ICD9 medical codes, providing a bridge between news and clinical terminology.
🧪 Try It Yourself
- ✍️ Paste or write a news article in the textbox below, or enter an article URL to fetch and edit the text.
- ⚡ Click the button to classify and (if health-related) get ICD9 code suggestions.
- 📚 Explore examples to see how the system works!
This tool brings together NLP and health informatics to help us stay ahead of disease outbreaks — faster, smarter, and with open data. 💡