A web-based tool for analyzing medical documents to identify adverse events, related medications, and relevant research articles.
- Upload and process PDF documents containing medical information
- Extract key medical entities:
- Medications and drugs
- Symptoms and side effects
- Medical conditions and diseases
- Intelligent text processing with advanced NLP capabilities
- Automatic PubMed article search based on extracted information
- Relevant medical literature discovery
- Direct links to full articles on PubMed
- Smart filtering for case studies and adverse event reports
- Comprehensive case summaries
- Relationship analysis between medications and symptoms
- Key findings highlighting
- Clinical context integration
- Modern, responsive design using Bootstrap 5
- Drag-and-drop file upload
- Real-time processing status indicators
- Clear visualization of results using cards
- Mobile-friendly layout
-
Frontend:
- HTML5
- CSS3 (Bootstrap 5.3.2)
- JavaScript (ES6+)
- Bootstrap Icons
-
APIs:
- Gemini API for text extraction and summarization
- OpenAI API for PubMed search term generation
- PubMed E-utilities for article retrieval
-
Features:
- PDF text extraction and base64 encoding
- Medical entity recognition using LLMs
- Smart PubMed search term generation
- XML parsing for PubMed articles
- Intelligent adverse event analysis
- Real-time processing with status indicators
- Clone the repository
- Configure your API keys:
- Set up Gemini API key
- Set up OpenAI API key
- Open
index.htmlin a modern web browser - Enter your API keys in the configuration panel
- Upload a medical document (PDF format)
- Wait for the three-step analysis to complete:
- Text extraction
- Article search
- Summary generation
- Review the extracted information, related articles, and adverse event analysis
adverse-events/
├── index.html # Main application page
├── script.js # Main application logic
├── api-config.js # API configuration and setup
├── xml-helper.js # XML parsing utilities
├── data/ # Data files
└── npi.docx # NPI guidelines
- Chrome (latest)
- Firefox (latest)
- Safari (latest)
- Edge (latest)
- Fork the repository
- Create a feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
- Google for Gemini API access
- OpenAI for GPT API access
- NCBI for PubMed E-utilities
- Bootstrap team for the UI framework