--- title: Medical AI Wiki emoji: 🔬 colorFrom: blue colorTo: purple sdk: docker app_port: 3001 --- # Medical AI Wiki A web application that helps users explore AI algorithms used in medical research papers from PubMed. ## Features - **Dashboard**: View statistics and trends of AI algorithms used in medical papers - **Algorithm Search**: Search for specific medical problems and see which algorithms are most commonly used - **Interactive Charts**: Visual representation of algorithm usage and distribution - **PubMed Integration**: Direct links to relevant papers on PubMed - **Editable Algorithm Database**: JSON-based configuration for easy algorithm management ## Tech Stack - **Frontend**: React + TypeScript + Vite + Tailwind CSS - **Backend**: Node.js + Express - **Charts**: Recharts - **API**: PubMed E-utilities - **Icons**: Lucide React ## Installation 1. Install dependencies for all parts: ```bash npm run install:all ``` 2. Start the development server: ```bash npm run dev ``` This will start both the backend (port 3001) and frontend (port 3000) concurrently. ## Usage 1. **Dashboard**: Visit the homepage to see overall statistics of AI algorithms in medical research 2. **Search**: Use the search page to find algorithms used for specific medical problems 3. **Algorithm Management**: Edit `/data/algorithms.json` to add, remove, or modify algorithms and their synonyms ## Algorithm Configuration The algorithms are configured in `/data/algorithms.json`. Each algorithm has: - `name`: Display name - `category`: Either "classical_ml" or "deep_learning" - `description`: Brief description of the algorithm - `synonyms`: Array of terms used to search PubMed (includes variations, abbreviations, etc.) ## API Endpoints - `GET /api/algorithms` - Get all algorithms - `PUT /api/algorithms` - Update algorithms configuration - `GET /api/search/dashboard-stats` - Get dashboard statistics - `POST /api/search/problem` - Search algorithms for a specific problem - `GET /api/search/pubmed-link` - Generate PubMed search URL - `GET /api/pubmed/search` - Search PubMed papers - `GET /api/pubmed/paper/:pmid` - Get specific paper details ## Development - Backend runs on port 3001 - Frontend runs on port 3000 with proxy to backend - Hot reload enabled for both frontend and backend