🏥 AI Health Navigator

A mobile-first web application that helps U.S. consumers find affordable healthcare options by analyzing symptoms with AI, estimating costs based on insurance coverage, and recommending nearby providers using real-time location data.

✨ Features

🤖 AI-Powered Symptom Analysis

• GPT-5 Integration: Advanced symptom analysis using OpenAI's latest model
• Intelligent Triage: Automatic urgency assessment (Low, Moderate, High, Emergency)
• Conversational Interface: Friendly AI avatar guides users through the process
• Quick-Start Prompts: Example symptom buttons for easy onboarding

💰 Cost Transparency

• Insurance-Based Estimates: Personalized cost estimates for 15+ insurance types
• Multiple Care Options: Compare costs across telehealth, urgent care, and primary care
• Money-Saving Tips: Actionable insurance advice based on your specific plan

📍 Real Provider Search

• Google Places Integration: Real-time search for nearby healthcare facilities
• Smart Filtering: Provider recommendations based on symptom urgency
• Accurate Distances: Geocoded ZIP codes for precise proximity calculations
• Comprehensive Data: Facility names, addresses, ratings, and contact information

📚 Educational Resources (Original Feature)

• Curated Medical Content: Links to trusted sources (Mayo Clinic, CDC, MedlinePlus, Harvard Health, NIH)
• AI Topic Identification: Automatically identifies relevant medical topics from symptoms
• Smart Matching Algorithm: Maps symptoms to appropriate educational articles
• Up to 4 Resources: Most relevant articles displayed per analysis

🔒 Privacy-First Architecture

• Completely Anonymous: No user accounts, no authentication, no tracking
• Stateless Design: No persistent storage of symptom data
• HIPAA Compliance Strategy: Intentionally avoids creating Protected Health Information (PHI)
• Transparent Data Usage: Clear disclosure of third-party data sharing (OpenAI, Google Places)

♿ Accessibility & UX

• Mobile-First Design: Optimized for smartphones and tablets
• WCAG AA Compliance: High contrast ratios and screen reader support
• Touch-Friendly: Minimum 44px touch targets
• Progressive Disclosure: Multi-step form reduces cognitive load

🚀 Tech Stack

Frontend

• React 18 - Modern component-based UI
• TypeScript - End-to-end type safety
• Vite - Lightning-fast build tool
• Tailwind CSS - Utility-first styling
• Shadcn/ui - Accessible component library
• TanStack Query - Server state management
• Wouter - Lightweight routing

Backend

• Node.js + Express - REST API server
• OpenAI GPT-5 - Symptom analysis AI
• Google Places API - Real provider search
• PostgreSQL - Ready for non-PHI features
• Drizzle ORM - Type-safe database queries

DevOps

• Replit - Deployment platform
• ESBuild - Production bundling
• Zod - Runtime type validation

📋 Prerequisites

• Node.js 20 or higher
• OpenAI API access (via Replit AI Integrations)
• Google Places API key
• PostgreSQL database (optional)

🛠️ Installation

1. Clone the repository

   git clone https://github.com/yourusername/ai-health-navigator.git
   cd ai-health-navigator

2. Install dependencies

   npm install

3. Set up environment variables

   Create a .env file or configure Replit Secrets:

   GOOGLE_PLACES_API_KEY=your_google_places_api_key
   SESSION_SECRET=your_session_secret
   DATABASE_URL=your_postgresql_connection_string (optional)

4. Start the development server

   npm run dev

5. Open your browser

   Navigate to http://localhost:5000

💻 Usage

Basic Workflow

1. Describe Your Symptoms

   • Use the conversational interface to describe what you're experiencing
   • Click example prompts for quick start (headache, chest pain, fever, etc.)

2. Provide Location

   • Enter your 5-digit ZIP code for local provider search

3. Select Insurance

   • Choose from 15+ common U.S. insurance types
   • Includes Medicare, Medicaid, major private insurers, and self-pay

4. Review Analysis

   • See AI-powered urgency assessment
   • Compare estimated costs across care types
   • Find nearby providers with directions
   • Read educational articles from trusted medical sources

5. Take Action

   • Contact recommended providers
   • Learn more from educational resources
   • Start a new analysis anytime

🏗️ Architecture

Data Flow

User Input (Symptoms, ZIP, Insurance)
          ↓
  React Frontend (Validation)
          ↓
  Express API (/api/analyze-symptoms)
          ↓
    ┌─────────────────────┐
    ↓                     ↓
OpenAI GPT-5        Google Places API
(Symptom Analysis)  (Provider Search)
    ↓                     ↓
    └─────────────────────┘
          ↓
  Educational Resource Matching
          ↓
  JSON Response to Frontend
          ↓
  Results Display with Resources

Key Design Decisions

• Stateless Architecture: No database storage of symptoms to avoid HIPAA compliance requirements
• AI-First Approach: GPT-5 handles complex medical triage logic
• Curated Resources: Custom matching algorithm for educational content
• Progressive Enhancement: Works on all devices, optimized for mobile

📊 API Reference

POST /api/analyze-symptoms

Analyzes user symptoms and returns care recommendations.

Request Body:

{
  symptoms: string;      // Min 10 characters
  zipCode: string;       // 5-digit ZIP code
  insuranceType: string; // One of 15+ insurance types
}

Response:

{
  id: string;
  conditionSummary: string;
  urgencyLevel: "Low" | "Moderate" | "High" | "Emergency";
  recommendedCareType: string;
  affordableOptions: Provider[];
  estimatedCosts: {
    telehealth: string;
    urgentCare: string;
    primaryCare?: string;
  };
  insuranceTip: string;
  safetyNotice: string;
  educationalResources?: EducationalResource[];
  createdAt: string;
}

🧪 Testing

The application includes comprehensive end-to-end tests using Playwright:

# Run tests
npm run test

# Run tests in headed mode
npm run test:headed

Test coverage includes:

• Multi-step form navigation
• AI analysis flow
• Educational resources display
• Mobile responsiveness
• Accessibility features

🤝 Contributing

Contributions are welcome! Please follow these guidelines:

1. Fork the repository
2. Create a feature branch (git checkout -b feature/amazing-feature)
3. Commit your changes (git commit -m 'Add amazing feature')
4. Push to the branch (git push origin feature/amazing-feature)
5. Open a Pull Request

Code Style

• TypeScript for all new code
• Follow existing patterns and conventions
• Add tests for new features
• Update documentation as needed

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

⚠️ Disclaimer

This application is for informational and educational purposes only.

• NOT a substitute for professional medical advice, diagnosis, or treatment
• NOT a medical service or HIPAA-covered entity
• Does not store or process identifiable health information
• Always consult qualified healthcare professionals for medical concerns
• Call 911 immediately for medical emergencies

🙏 Acknowledgments

Medical Resources

• Mayo Clinic - Evidence-based medical information
• MedlinePlus (NIH) - Trusted health information
• Harvard Health - Expert medical analysis
• CDC - Public health guidance
• NIMH - Mental health resources

Technologies

• OpenAI - GPT-5 language model
• Google Places API - Location services
• Replit - Development and deployment platform
• Shadcn/ui - Component library

Community

• Built with ❤️ for improving healthcare accessibility
• Inspired by the need for transparent healthcare pricing
• Dedicated to helping uninsured and underinsured Americans

📧 Contact

For questions, feedback, or issues, please open a GitHub issue or contact the maintainers.

---

Made with 💙 to help people find affordable healthcare