👨🏻⚕️ Dr. Heal AI - Intelligent Medical Assistant
Revolutionizing Healthcare with Multi-Agent AI
Dr. Heal AI is a production-ready medical consultation system that leverages cutting-edge multi-agent architecture to provide intelligent, personalized health guidance. Built with LangGraph orchestration and powered by Google Gemini 2.0 Flash, this system represents the future of AI-assisted healthcare.
The Problem
Traditional medical chatbots provide generic responses and lack the sophistication to handle complex medical queries. Patients need intelligent systems that can:
- Analyze symptoms with medical precision
- Provide comprehensive disease information
- Recommend evidence-based treatments
- Identify medical emergencies instantly
Our Solution: Multi-Agent Intelligence
Dr. Heal AI employs four specialized AI agents working in perfect coordination:
🔬 SymptomAnalyzerAgent
Analyzes patient symptoms, assesses severity, and identifies potential conditions using advanced pattern recognition and medical knowledge retrieval.
📚 DiseaseExpertAgent
Provides comprehensive disease information based on ICD-10 classifications, including symptoms, risk factors, complications, and prognosis.
💊 TreatmentAdvisorAgent
Recommends evidence-based treatments, medications, lifestyle modifications, and when to seek professional medical care.
🚨 EmergencyTriageAgent
Identifies life-threatening conditions and provides critical emergency protocols, potentially saving lives through immediate guidance.
.png?Expires=1762498631&Key-Pair-Id=K2V2TN6YBJQHTG&Signature=VJmhurUsiikZKIz3xfkxtAqnGwy7T8qqpFR3um7ynoeZqPs~m9aFa8J2qQJlVeXeF6hJZDdd9QfFv2Ta2n42EpU7hy2F27FruP4zrSHPtDkTnXPULvXYPTfKkVkd1ykj38RcKQfe~ns9IucQwkH2m2nBFTBOly5sJPOWlTzM0ERUiN8dpgfWb86sTJ14bbUiZ0oc3ImEtremSTGfA6dCoD09RmACi1up5rQ4wz1WrMDVlCiOJvZhBIjFwpv-UmyxFStqr790oO-rHZs~nYwhelejlV-N-pXL5jdWNpgflgTQppgfLOqYbgd1dSduQixMz6dQATcWZmYhzRR-LvtcIg__)
Technical Architecture
Backend Excellence
- Framework: FastAPI for high-performance API endpoints
- Orchestration: LangGraph for sophisticated agent coordination
- AI Model: Google Gemini 2.0 Flash for advanced language understanding
- Vector Database: ChromaDB with 40+ curated medical documents
- Knowledge Base: RAG system with ICD-10 codes, medications, symptom mappings, and emergency protocols
- Database: PostgreSQL (Supabase) for user data and conversation history
- Security: JWT authentication, bcrypt password hashing, rate limiting (100 req/min)
Frontend Innovation
- Framework: Flutter for beautiful cross-platform mobile experience
- Design: Material Design 3 with intuitive navigation
- State Management: Riverpod for reactive state handling
- Features: Real-time chat, conversation history, agent-specific response badges
Production Deployment
- Containerization: Docker with multi-stage builds
- Hosting: Railway.app with automatic CI/CD
- Monitoring: Health checks and comprehensive logging
- Testing: 70%+ test coverage with pytest
Key Features That Set Us Apart
🤖 Intelligent Agent Coordination
Unlike single-model chatbots, our agents collaborate through shared state management, ensuring comprehensive and contextually aware responses.
📊 Medical Knowledge Base
Our RAG system includes:
- 10 ICD-10 disease categories
- 10 common medications with dosages and interactions
- 10 critical symptom-disease mappings
- 10 life-saving emergency protocols
🔒 Enterprise-Grade Security
- Input validation with Pydantic models
- JWT token authentication
- Rate limiting to prevent abuse
- Comprehensive error handling and logging
⚡ Production-Ready Performance
- Average response time: <2 seconds
- 70%+ test coverage
- Automated deployment pipeline
- Graceful error handling and retry logic
Real-World Impact
Dr. Heal AI bridges the gap between patients and healthcare information, providing:
- 24/7 Availability: Instant medical guidance anytime, anywhere
- Accurate Information: Evidence-based responses backed by medical knowledge
- Emergency Detection: Life-saving identification of critical conditions
- Accessibility: Free, mobile-first healthcare assistance
Technical Highlights
# Multi-agent orchestration with LangGraph class MedicalAgentGraph: def __init__(self): self.symptom_analyzer = SymptomAnalyzerAgent() self.disease_expert = DiseaseExpertAgent() self.treatment_advisor = TreatmentAdvisorAgent() self.emergency_triage = EmergencyTriageAgent() def process_query(self, user_query: str): # Intelligent routing based on query analysis state = AgentState(query=user_query) # RAG retrieval for medical context state.rag_results = self.vector_store.search(user_query) # Agent coordination state = self.symptom_analyzer.process(state) state = self.disease_expert.process(state) state = self.treatment_advisor.process(state) state = self.emergency_triage.process(state) return self.format_response(state)
Compliance & Standards
Module 2: Multi-Agent System ✅
- 4 specialized agents with distinct responsibilities
- LangGraph orchestration framework
- 3+ integrated tools (ChromaDB RAG, DuckDuckGo Search, Gemini LLM)
- Shared state communication protocol
Module 3: Production-Ready ✅
- Comprehensive testing suite (70%+ coverage)
- Security guardrails (JWT auth, rate limiting, input validation)
- Intuitive Flutter mobile UI
- Resilience & monitoring (retry logic, health checks, logging)
- Professional documentation
Project Statistics
- Total Lines of Code: 15,000+
- Backend Modules: 35+ Python files
- Frontend Components: 50+ Dart files
- API Endpoints: 15+
- Medical Documents: 40+ in vector database
- Deployment Time: ~6 minutes
- Test Coverage: 70%+
Getting Started
Try It Now
Download the Android APK from our GitHub Releases
For Developers
# Clone repository git clone https://github.com/BeamlakTamirat/Dr-Heal-Ai.git cd Dr-Heal-Ai # Backend setup cd backend python -m venv venv source venv/bin/activate # Windows: venv\Scripts\activate pip install -r requirements.txt uvicorn app.main:app --reload # Frontend setup cd frontend flutter pub get flutter run
Future Roadmap
- Voice input for symptom description
- Multi-language support for global accessibility
- Medical image analysis capabilities
- Prescription tracking and medication reminders
- Telemedicine integration
- Wearable device integration
- Advanced analytics dashboard
Why Dr. Heal AI Matters
In a world where healthcare access is limited and medical information is often unreliable, Dr. Heal AI provides:
- Democratized Healthcare: Free, intelligent medical guidance for everyone
- Immediate Assistance: No waiting rooms, no appointments needed
- Educational Value: Helps users understand their health conditions
- Emergency Preparedness: Life-saving protocols at your fingertips
Technical Innovation
Dr. Heal AI showcases advanced AI engineering:
- Multi-agent orchestration with LangGraph
- RAG implementation with vector embeddings
- Production deployment with Docker and Railway
- Mobile-first design with Flutter
- Enterprise security with JWT and rate limiting
Open Source & Community
Dr. Heal AI is open source and welcomes contributions. Whether you're a developer, medical professional, or AI enthusiast, join us in revolutionizing healthcare accessibility.
Repository: github.com/BeamlakTamirat/Dr-Heal-Ai
Disclaimer
Dr. Heal AI is an educational and informational tool. It does not replace professional medical advice, diagnosis, or treatment. Always consult qualified healthcare providers for medical concerns.
Built with ❤️ by Beamlak Tamirat
Leveraging AI to make healthcare accessible to everyone, everywhere.
Technologies: FastAPI • LangGraph • Google Gemini • ChromaDB • Flutter • PostgreSQL • Docker • Railway
License: MIT
Dr. Heal AI - Where artificial intelligence meets compassionate care.