Medical OCR

# System dependencies
brew install tesseract poppler          # macOS
apt-get install tesseract-ocr poppler-utils  # Ubuntu

# Install base package
pip install medical-ocr

# With GPU-accelerated OCR (EasyOCR + OpenCV)
pip install medical-ocr[gpu]

# With Google Cloud Vision fallback
pip install medical-ocr[gcp]

# Set API key for LLM refinement pass
export OPENAI_API_KEY=sk-proj-...

# Process a medical document — extract all fields
medical-ocr report.pdf --all --format json

# Extract specific fields only
medical-ocr report.pdf --fields icd,cpt,medications

# Batch process a directory
medical-ocr ./patient-records/ --all --format json --output ./extracted/

# Run as REST API
medical-ocr --api
# POST /extract  { "file": "path/to/document.pdf" }

{
  "document_type": "treatment_record",
  "icd_codes": ["M54.5", "G89.29"],
  "cpt_codes": ["99213", "97110"],
  "medications": [
    { "name": "Ibuprofen", "dosage": "800mg", "frequency": "TID" }
  ],
  "body_parts": ["lumbar spine", "right shoulder"],
  "work_restrictions": ["no lifting > 10 lbs", "limited standing"],
  "dates": {
    "first_visit": "2025-01-10",
    "last_visit": "2025-03-15"
  }
}