Skip to main content

​
Medical Document Parsing

The Medical Document Parsing API allows you to upload lab report documents (PDF or image formats) and extract structured clinical data from unstructured files. It converts scanned or digital lab reports into machine-readable formats suitable for downstream clinical and analytical workflows. Read more : (API Reference - Medical Document Parsing) section.

​
What It Extracts

Parsed results include:
  • Lab test names
  • Measured values
  • Units of measurement
  • Normal reference ranges
  • Associated clinical metadata
The output is available in:
  • FHIR format
  • Enhanced JSON format

​
Use Cases

  • Digitizing scanned lab reports
  • Enriching patient health records
  • Enabling search and analytics on lab data
  • Powering clinical workflows and decision support systems

​
How It Works

  1. Upload Report
    Upload a scanned lab report (PDF or image).
    You receive a document_id for the uploaded file.
  2. Retrieve Parsed Report
    Use the document_id to fetch structured results in:
    • FHIR format, or
    • Enhanced JSON format
  3. Delete Report
    Remove the uploaded document using its document_id.

​
Key Characteristics

  • Supports both PDF and image-based lab reports
  • Produces structured, machine-readable clinical data
  • Designed for integration into clinical systems and AI workflows
  • Informational extraction only; no clinical interpretation

​
Scope & Limitations

  • Focused on laboratory report parsing
  • Accuracy depends on document quality and scan clarity
  • Parsed data should be clinically verified before use
Read more : (API Reference - Medical Document Parsing) section.