> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.emtelligent.com/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.emtelligent.com/_mcp/server.

# Overview

Emtelligent's clinical extraction pipelines perform complex data extraction from medical documents. These pipelines orchestrate emtelligent services to perform:

* Document splitting and classification
* Clinical NLP
* Complex data extraction

These pipelines are accessed via API.

## About this Documentation

This documentation serves as a complete guide for integrating with and using the Extract API to extract core clinical information from PDF medical documents.

This documentation is intended for data engineers, and clinical informaticists and data scientists. All users should start in the **Overview** section. Data engineers will want to consult the **Workflow** section of the documentation, whereas data end-users (informaticists and data scientists) may find the **Clinical Extractions** section most useful.

If you have further questions contact emtelligent support at [support@emtelligent.com](mailto:support@emtelligent.com)

> **Note**
>
> This documentation is for the generally available solution. Enterprise customers may have customizations not covered here. However, the information about setup and extraction API remain relevant.