Medical Records NLP Engine - Proof of Concept

Project Description

To analyse and extract in medical record documents and provide feasibility assessment for longer term medical coding automation.

DATA SOURCES & INFORMATION EXTRACTION:

We will focus on the following two data sources

-          Scanned OCRs

-          XML Documents

For both of them, the information to be extracted would be as follows

-          Date of Service (DOS)

-          Medical History

-          Assessmeent

-          Page number from which data was extracted

Currently, we would focus on a single template to extract information.

DELIVERABLES:

The final deliverable would consist of a web interface which allows the user to upload a chart and see the outputs, as above.