Project Info
- Industry Healthcare
- Location United States
- Date 11 June 2021
- Size 200-500
Project Info
About This Project
Customer is a leading healthcare solutions provider located in Texas, USA. Customer has decades of healthcare operations experience and specializes in empowering healthcare professionals in their roles.
Executive Summary
Implement Amazon Textract an AWS service to automatically extract text and data from tens of thousands of medical study results stored in PDF files. Build an OCR solution that is customizable and flexible to meet FDA regulations.
Challenges
- Existing manual process to extract data was time consuming, expensive and error prone.
- Client wants a solution to extract data quickly and accurately.
- Client wants to lower document processing cost.
Eliminate the need to maintain code or templates for every document or form or worry about how pagelayouts change over time.
How Our Organization Helped
- Implemented HIPAA compliant Amazon Textract service to extract valuable text and data from scanned documents accurately and efficiently.
- Built OCR solution that is fast, secure and reliable.
- Automated extraction of digitised files to meet high accuracy rate requirement.
- Application showed consistently high accuracy across many different tables, layouts, symbols and fonts.
Results
Develop an sophisticated application that achieved a 97% accuracy rate across all documentation. This application provides seamless experience with no errors in the extracted data, successfully serving healthcare industry.
