United StatesHealthcare and life sciences2021 – ongoingAnthem
Amazon Textract extraction of provider claim documents
AWS reported that Anthem automated 80% of its claims-processing workflow
Problem
Anthem staff took an average of 20 minutes per claim to manually extract information from submitted documents.
Approach
Anthem used Amazon Textract to process documents submitted through its provider portal. Optical character recognition extracted data, while machine learning indexed and classified documents. Processed claims then became available to Anthem staff.
Results
Takeaway
The reported automation covered document processing within the claims workflow. It did not establish that AI made coverage or payment decisions.
Categories
- Size
- Large enterprise
- Industry
- Healthcare and life sciences
- Business function
- Production and quality
- Innovation type
- Process innovation
- AI technology
- Computer visionPredictive analytics and ML
- Adoption
- Vendor solution
- Evidence
- Vendor case study
Sources
Source summaries
AWS reported that Anthem automated 80% of its claims-processing workflow and processed thousands of claims daily. Automation of 90% or higher remained an expectation.
Full details are in the original sources.