AI-Powered Document Intelligence for Healthcare Order Intake
- Technology: AWS, OCR, Generative AI
- Industry: Healthcare, DME
Industry Overview
About Client
Business Objectives
- Automate the capture of incoming fax-based orders
- Extract relevant information from unstructured documents
- Validate critical fields and diagnosis codes
- Reduce manual data entry and errors
- Route exceptions for manual review
- Automatically retry failed processing
- Provide full visibility into order processing and pipeline status
Solution
- Capture — incoming faxes arrive as email attachments in a dedicated Amazon WorkMail inbox and are automatically routed into cloud storage
- OCR — each page is converted to a high-resolution image and processed with AWS Textract to extract raw text and layout
- AI extraction — Amazon Bedrock reads the extracted text and produces a structured record covering patient, diagnosis, procedure, and delivery details
- Validation — diagnosis codes and nine mandatory fields are checked automatically; anything invalid or incomplete is routed to a reviewer with an instant alert
- Delivery — fully validated records are pushed into the client's document repository and order-management database, ready for immediate use
- Resilience — a daily automated job retries documents affected by temporary failures, and a daily summary report gives the operations team full visibility into pipeline health
| COMPONENT | ROLE |
|---|---|
| Amazon S3 | Central storage for incoming faxes, intermediate artifacts, and structured outputs |
| AWS Lambda | Orchestrates every processing stage, from intake through delivery |
| AWS Textract | Performs OCR on each scanned page, extracting text and layout |
| Amazon Bedrock | Reads extracted text and generates structured, validated order data |
| Amazon EventBridge | Drives scheduled retries and daily reporting |
| Amazon SNS | Delivers real-time exception alerts and daily summary reports |
| VPC · SharePoint · SQL Server | Secures downstream storage with dual persistence for traceability |
Solution Architecture: Fax OCR Processing for Healthcare DME
Benefits
| METRIC | VALUE | WHAT IT DEMONSTRATES |
|---|---|---|
| Documents processed / day | 116–130 | Solution throughput |
| Processing time / document | 20–30 sec | Processing speed |
| Manual review / day | 1–2 | Human intervention required |
| Fields extracted / document | 20–30 | Data extraction scale |
| Estimated successful processing rate | ~98.5–99.2%* | Overall pipeline reliability |
In Our Customers’ Words
Real pleasure consulting with Kenexai to set up our company’s entire data warehouse and dashboards on AWS. I will definitely be reaching out to them for future work to be done. Our project was effective and 100% achieved what I planned to do in the beginning, in a shorter time frame and with less effort than I expected.
Hans
United States
CCR Data perform complex data migrations, we needed and extra pair of hands to restore an Oracle database and transfer the data to a Microsoft SQL database ready for our migration analysts to do their stuff. We would not hesitate in recommending or using Kenexai again and would be happy to outsource bigger projects to them in the future.
Henry Sykes
Director - CCR Data
I have used RA on numerous occasions over the past 2 years, specifically with Nitesh Solanki for the delivery on PDI ETL jobs. I am very happy with him and the high level of quality work he has provided. He seems to be available all the time and works extremely hard to deliver high quality solutions.
Mark Scriven
Technical Director - Value Ad