Care Access achieves 86% cost reduction and 66% faster data processing with Amazon Bedrock prompt caching
Care Access processed hundreds of medical records daily for its health screening program, with each analysis requiring multiple separate prompts that each reprocessed substantial portions of the record content, driving high operational costs and slower processing times as participant volume scaled.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · EHR retrieval from S3
Individual electronic health records are retrieved from an Amazon S3 bucket, normalized for processing, and prepared for inference with unnecessary data removed.
Tools used
Amazon BedrockAmazon S3Amazon AthenaAWS Lake FormationAmazon CloudWatch
Outcome
Prompt caching in Amazon Bedrock achieved an 86% reduction in Bedrock costs and a 66% reduction in processing time per record, saving 4-8+ hours of processing time daily, while maintaining compliance standards and enabling continued program growth.
What failed first
The initial LLM implementation required every separate analysis question to reprocess the full medical record content, and as participant volume grew, this approach led to significant daily operational costs.
data extractiondocument aiclinical notemedical recordmetric backednamed customerproduction runtime claimedsource backedtools describedworkflow describedhealthcarepharma life sciencescost reductioncycle time reductiontime savedplatform led casemedical records processingdocument to recordextract classify route