clinical_documentation · healthcare · workflow
Clario automates clinical research COA interview analysis using generative AI on AWS
Traditional COA interview quality evaluation required time-consuming, logistically challenging reviews of audio-video recordings in near real time, with variability between expert reviewers, poor assessment technique, and other noise factors that could lead to unreliable results and study failure.
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 · Interview recordings uploaded to S3
COA interview audio and video files are collected on premises and uploaded via AWS Direct Connect to Amazon S3.
Tools used
Amazon BedrockAmazon SageMakerAmazon Titan Text Embeddings v2Amazon OpenSearchAmazon EKSAnthropic Claude 3.7 SonnetAmazon RDSAmazon API GatewayAWS Lambda
Outcome
Clario's AI-powered solution shows potential to decrease manual review effort by over 90%, achieve up to 100% data coverage through automated review, and shorten central review turnaround time from weeks to hours.
Results
Time savedfrom weeks to hours
Volumeover 90%
Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes, 4 dropped as unverifiable.
agentic workflowdocument classificationragspeech to textsummarizationcall recordingclinical notefailure mode describedhuman review describedmetric backednamed customerproduction runtime claimedworkflow describedpharma life sciencesautomation ratecycle time reductionemployee productivitytechnical build writeupclinical documentationquality assuranceagentic task executionextract classify route