Clario automates clinical research COA interview analysis using generative AI on AWS
The problem
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.
Workflow diagram · grounded in source
1
Interview recordings uploaded to S3
Trigger
COA interview audio and video files are collected on premises and uploaded via AWS Direct Connect to Amazon S3.
▾ source quote
“The COA interview recordings (audio and video files) from the interviews are collected on premises (1) using a recording application. The files are uploaded using
AWS Direct Connect
with encryption in transit to
Amazon Simple Storage Service (Amazon S3)”
2
Speaker diarization on SageMaker
Ai action
A custom speaker diarization model on Amazon SageMaker extracts the audio and identifies speech segments of unique speakers.
▾ source quote
“extracts the audio and identifies speech segments of unique speakers using a custom speaker diarization model on
Amazon SageMaker”
3
Multi-lingual transcription via Whisper
Ai action
The Whisper model from the Amazon Bedrock Marketplace generates near real-time transcriptions of the COA interview recordings.
▾ source quote
“Clario uses the Whisper model from the
Amazon Bedrock Marketplace
(5) to generate near real-time transcriptions of the COA interview recordings. The transcriptions are then annotated with speaker information and timecodes”
4
Vectorization and storage in OpenSearch
Integration
Transcripts are vectorized using the Amazon Titan Text Embeddings v2 model and stored in Amazon OpenSearch for semantic retrieval.
▾ source quote
“vectorized using an embedding model (Amazon Titan Text Embeddings v2 model) and stored into Amazon OpenSearch (7) for semantic retrieval”
5
Graph-based agent COA review
Ai action
A graph-based agent system on Amazon EKS executes automated COA interview review by retrieving the interview guide, loading checklist criteria, and querying OpenSearch for relevant segments.
▾ source quote
“Clario's AI Orchestration Engine executes a graph-based agent system running on Amazon Elastic Kubernetes Service (Amazon EKS) (3) for automated COA interview review. The agent implements a multi-step workflow that: (1) retrieves the assessment's structured interview guide from configuration, (2) …”
6
LLM classification and quality evaluation
Ai action
Anthropic Claude 3.7 Sonnet from Amazon Bedrock classifies each speech segment as interviewer or participant and determines if each interview turn meets the interview quality criteria.
▾ source quote
“The agent uses advanced large language models (LLMs), such as Anthropic Claude 3.7 Sonnet from Amazon Bedrock (6), to classify the speech segment as interviewer or participant, and to determine if each interview turn meets the interview quality criteria”
7
AI output validation against source
Validation
AI outputs are cross-checked against source documents for factual accuracy before human review.
▾ source quote
“Clario to implement a validation system where AI outputs are cross-checked against source documents for factual accuracy before human review”
8
Review compiled and persisted to RDS
Output
The AI Orchestration Engine compiles the overall review of the interview and persists the information in Amazon RDS.
▾ source quote
“Clario's AI Orchestration Engine then compiles the overall review of the interview and persists the information in
Amazon Relational Database Service (Amazon RDS)”
Reported 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.
Reported metrics
Manual review effort reductionover 90%
Data coverage via automated reviewup to 100%
Central review turnaround timefrom weeks to hours
Reported stack
Amazon BedrockAmazon SageMakerAmazon Titan Text Embeddings v2Amazon OpenSearchAmazon EKSAnthropic Claude 3.7 SonnetAmazon RDSAmazon API GatewayAWS Lambda
◆ Does this fit your context?
Compare to your context
Tell us your scale, team, and constraints. We'll show what changes at your size, what fails at your scale, and whether this case is a fit, needs adaptation, or won't scale to you. Free demo, no signup.
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.
What tools did this team use?
Amazon Bedrock, Amazon SageMaker, Amazon Titan Text Embeddings v2, Amazon OpenSearch, Amazon EKS, Anthropic Claude 3.7 Sonnet, Amazon RDS, Amazon API Gateway, AWS Lambda.
What results were reported?
Manual review effort reduction: over 90%; Data coverage via automated review: up to 100%; Central review turnaround time: from weeks to hours (source-reported, not independently verified).
How is this clinical documentation AI workflow structured?
Interview recordings uploaded to S3 → Speaker diarization on SageMaker → Multi-lingual transcription via Whisper → Vectorization and storage in OpenSearch → Graph-based agent COA review → LLM classification and quality evaluation → AI output validation against source → Review compiled and persisted to RDS.
This case is one data point. Whether its pattern fits you depends on your volumes, your stack, and your exception load — that comparison is the step no case study can do for you.