Clinical documentation · Production

Clario streamlines clinical trial software configurations using Amazon Bedrock

The problem

Clario's clinical trial software configuration process relied on manual extraction of structured data from PDF transmittal forms and multiple enterprise data providers, creating transcription inconsistencies, version control complications, fragmented data silos, and delays in software build timelines.

Workflow diagram · grounded in source

Study code lookup and API fetch

trigger

“Users begin by entering a study code that uniquely identifies the clinical trial. The study lookup operation makes an API call to fetch study details such as study plan, participation criteria, sponsors, collaborators, and more from the …”

Transmittal form upload

integration

“Users upload transmittal forms containing study parameters such as information about exams, visits, conditions, and interventions to the Genie AI Service using the web UI through a secure AWS Direct Connect network.”

AI data extraction from PDFs

ai_action

“The solution uses Anthropic's Claude Sonnet on Amazon Bedrock through API calls to perform the following actions: Parse and extract structured data from transmittal forms”

Human review and validation

human_review

“An interactive review dashboard helps stakeholders verify AI-extracted information and make necessary corrections before finalizing the validated configuration.”

SCS document generation

output

“Post-validation, the system automatically generates a Software Configuration Specification (SCS) document as a comprehensive record of the software configuration.”

AI XML generation

ai_action

“The SCSXMLConverter, an internal microservice of the Genie AI Service, processes both SCS document and study configurations. This microservice invokes Anthropic's Claude 3.7 Sonnet through API calls to generate a standardized SCS XML file.”

XML validation

validation

“Validation checks are performed on the generated XML to make sure it meets the structural and content requirements of Clario's clinical study software.”

XML release to clinical software

output

“The process culminates with generative AI-powered XML generation, which is then released into Clario's proprietary medical imaging software for study builds”

Reported outcome

The Genie AI Service reduced configuration execution time and transcription errors, drastically reduced manual effort, enabled teams to focus on value-added activities, and established strong compliance through complete audit trails.

Reported metrics

Study configuration execution timehas been reduced while improving overall quality

Transcription errorsreduced potential transcription errors

Manual effortdrastically reduces manual effort

Reported stack

Amazon BedrockAnthropic's Claude 3.7 SonnetAmazon ECSGenie AI ServiceSCSXMLConverterGenie Database

Source

https://aws.amazon.com/blogs/machine-learning/clario-streamlines-clinical-trial-software-configurations-using-amazon-bedrock?tag=soumet-20

Read source ↗

Frequently asked questions

What did this team achieve with this AI workflow?

The Genie AI Service reduced configuration execution time and transcription errors, drastically reduced manual effort, enabled teams to focus on value-added activities, and established strong compliance through comple…

What tools did this team use?

Amazon Bedrock, Anthropic's Claude 3.7 Sonnet, Amazon ECS, Genie AI Service, SCSXMLConverter, Genie Database.

What results were reported?

Study configuration execution time: has been reduced while improving overall quality; Transcription errors: reduced potential transcription errors; Manual effort: drastically reduces manual effort (source-reported, not independently verified).

How is this clinical documentation AI workflow structured?

Study code lookup and API fetch → Transmittal form upload → AI data extraction from PDFs → Human review and validation → SCS document generation → AI XML generation → XML validation → XML release to clinical software.