Pharmaceuticals and biotech / Clinical trial technology
Thermo Fisher Scientific: Natural-language discovery and filtering of clinical trial recruitment cohorts
- Company
- Thermo Fisher Scientific
- Country
- Multiple countries
- Adoption stage
- In operation
- Source published
- Date basis
- The date the source was published. It can differ from the date adoption started.
- How the source was checked
- Read the full source text
The work problem
Thermo Fisher Scientific recruitment data was scattered across surveys, consent records and recruitment activity. Teams repeatedly requested technical queries as cohort criteria changed.
Technology and data
The AWS and company-authored article describes curating data with S3 and Glue for natural-language discovery in Patient Match AI. Recruitment staff refine age, geography and treatment criteria. Identifiable workflows retain consent and contactability controls. Lambda handles patient match scoring.
Results
The article reports over 20 million consolidated profiles and common cohort analyses reduced from days to minutes. Shared test queries ran against the full dataset in under six seconds. Production began in Q2 FY26.
Limits and open questions
The fiscal quarter was not converted into an adoption month. Test-query speed does not establish improvement for every query or patient enrollment rates.
Sources
- How Thermo Fisher Scientific built AI-powered patient matching on AWSAWS / Thermo Fisher Scientific, Accessed
Compiled from public sources. These are not results from ATF Works customers.