FDA unveils ‘Elsa’ generative AI tool for staff

The U.S. Food and Drug Administration launched a generative artificial intelligence-powered tool on Tuesday, tailored to help the agency’s scientific research efforts and operational work as part of a larger bid to expedite its core missions. 

Named Elsa, the large language model is hosted within a high-security GovCloud environment to ensure the safety of the reservoir of internal documents it can access. Chief among Elsa’s tasks will be aiding FDA staff in hastening the clinical review process and shortening time spent on scientific evaluations.

“Today marks the dawn of the AI era at the FDA with the release of Elsa, AI is no longer a distant promise but a dynamic force enhancing and optimizing the performance and potential of every employee,” FDA Chief AI Officer Jeremy Walsh said in a press release. “As we learn how employees are using the tool, our development team will be able to add capabilities and grow with the needs of employees and the agency.”

As an LLM, Elsa is designed to aid in the reading, writing and summarizing of internal FDA documents. Some other notable features of the tool include summarizing adverse events to contribute to safety assessments, generating faster label comparisons and creating code to develop databases for nonclinical applications. 

The model wasn’t trained on data submitted by regulated industry as a means to protect sensitive data handled by the FDA.

“The introduction of Elsa is the initial step in the FDA’s overall AI journey,” the agency’s press release said. “As the tool matures, the agency has plans to integrate more AI in different processes, such as data processing and generative-AI functions to further support the FDA’s mission.”

Elsa’s deployment comes ahead of schedule, with the rollout date initially slated for June 30. Leadership at the FDA has been keen to incorporate more AI tools across agency operations following an initial pilot trial stage. In a May comment to Nextgov/FCW, the FDA clarified that agency Commissioner Marty Makary’s posture on AI implementation focuses on leveraging the technology to support human employees rather than replacing them.

“When used responsibly, AI can enhance regulatory rigor by helping predict toxicities and adverse events for certain conditions,” the spokesperson said in May.