The implementation of artificial intelligence (AI) in the clinical research space has happened at such a rapid pace that many are left asking a fundamental question: How do we know if this thing is working the way we intended? When pressed, AI vendors rarely provide error rate data or any delineation between the root causes of failure. That absence of accountability is precisely where quality professionals need to step in. AI might be new, but basic research principles still apply.

Geared toward research site staff who are implementing generative AI for source records and sponsor staff using AI to support database and protocol development, this presentation borrows directly from medical device quality methodology to build internal AI quality assurance programs. Most current quality standards were not written with AI in mind; thus, quality assurance of AI systems does not require a novel approach, it requires research.

CEU: 1.0 ACRP

Speaker:

• Michele LaBadie, ACRP - CP, MDP, PM, Clinical Trial Manager, Shoulder Innovations