Yes, AI outputs in elluminate can contain errors, which is why every AI capability includes a user review step before outputs are used. Generative AI outputs can include incorrect interpretations, omissions, or unsupported statements, and output quality depends on the available data and context. Machine learning models can flag records that do not require action or miss records that do.

To support accurate, verifiable outputs, generative AI capabilities base each output on the study data, metadata, and documents available to the user, use defined tools for data retrieval and computation, and display the basis for results, such as generated SQL queries, protocol references, and the rationale for suggestions. AI capabilities do not modify study data.

Important: Users remain responsible for checking important findings against the underlying study data and applying professional judgment before taking action.

For details, refer to the AI Governance, Privacy, and Data Security in elluminate article.