Elsevier Evaluation Framework for AI in Healthcare

[Chris Johnston]

Elsevier & the Medical Library Association (MLA) are co-hosting a webinar exploring Elsevier's work to develop evaluation tools for AI in healthcare, and particularly in clinical decision support. While this session is targeted at medical librarians, it's open to anyone interested in learning more.

From their email:

Join Amanda Barry, MPH, Principal Clinical Analyst and AI Ethics at Elsevier, who has been at the forefront of developing evaluation protocols for generative AI tools since October 2023. Her work with Elsevier Health's AI evaluation team focuses on accuracy, safety, and mitigating demographic bias in healthcare AI systems like ClinicalKey AI and Sherpath AI.

This webinar is particularly relevant for medical librarians who are increasingly asked about AI tools by healthcare providers. Amanda's epidemiological background and 11+ years in clinical decision support allow her to provide unique insights into what makes AI tools truly reliable for clinical use. Her team's research methodology, recently published in JAMIA Open, offers a "clinician-in-the-loop approach" that ensures AI evaluation assesses what matters most to clinicians.

[Paper: Reproducible generative artificial intelligence evaluation for health care: a clinician-in-the-loop approach]

Don't miss this opportunity to learn more about how we're guiding healthcare professionals toward trustworthy AI resources on Thursday, August 2025, at 1:00 p.m., central time.

Register here