Moving Beyond the Hype to Objective Measurement of Generative AI Clinical Documentation

How can organizations and healthcare providers objectively evaluate the risks and benefits of new generative AI clinical documentation offerings?  Are there process or outcome measures that represent best practice? What do we know now about safety measurement, and can we automate evaluation of quality in areas as subjective as clinical note and patient advice compositions?

Join this panel discussion, as leaders in the field will address these questions and more, focusing on practical advice that is informed by the medical literature.  Attendees will leave with a broad understanding of different types of evaluation processes and how organizations can handle the outcomes of their evaluation.

Learning Objectives

• Explain the potential risks and benefits of generative AI clinical documentation offerings.
• Discuss the current understanding of safety measurement and quality evaluation in clinical note and patient advice compositions.
• Identify the best process and outcome measures for evaluating generative AI clinical documentation based on current best practices.
• Apply practical advice for handling the outcomes of evaluation of generative AI clinical documentation in healthcare organizations.
• Discuss the feasibility and effectiveness of automating the evaluation of quality in subjective areas such as clinical note and patient advice compositions.

Speakers

Moderator:

• Jonah Feldman, MD, Medical Director, Clinical Transformation and Informatics at NYU Langone Health.

Panelists:

• Jonathan Austrian, MD, Associate Chief Medical Information Officer, Inpatient Informatics at NYU Langone Health.
• Michael Gao, Principal Data Scientist at Duke Institute for Health Innovation
• Manisha Loss, MD, Associate Chief Medical Information Officer (aCMIO) for Johns Hopkins Medicine. She is also an Associate Professor of Dermatology at the Johns Hopkins University School of Medicine.

The views and opinions expressed in this content or by commenters are those of the author and do not necessarily reflect the official policy or position of HIMSS or its affiliates.