Skip to main content
Showing 331 - 340 out of 347
Course/Webinar

Levels of Clinical Evaluation for LLMs: Towards More Realistic Evaluations

Large language models (LLMs) hold immense promise for democratizing access to medical information and assisting physicians in delivering higher-quality care. However, realistic evaluations of LLMs in clinical contexts have been limited, with much focus placed on multiple-choice evaluations of clinical knowledge.

Important Dates

Early bird deadline: 2024 Annual Symposium

Join thousands of colleagues in San Francisco, November 9-13 for the AMIA 2024 Annual Symposium. This annual event is the world’s premier meeting for the research and practice of biomedical and health informatics.

AMIA Board

Board of Directors Meeting - Sep. 2024

The Board of Directors is the primary governance body of the Association. Its members focus on high-level strategy, oversight, and accountability for the organization and its operations.

Course/Webinar

Sponsored Webinar with RTI International

The Transformative Impact of AI in Healthcare, Informatics, and the Research Community. Join researchers from RTI International for an insightful webinar exploring the transformative impact of AI in healthcare, informatics, and the research community. We'll kick off with a brief overview of AI's role in the sector, highlighting its integration with Clinical Decision Support (CDS) systems, applying AI in Large-scale EHR Data Repositories, and how LLMs are more than just Gen AI.

Course/Webinar

Behavioral Testing and Evaluation to Probe Language Models for Algorithmic Bias

-

With growing legal and scientific evidence for the importance of reducing model bias, both model developers and deployers need tools to quantify the bias. Unfortunately, algorithmic bias can take as many forms as there are implementations. In this talk, Paul M. Heider covesr a range clinical NLP use cases like de-identification and predicting diagnoses, highlighting the utility of behavioral testing and comparative evaluation methods to identify the scope of a model’s bias.

Course/Webinar

ASTP/ONC HTI-2 Proposed Rule

The ASTP/ONC Health Data, Technology, and Interoperability: Patient Engagement, Information Sharing, and Public Health Interoperability (HTI-2) Proposed Rule builds upon the passage of the 21st Century Cures Act (Cures Act) and progress in data interoperability throughout the health care landscape.

Course/Webinar

FAMIA Leadership Lounge: Live with Jesse Ehrenfeld, MD, MPH, FAMIA

Join the Fellows of AMIA for the premiere of the FAMIA Leadership Lounge: Live! a webinar series featuring FAMIA leaders in a fireside-chat style discussion.  The first session features Jesse Ehrenfeld, MD, MPH, FAMIA, 178th president of the American Medical Association, board certified clinical informatician, Professor and Senior Associate Dean for the Medical College of Wisconsin.

Course/Webinar

25x5 Policy and Advocacy Workstream: Addressing Documentation Burden with Federal Legislators and Regulators

This webinar will provide an opportunity for members to hear from the 25x5 Policy and Advocacy Workstream about their work tackling documentation burden for clinical workers at a federal level. Members will hear updates on how the Workstream advances the 25x5 Task Force’s mission to reduce U.S. health professionals’ documentation burden to 25% of the current state within five years of the Task Force’s inception in 2021, as well as how the Workstream advances Informatics

Course/Webinar

Patient Record Summarization in the Age of LLMs

Clinician burnout, driven in part by the increasing burden of EHR documentation, is a significant threat to healthcare quality. This talk will introduce SPEER, a novel approach to automatically generating clinically useful hospital-course summaries from raw clinical notes. The SPEER method leverages the power of Large Language Models (LLMs) while addressing key challenges in clinical summarization, such as identifying salient information from lengthy records and ensuring the accuracy of generated summaries. We will also discuss the state of the art in automated evaluation methods and implications of summarization from a human-centered AI standpoint.

FIlters

Event Type