July 23 - Leveraging Large Language Models for Decision Support in Personalized Oncology
Image For Activity Cover
Availability
Registration ends on July 23, 2024
Expires on 08/23/2024
Online Meeting
Jul 23, 2024 11:00 AM - 12:00 PM EST
Cost
$0.00
Credit Offered
1 CME (AMA) Credit
1 CME (Other) Credit

Title:  Leveraging Large Language Models for Decision Support in Personalized Oncology

Tuesday, July 23, 2024

11:00am-12:00pm ET

 

Description

Large Language Models (LLMs) are AI tools trained to generate new text from large datasets. Since the release of ChatGPT, they have received significant public attention and sparked a debate about the benefits and risks of Artificial Intelligence to an unprecedented degree. LLMs enable tasks such as answering questions, summarizing text, or translating, with a quality that approaches human level. The use of LLMs is increasingly entering the medical field, changing how research is conducted on medical issues, how medicine is taught, and how it is practiced by physicians.

In this presentation, we will give an introduction into LLMs and present a study, which evaluates the potential of conversational large language models (LLMs) as tools for personalized decision-making in precision oncology. Ten fictional cases of advanced cancer with genetic alterations were assessed by four different LLMs (ChatGPT, Galactica, Perplexity, and BioMedLM) and one expert physician to identify treatment options. While LLMs provided a higher number of treatment options compared to the expert, their suggestions often deviated from expert recommendations. However, LLMs did propose some reasonable strategies not easily identified by experts, suggesting potential for improvement in LLM-based decision-making tools. Despite not yet being suitable for routine clinical use, LLMs may enhance existing methods in oncology decision support, particularly as technology advances.

 

Target Audience

All medical and healthcare professionals and researchers interested in understanding cancer genomic testing and somatic and germline variant interpretation methods. This series is presented as a collaboration between ClinGen Somatic, VICC, and ACMG consortia.

 

Agenda

Presentation followed by live Q&A. 

 

Learning Objectives

At the conclusion of this session, participants should be able to:

1. Name different Large Language Models which are currently available.

2. Discuss possible constraints of LLMs in the field of precision oncology.

3. Differentiate between prompting strategies.

no image

Moderator:
Beth Pitel, MS

Clinical Variant Scientist – Oncology

Assistant Professor of Laboratory Medicine and Pathology

Mayo Clinic

 

no image

Presenters:
Manuela Benary, PhD

Bioinformatician
Charité – Universitätsmedizin Berlin, Berlin, Germany

Manuela Benary is the lead bioinformatician at the Charité Comprehensive Cancer Center and a scientist at the Core Unit Bioinformatics (CUBI) which provides bioinformatics and data analysis expertise for translational research at the Berlin Institute of Health (BIH). She is the co-spokesperson of the Platform for Personalized Cancer Medicine - Charité (PPK - C). Her research focuses, among other things, on the potential applications of Large Language Models (LLMs) in precision medicine.


Xing Wang

Second-year PhD student, Humboldt-University in Berlin

 

Xing David Wang is a second-year PhD student at Humboldt-University in Berlin at the chair Knowledge Management in Bioinformatics of Professefor Ulf Leser. His research interests lie in the field of text mining and natural language processing for biomedicine particularly in the intersection with precision oncology.

 

 

 

Planning Committee:

Beth Pitel, MS, CG(ASCP)

Gordana Raca, MD, PhD, FACMG

Manuela Benary, PhD

Jason Saliba, PhD

Jane Radford, MHA, CHCP

Claudia Barnett 

Accredited Continuing Education Information:

Continuing Medical Education (CME AMA & CME Other)

 

Accreditation

The American College of Medical Genetics and Genomics is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians.

 

Credit Designation

The American College of Medical Genetics and Genomics designates this live activity for a maximum of 1.0 AMA PRA Category 1 Credits™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.

 

The American Medical Association (AMA) defines physicians as those individuals who have obtained an MD, DO, or equivalent medical degree from another country. Non-physicians may request a certificate of attendance for their participation.

 

Claiming your Educational Credits

Complete the activity and carefully complete the evaluation form. The deadline to claim educational credits is within 30 days of the date of the activity. Educational credit requests after this date will not be accepted.

Accredited Continuing Education Information:

Continuing Medical Education (CME AMA & CME Other)

 

Accreditation

The American College of Medical Genetics and Genomics is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide continuing medical education for physicians.

 

Credit Designation

The American College of Medical Genetics and Genomics designates this live activity for a maximum of 1.0 AMA PRA Category 1 Credits™. Physicians should claim only the credit commensurate with the extent of their participation in the activity.

 

The American Medical Association (AMA) defines physicians as those individuals who have obtained an MD, DO, or equivalent medical degree from another country. Non-physicians may request a certificate of attendance for their participation.

 

Claiming your Educational Credits

Complete the activity and carefully complete the evaluation form. The deadline to claim educational credits is within 30 days of the date of the activity. Educational credit requests after this date will not be accepted.

 

Accredited Continuing Education Financial Disclosure

The American College of Medical Genetics and Genomics (ACMG) is accredited by the Accreditation Council for Continuing Medical Education (ACCME) to provide Accredited Continuing Education (ACE) for physicians. ACMG is an organization committed to improvement of patient care and general health by the incorporation of genetics and genomics into clinical practice.

 

ACMG has implemented the following procedures to ensure the independence of ACE activities from commercial influence/promotional bias, the Accreditation Council for Continuing Medical Education (ACCME) requires that providers (ACMG) must be able to demonstrate that: 1) everyone in a position to control the content of an ACE activity has disclosed all financial relationships that they have had in the past 24 months with ineligible* companies; 2) ACMG has implemented a mechanism to mitigate relevant financial relationships; and 3) all relevant financial relationships with ineligible companies are disclosed to the learners before the beginning of the educational activity. The learners must also be informed if no relevant financial relationships exist.
*Ineligible companies are defined as those whose primary business is producing, marketing, selling, re-selling, or distributing healthcare products used by or on patients.

 

ACMG Education Policies

Please review the policies below regarding the ACMG Education program

 

All of the relevant financial relationships listed for these individuals have been mitigated.

 

NAME

ROLE

RELATIONSHIP/ COMPANY

 

Planning Member

Presenter Panelist Moderator

Peer Reviewer

 

Xing Wang

 

 

 

Nothing to Disclose

Beth Pitel, MS, CG(ASCP)

 

 

Advisory Board – Qiagen, LLC

Claudia Barnett

 

 

Nothing to Disclose

Gordana Raca, MD, PhD, FACMG

 

Nothing to Disclose

Jane Radford, MHA, CHCP

 

 

Nothing to Disclose

Jason Saliba, PhD

 

 

Nothing to Disclose

Manuela Benary, PhD

 

 

Nothing to Disclose

 

 

Questions regarding CE credit should be directed to education@acmg.net

 

 

 

© 2024 American College of Medical Genetics and Genomics. All rights reserved.

Powered By