Back to all short courses
Practical Applications of Large Language Models for Real World Evidence Generation and HEOR- Virtual
LEVEL: Intermediate
TRACK: Real World Data & Information Systems
LENGTH: 4 Hours | Course runs 2 consecutive days, 2 hours each day
Register Here
Wednesday, 4 September 2024 | Course runs 2 consecutive days, 2 hours per day
10:00AM–12:00PM Eastern Daylight Time (EDT)
14:00PM–16:00PM Coordinated Universal Time (UTC)
16:00PM–18:00PM Central European Summer Time (CEST)
Thursday, 5 September 2024 | Course runs 2 consecutive days, 2 hours per day
10:00AM–12:00PM Eastern Daylight Time (EDT)
14:00PM–16:00PM Coordinated Universal Time (UTC)
16:00PM–18:00PM Central European Summer Time (CEST)
DESCRIPTION
This academic course explores Large Language Models (LLMs) like GPT, BERT, and LLaMA, and how to use them for real world evidence generation and HEOR. Topics include LLM basics, training, health data analysis, optimal model selection for specific tasks, and ethical and regulatory considerations related to LLMs and health data. Students will learn about regulatory guidelines for using LLMs in healthcare applications and how to ensure responsible use that complies with regulations. The course introduces prompt engineering using practical examples, allowing students to apply it to real LLMs. Medical data summarization using LLMs is examined, as well as evidence generation, analysis of healthcare data, and the automation of value dossier creation. Through this comprehensive curriculum, participants gain the knowledge and skills to responsibly employ LLMs for practical tasks in RWE and HEOR while addressing regulatory requirements. To participate in hands-on activities, participants must have access to a laptop and a ChatGPT personal or corporate account.
PREREQUISITE: General knowledge of ChatGPT is important.
Faculty
Manuel Cossio, MMed, MEng
Researcher & Global Digital Health Head
HE-Xperts Consulting LLC
Miami, FL, USA and
Universitat de Barcelona
Barcelona, Spain
Ben Bray, MD, MSc
Evidence Generation Lead
Lane Clark and Peacock LLP
London, England, UK
Basic Schedule:
4 Hours | Course runs 2 consecutive days, 2 hours each day
ISPOR short courses are designed to enhance knowledge and techniques in core health economics and outcomes research (HEOR) topics as well as emerging trends in the field. Short courses offer 4 or 8 hours of premium scientific education and an electronic course book. Active attendee participation combined with our expert faculty creates an immersive and impactful virtual learning experience. Short courses are not recorded and are only available during the live broadcast.
