Emerging Trends in AI Applications: Shaping Pharmacoepidemiology and Health Technology Assessments
Author(s)
Aurore BERGAMASCO, PharmD, MSc1, Richard CHIV, MSc2, Yola Moride, PhD2;
1YOLARX Consultants, Paris, France, 2YOLARX Consultants, Montreal, QC, Canada
1YOLARX Consultants, Paris, France, 2YOLARX Consultants, Montreal, QC, Canada
OBJECTIVES: Since the advent of artificial intelligence (AI), interest in its application in pharmacoepidemiology (PE) and health technology assessment (HTA) has grown significantly. This study aimed to evaluate trends in AI utilization across studies presented at major conferences in PE and HTA since the public release of ChatGPT on November 30, 2022.
METHODS: A systematic approach was used to identify all conference proceedings mentioning AI-related keywords, such as “artificial intelligence”, “machine learning”, “large language model”, “natural language processing” or “ChatGPT”, among others. The analysis included studies presented at meetings of the International Society for Pharmacoeconomics and Outcomes Research (ISPOR) and the International Society for Pharmacoepidemiology (ISPE), encompassing annual meetings, mid-year events, and regional conferences from January 1, 2020, to December 6, 2024. For each relevant study, extracted data included the conference name and year, type of investigator, research field, research activity, and the specific AI tool or large language models (LLMs) utilized.
RESULTS: Of the 28,184 abstracts presented at ISPOR and ISPE conferences during the search period, 1,153 eligible proceedings reporting on AI use were identified. Across all conferences from 2020 to 2024, there was a consistent increase in the number of studies utilizing AI, with ISPOR exhibiting both the highest number of studies (n= 900) and the steepest growth in AI adoption compared to ISPE (n=253). The majority of these studies were conducted by contract research organizations (44%), followed by academic groups(40%), and the pharmaceutical industry (16%). Notably, AI tools and LLMs were predominantly used to semi- or fully automate literature reviews (89%), followed by economic modeling (9%).
CONCLUSIONS: ISPOR conferences demonstrated the highest engagement with AI-driven studies, suggesting a growing interest in integrating AI into health economics and outcomes research. The predominance of AI in automating literature reviews underscores its role in enhancing research efficiency and scalability.
METHODS: A systematic approach was used to identify all conference proceedings mentioning AI-related keywords, such as “artificial intelligence”, “machine learning”, “large language model”, “natural language processing” or “ChatGPT”, among others. The analysis included studies presented at meetings of the International Society for Pharmacoeconomics and Outcomes Research (ISPOR) and the International Society for Pharmacoepidemiology (ISPE), encompassing annual meetings, mid-year events, and regional conferences from January 1, 2020, to December 6, 2024. For each relevant study, extracted data included the conference name and year, type of investigator, research field, research activity, and the specific AI tool or large language models (LLMs) utilized.
RESULTS: Of the 28,184 abstracts presented at ISPOR and ISPE conferences during the search period, 1,153 eligible proceedings reporting on AI use were identified. Across all conferences from 2020 to 2024, there was a consistent increase in the number of studies utilizing AI, with ISPOR exhibiting both the highest number of studies (n= 900) and the steepest growth in AI adoption compared to ISPE (n=253). The majority of these studies were conducted by contract research organizations (44%), followed by academic groups(40%), and the pharmaceutical industry (16%). Notably, AI tools and LLMs were predominantly used to semi- or fully automate literature reviews (89%), followed by economic modeling (9%).
CONCLUSIONS: ISPOR conferences demonstrated the highest engagement with AI-driven studies, suggesting a growing interest in integrating AI into health economics and outcomes research. The predominance of AI in automating literature reviews underscores its role in enhancing research efficiency and scalability.
Conference/Value in Health Info
2025-05, ISPOR 2025, Montréal, Quebec, CA
Value in Health, Volume 28, Issue S1
Code
MSR69
Topic
Methodological & Statistical Research
Topic Subcategory
Artificial Intelligence, Machine Learning, Predictive Analytics
Disease
No Additional Disease & Conditions/Specialized Treatment Areas