The Use of Large Language Models to Accelerate Literature Review Towards Digital Health Equity and Inclusiveness
Presentation Time: 11:45 AM - 12:00 PM
Abstract Keywords: Large Language Models (LLMs), Diversity, Equity, Inclusion, Accessibility, and Health Equity, Information Extraction
Primary Track: Foundations
Programmatic Theme: Clinical Research Informatics
Digital health technologies (DHTs) have revolutionized clinical trials (RCTs), offering unprecedented opportunities to streamline processes, enhance patient engagement, and improve data quality. Growing technology device and broadband access are contributing to the increasing number of RCTs implementing DHTs. In theory, DHTs have the potential to make clinical research more inclusive and diverse. However, while the diversity in DHT technologies and implementations presents a strong display of healthcare innovation, major challenges arise concerning DHT generalizability and translation into real-world medical practice. In this study, we report our efforts in accelerating the literature review process related to the use of DHTs in RCTs by leveraging large language models (LLMs); identified in existing LLM task evaluation literature as a possible literature review methodology supporting scalability. We designed three tasks for automating screening and information extraction of DHT-enabled RCTs using multiple LLMs. Experiments show promising results of LLMs for accelerating the literature review tasks.
Speaker(s):
Taylor Harrison, M.B.A.
Mayo Clinic
Presentation Time: 11:45 AM - 12:00 PM
Abstract Keywords: Large Language Models (LLMs), Diversity, Equity, Inclusion, Accessibility, and Health Equity, Information Extraction
Primary Track: Foundations
Programmatic Theme: Clinical Research Informatics
Digital health technologies (DHTs) have revolutionized clinical trials (RCTs), offering unprecedented opportunities to streamline processes, enhance patient engagement, and improve data quality. Growing technology device and broadband access are contributing to the increasing number of RCTs implementing DHTs. In theory, DHTs have the potential to make clinical research more inclusive and diverse. However, while the diversity in DHT technologies and implementations presents a strong display of healthcare innovation, major challenges arise concerning DHT generalizability and translation into real-world medical practice. In this study, we report our efforts in accelerating the literature review process related to the use of DHTs in RCTs by leveraging large language models (LLMs); identified in existing LLM task evaluation literature as a possible literature review methodology supporting scalability. We designed three tasks for automating screening and information extraction of DHT-enabled RCTs using multiple LLMs. Experiments show promising results of LLMs for accelerating the literature review tasks.
Speaker(s):
Taylor Harrison, M.B.A.
Mayo Clinic
The Use of Large Language Models to Accelerate Literature Review Towards Digital Health Equity and Inclusiveness
Category
Paper - Student