This feasibility study explores how large language models (specifically GPT-4) can accelerate the time-consuming data extraction phase of systematic reviews in medical research.

• Successfully extracted key study characteristics from clinical and animal studies
• Demonstrated potential for semi-automated PICO element extraction (Participants, Interventions, Controls, Outcomes)
• Identified both capabilities and limitations for practical implementation

This research matters because systematic reviews are crucial for evidence-based medicine but require significant manual effort. AI-assisted extraction could dramatically reduce researcher workload while maintaining quality, potentially accelerating medical evidence synthesis at scale.

Exploring the use of a Large Language Model for data extraction in systematic reviews: a rapid feasibility study