Artificial intelligence enhances screening efficiency for inflammatory bowel disease clinical trials: a prospective...

Area of Science:

• * Clinical trial recruitment
• * Artificial intelligence in medicine
• * Inflammatory Bowel Disease (IBD) research

Background:

• * Clinical trials are crucial for advancing IBD treatment.
• * Patient recruitment remains a significant bottleneck in clinical trial completion.
• * Current methods for identifying eligible patients can be inefficient.

Purpose of the Study:

• * To evaluate the efficacy of a large language model (LLM)-based AI tool in improving patient identification for IBD clinical trials.
• * To compare the performance of the AI tool against traditional physician referral methods.
• * To assess the impact of AI on clinical trial screening efficiency.

Main Methods:

• * Development and implementation of an LLM-based AI tool to screen electronic medical records (EMRs).
• * The AI tool was programmed with specific inclusion and exclusion criteria for IBD clinical trials.
• * Candidate patient lists were generated and ranked by the AI tool for review.

Main Results:

• * The LLM-based AI tool significantly improved the identification of potentially eligible patients for IBD clinical trials.
• * AI-driven screening demonstrated higher efficiency compared to standard physician referrals.
• * Ranked candidate lists facilitated a more streamlined review process.

Conclusions:

• * LLM-based AI tools offer a promising solution to enhance patient recruitment for IBD clinical trials.
• * AI can optimize the screening process, leading to faster and more efficient trial enrollment.
• * This technology has the potential to accelerate IBD research and therapeutic development.