Related Experiment Video
Updated: Jul 2, 2025
Semiconductor Sequencing for Preimplantation Genetic Testing for Aneuploidy
Published on: August 25, 2019
Retrieval Augmented Generation Enabled Generative Pre-Trained Transformer 4 (GPT-4) Performance for Clinical Trial
Ozan Unlu1,2,3,4, Jiyeon Shin1,5, Charlotte J Mailly1,5
1Accelerator for Clinical Transformation, Brigham and Women's Hospital, Boston, MA.
Retrieval-Augmented Generation (RAG) with GPT-4 accurately identifies clinical trial eligibility criteria, improving upon traditional manual screening methods for efficiency and accuracy in patient selection.
Area of Science:
- Artificial Intelligence in Clinical Trials
- Natural Language Processing for Healthcare
- Clinical Trial Subject Screening Optimization
Background:
- Traditional clinical trial subject screening is resource-intensive and prone to errors.
- Large language models (LLMs) offer potential for enhanced quality and efficiency in screening.
- This study evaluates a Generative Pretrained Transformer Version 4 (GPT-4) powered Retrieval-Augmented Generation (RAG) system for trial criteria identification.
Conclusions:
- GPT-4 based solutions, like RECTIFIER, demonstrate significant potential to enhance clinical trial screening efficiency and reduce costs.
- Automation of screening processes requires careful consideration of potential hazards.
- Implementing mitigation strategies, such as final clinician review, is crucial before patient engagement with AI-driven tools.
More Related Videos
09:30Pre-Implantation Genetic Testing for Aneuploidy on a Semiconductor Based Next-Generation Sequencing Platform
Published on: August 17, 2022
09:03Parallel Interrogation of β-Arrestin2 Recruitment for Ligand Screening on a GPCR-Wide Scale using PRESTO-Tango Assay
Published on: March 10, 2020
