Can AI-Powered TrialGPT Enhance Patient Recruitment for Clinical Trials?

Clinical trials are pivotal for medical advancements, yet recruiting participants remains a significant challenge due to complex eligibility criteria and various barriers. Traditional manual screening is time-consuming and prone to errors, often causing delays. TrialGPT, an artificial intelligence (AI)-based system leveraging large language models, offers a promising solution to streamline this process. It comprises three modules: “Retrieval, Matching, and Ranking,” significantly improving the efficiency and accuracy of patient-trial matching. TrialGPT reduces the trial pool by over 90%, matches patient eligibility with 87.3% accuracy, and enhances trial prioritization by 43.8%. Its implementation can expedite recruitment, crucial for time-sensitive research areas, such as oncology. However, challenges such as reliance on proprietary large language models, data privacy, and integration with real-world data persist. As AI technologies continue to advance, TrialGPT exemplifies the potential of AI to revolutionize clinical trials, albeit with caution to ensure ethical standards and patient safety. AI trial matching should be piloted using a combination of AI and human screening, with the aim of improving participant accrual.