According to a study published in Nature Communications, researchers at the National Institutes of Health (NIH) created an artificial intelligence (AI) algorithm to help connect potential volunteers to appropriate clinical research studies listed on ClinicalTrials.gov.
Image Credit: PopTika/Shutterstock.com
The study discovered that TrialGPT, an AI algorithm, could effectively find pertinent clinical trials for which a person qualifies and offer a synopsis that describes in detail how the individual satisfies the requirements for study enrollment.
The researchers concluded that this tool might aid doctors in navigating the wide and constantly evolving array of clinical trials accessible to their patients, perhaps resulting in better clinical trial enrollment and quicker advancements in medical research.
Researchers from the NIH's National Library of Medicine (NLM) and National Cancer Institute used large language models (LLMs) to create an innovative framework for TrialGPT that streamlines clinical trial matching. TrialGPT begins by processing a patient summary, which includes important medical and demographic information.
The algorithm then selects relevant clinical trials from ClinicalTrials.gov for which the patient is eligible while excluding trials for which they are ineligible. TrialGPT then explains how the person satisfies the study’s enrollment criteria. The result is an annotated list of clinical trials, ranked by relevance and eligibility, that physicians can use to discuss clinical trial options with their patients.
Machine learning and AI technology have held promise in matching patients with clinical trials, but their practical application across diverse populations still needed exploration. This study shows we can responsibly leverage AI technology so physicians can connect their patients to a relevant clinical trial that may be of interest to them with even more speed and efficiency.
Stephen Sherry, PhD, Acting Director, National Library of Medicine
To determine how successfully TrialGPT predicted whether a patient met a given requirement for a clinical trial, the researchers compared its results to those of three human clinicians who evaluated over 1,000 patient-criterion pairs. They discovered that TrialGPT had roughly the same degree of accuracy as doctors.
The researchers conducted a pilot user study in which two human clinicians reviewed six anonymous patient summaries and matched them to six clinical trials. For each patient and trial pair, one doctor was requested to manually analyze the patient summaries, determine eligibility, and decide whether the patient would be eligible for the trial.
Another clinician used TrialGPT to determine the patient’s eligibility for the same patient-trial pair. The researchers discovered that doctors spent 40% less time screening patients while maintaining the same degree of accuracy.
Clinical trials find vital medical discoveries that benefit health, and their clinicians often inform potential volunteers about these opportunities. However, locating the correct clinical trial for interested volunteers is a time-consuming and resource-intensive procedure that can impede critical medical research.
Our study shows that TrialGPT could help clinicians connect their patients to clinical trial opportunities more efficiently and save precious time that can be better spent on harder tasks that require human expertise.
Zhiyong Lu, PhD, Study Corresponding Author and Senior Investigator, National Library of Medicine
Given the positive benchmarking results, the research team was recently selected for The Director’s Challenge Innovation Award, allowing them to evaluate the model’s effectiveness and fairness in real-world clinical settings.
The researchers believe that this study will improve clinical trial recruitment and lower obstacles to participation for underrepresented populations in clinical research.
Researchers from Albert Einstein College of Medicine in New York City, the University of Pittsburgh, the University of Illinois Urbana-Champaign, and the University of Maryland, College Park, co-authored the study.
NIH-Developed AI Algorithm Successfully Matches Potential Volunteers to Clinical Trials Release
Video Credit: National Library of Medicine
Journal Reference:
Jin, Q. et.al. (2024) Matching patients to clinical trials with large language models. Nature Communications. doi.org/10.1038/s41467-024-53081-z