news release
Monday, November 18, 2024
Such algorithms have the potential to save clinicians time and accelerate clinical enrollment and research.
National Institutes of Health (NIH) researchers have developed an artificial intelligence (AI) algorithm to help speed the process of matching potential volunteers to relevant clinical research trials listed on ClinicalTrials.gov. did. In the study published in Nature Communications, an AI algorithm called TrialGPT identifies relevant clinical trials for which a person is eligible and clearly explains how the person meets the criteria for study enrollment. I found that I can provide an overview. Researchers say this tool will help clinicians navigate the vast and ever-changing number of clinical trials available to patients, thereby improving clinical trial enrollment and leading to faster advances in medical research. concluded that it is possible.
A team of researchers from the NIH’s National Library of Medicine (NLM) and the National Cancer Institute has developed TrialGPT’s innovative framework to streamline the clinical trial matching process by harnessing the power of large-scale language models (LLMs). I have developed a work. TrialGPT first processes a patient summary, including relevant medical and demographic information. The algorithm then identifies relevant clinical trials from ClinicalTrials.gov that the patient is eligible to participate in and filters out those in which the patient is ineligible. TrialGPT then explains how the person meets the study enrollment criteria. The final output is an annotated list of clinical trials ranked by relevance and eligibility, which clinicians can use to discuss clinical trial opportunities with patients.
“Machine learning and AI technologies hold promise in matching patients to clinical trials, but their practical application to diverse populations remains to be explored,” said Dr. Stephen Sherry, NLM Acting Director. “This study shows that we can responsibly leverage AI technology to help physicians more quickly and efficiently connect patients to relevant clinical trials of interest.”
To assess how accurately TrialGPT predicted whether a patient met specific requirements for a clinical trial, researchers evaluated TrialGPT results for more than 1,000 patient-criteria pairs. The results of three clinicians were compared. They found that TrialGPT achieved nearly the same level of accuracy as clinicians.
Additionally, the researchers conducted a pilot user study, asking two clinicians to review six anonymous patient summaries and match them to six clinical trials. For each patient and trial pair, one clinician will be asked to manually review the patient’s summary, confirm whether the person is eligible, and determine whether the patient can participate in the trial. I did. For the same patient-trial pair, another clinician assessed patient eligibility using TrialGPT. Researchers found that using TrialGPT, clinicians could spend 40% less time screening patients while maintaining the same level of accuracy.
Clinical trials reveal important medical discoveries that improve health, and prospective participants often learn about these opportunities through their clinicians. However, finding appropriate clinical trials for interested participants is a time- and resource-intensive process that can delay important medical research.
“Our research shows that TrialGPT can help clinicians connect patients to clinical trial opportunities more efficiently, saving valuable time and making it more effective for more difficult tasks that require human expertise. ,” said Zhiyong Lu, senior investigator at NLM and corresponding author of the study. Ph.D.
Given the promising benchmarking results, the research team was recently selected for the Director’s Challenge Innovation Award, which further evaluates the model’s performance and fairness in real-world clinical settings. Researchers hope this effort could make clinical trial recruitment more effective and reduce barriers to participation for underrepresented populations in clinical research.
The study was co-authored by collaborators at Albert Einstein College of Medicine in New York City. University of Pittsburgh; University of Illinois at Urbana-Champaign. and the University of Maryland, College Park.
NLM is a leader in biomedical informatics and data science research and the world’s largest biomedical library. NLM conducts and supports research into how health information is recorded, stored, retrieved, preserved, and communicated. NLM creates resources and tools used by millions of people billions of times each year to access and analyze molecular biology, biotechnology, toxicology, environmental health, and health services information. Masu. Additional information is available at https://www.nlm.nih.gov.
About the National Institutes of Health (NIH): The nation’s medical research agency, NIH includes 27 institutes and centers and is part of the U.S. Department of Health and Human Services. NIH is the primary federal agency that conducts and supports basic, clinical, and translational medical research, investigating the causes, treatments, and cures for both common and rare diseases. For more information about NIH and its programs, please visit www.nih.gov.
NIH…Turning discovery into health®
reference
Matching patients to clinical trials using large-scale language models. Nature Communications. DOI: 10.1038/s41467-024-53081-z. (2024).
