nih-gov/www.nlm.nih.gov/news/AI_algorithm_volunteers_clinical_trials.html
2025-02-26 13:17:41 -05:00

311 lines
24 KiB
HTML
Raw Permalink Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

<!doctype html>
<html lang="en">
<head>
<meta name="title" property="og:title" content="NIH-developed AI algorithm matches potential volunteers to clinical trials">
<meta name="type" property="og:type" content="website">
<meta name="description" property="og:description" content="Learn about the latest happenings at the worlds largest biomedical library.">
<meta name="image" property="og:image" content="https://www.nlm.nih.gov/images/NLMgeneric.jpg">
<meta name="image:alt" property="og:image:alt" content="National Library of Medicine (NLM)">
<meta name="twitter:card" content="summary_large_image">
<meta name="twitter:site" content="@NLM_NIH">
<meta name="twitter:title" content="NIH-developed AI algorithm matches potential volunteers to clinical trials">
<meta name="twitter:description" content="Learn about the latest happenings at the worlds largest biomedical library.">
<meta name="twitter:image" content="https://www.nlm.nih.gov/images/NLMgeneric.jpg">
<meta name="twitter:image:alt" content ="National Library of Medicine (NLM)">
<meta name="NLM.Contact.Email" content="NLMCommunications@nlm.nih.gov" />
<title>NIH-developed AI algorithm matches potential volunteers to clinical trials</title>
<meta name="viewport" content="width=device-width, initial-scale=1, shrink-to-fit=no">
<meta http-equiv="X-UA-Compatible" content="IE=edge" />
<meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
<meta http-equiv="X-UA-Compatible" content="IE=edge,chrome=1"/>
<link rel="preconnect" href="https://fonts.googleapis.com">
<link rel="preconnect" href="https://fonts.gstatic.com" crossorigin>
<link href="https://fonts.googleapis.com/css2?family=Roboto:wght@100;300;400;500;700&display=swap" rel="stylesheet">
<link rel="stylesheet" href="https://use.fontawesome.com/releases/v5.0.10/css/all.css" integrity="sha384-+d0P83n9kaQMCwj8F4RJB66tzIwOKmrdb46+porD/OvrJ+37WqIM7UoBtwHO6Nlg" crossorigin="anonymous">
<link rel="schema.DC" href="http://purl.org/dc/elements/1.1/" title="The Dublin Core metadata Element Set" />
<meta name="DC.Title" content="National Library of Medicine - National Institutes of Health" />
<meta name="DC.Publisher" content="U.S. National Library of Medicine" />
<meta name="DC.Language" content="eng" />
<!--<meta name="keywords" content="National Library of Medicine, MEDLINE, LocatorPlus, MedlinePlus, NLM, Index Medicus, UMLS, Unified Medical Language System, Mesh, Medical Subject Headings, Visible Human, PubMed, PubMed Central, ClinicalTrials, TOXNET, Digital Collections, DailyMed, AccessGUDID, Genetics Home Reference" />
<meta name="description" content="The National Library of Medicine (NLM), on the NIH campus in Bethesda, Maryland, is the world's largest biomedical library and the developer of electronic information services that delivers data to millions of scientists, health professionals and members of the public around the globe, every day. " /> -->
<link rel="stylesheet" href="/home_assets/uswds/css/styles.css">
<!-- Google Tag Manager --><script>(function(w,d,s,l,i){w[l]=w[l]||[];w[l].push(
{'gtm.start': new Date().getTime(),event:'gtm.js'}
);var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-MT6MLL');</script> <!-- End Google Tag Manager -->
</head>
<body>
<!-- TOP NAV -->
<a class="usa-skipnav" href="#main">Skip to main content</a>
<div class="usa-banner site-banner" aria-label="Official government website">
<div class="usa-accordion">
<header class="usa-banner__header">
<div class="usa-banner__inner">
<div class="grid-col-auto"> <img
class="usa-banner__header-flag"
src="https://assets.nlm.nih.gov/uswds/img/us_flag_small.png"
alt="U.S. flag"
/> </div>
<div class="grid-col-fill tablet:grid-col-auto">
<p class="usa-banner__header-text"> An official website of the United States government </p>
<p class="usa-banner__header-action" aria-hidden="true"> Here's how you know </p>
</div>
<button
class="usa-accordion__button usa-banner__button"
aria-expanded="false"
aria-controls="gov-banner"
> <span class="usa-banner__button-text">Here's how you know</span> </button>
</div>
</header>
<div class="usa-banner__content usa-accordion__content" id="gov-banner">
<div class="grid-row grid-gap-lg">
<div class="usa-banner__guidance tablet:grid-col-6"> <img
class="usa-banner__icon usa-media-block__img"
src="https://assets.nlm.nih.gov/uswds/img/icon-dot-gov.svg"
role="img"
alt=""
aria-hidden="true"
/>
<div class="usa-media-block__body">
<p> <strong> Official websites use .gov </strong> <br />
A <strong>.gov</strong> website belongs to an official government
organization in the United States. </p>
</div>
</div>
<div class="usa-banner__guidance tablet:grid-col-6"> <img
class="usa-banner__icon usa-media-block__img"
src="https://assets.nlm.nih.gov/uswds/img/icon-https.svg"
role="img"
alt=""
aria-hidden="true"
/>
<div class="usa-media-block__body">
<p> <strong> Secure .gov websites use HTTPS </strong> <br />
A <strong>lock</strong> ( <span class="icon-lock"
>
<svg
xmlns="http://www.w3.org/2000/svg"
width="52"
height="64"
viewBox="0 0 52 64"
class="usa-banner__lock-image"
role="img"
aria-labelledby="banner-lock-title-default banner-lock-description-default"
focusable="false"
>
<title id="banner-lock-title-default">Lock</title>
<desc id="banner-lock-description-default">A locked padlock</desc>
<path
fill="#000000"
fill-rule="evenodd"
d="M26 0c10.493 0 19 8.507 19 19v9h3a4 4 0 0 1 4 4v28a4 4 0 0 1-4 4H4a4 4 0 0 1-4-4V32a4 4 0 0 1 4-4h3v-9C7 8.507 15.507 0 26 0zm0 8c-5.979 0-10.843 4.77-10.996 10.712L15 19v9h22v-9c0-6.075-4.925-11-11-11z"
/>
</svg
>
</span> ) or <strong>https://</strong> means youve safely connected to
the .gov website. Share sensitive information only on official,
secure websites. </p>
</div>
</div>
</div>
</div>
</div>
</div>
<!-- HEADER -->
<header id="siteheader" class="usa-header usa-header--basic">
<div class="usa-nav-container tablet:padding-x-4 mobile-lg:padding-x-2 padding-y-1">
<div class="grid-row padding-y-105">
<div class="grid-col-8 desktop:grid-col-4 tablet-lg:grid-col-4 tablet:grid-col-6"> <a href="https://www.nlm.nih.gov/"> <img src="https://assets.nlm.nih.gov/uswds/img/NLM_White.png" alt="NLM logo" class="logo margin-top-1"> </a> </div>
<div class="desktop:grid-col-4 desktop:grid-offset-4 tablet-lg:grid-col-6 tablet-lg:grid-offset-2 tablet:grid-col-6 grid-col-12">
<form class="usa-search desktop:margin-top-2 tablet:margin-top-2 mobile:margin-top-1" role="search" data-gtm-form-interact-id="0" method="get" action="//vsearch.nlm.nih.gov/vivisimo/cgi-bin/query-meta" target="_self" name="searchForm" id="searchForm2">
<input class="usa-input ui-autocomplete-input" aria-label="Search" type="search" name="query" data-gtm-form-interact-field-id="0" id="search2" placeholder="Search NLM" autocomplete="off">
<input type="hidden" name="v:project" value="nlm-main-website">
<button class="usa-button border border-top border-bottom border-right border-white" role="button" aria-label="Search" alt="Search" type="submit"> <span class="usa-search__submit-text"> <i class="fas fa-search"></i> </span> </button>
</form>
</div>
</div>
</div>
</header>
<div class="bg-secondary insertCOOP">
<div class="usa-nav-container">
<div class="usa-navbar ">
<button class="usa-menu-btn">Menu</button>
</div>
<nav aria-label="Primary navigation" class="usa-nav">
<button class="usa-nav__close"><img src="https://assets.nlm.nih.gov/uswds/img/close.svg" alt="close"></button>
<ul class="usa-nav__primary usa-accordion insertNav">
<li class="usa-nav__primary-item desktop-lg:margin-x-5 desktop:margin-x-3 tablet:margin-x-0">
<button type="button" class="usa-accordion__button usa-nav__link usa-current" aria-expanded="false" aria-controls="basic-nav-section-one"> <span>Products and Services <i class="fas fa-caret-down margin-left-05"></i> </span> </button>
<ul id="basic-nav-section-one" class="usa-nav__submenu bg-secondary" hidden="">
<li class="usa-nav__submenu-item"> <a href="//eresources.nlm.nih.gov/nlm_eresources/"><span>All Products and Services</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="//clinicaltrials.gov/"><span>ClinicalTrials.gov</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="//collections.nlm.nih.gov/"><span>Digital Collections</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="//catalog.nlm.nih.gov"><span>LocatorPlus Catalog</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="//meshb.nlm.nih.gov/search"><span>Medical Subject Headings (MeSH)</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="//medlineplus.gov/"><span>MedlinePlus</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="//pubmed.ncbi.nlm.nih.gov/"><span>PubMed/MEDLINE</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="//uts.nlm.nih.gov/uts/"><span>Unified Medical Language System (UMLS)</span></a> </li>
</ul>
</li>
<li class="usa-nav__primary-item desktop-lg:margin-x-5 desktop:margin-x-3 tablet:margin-x-0">
<button type="button" class="usa-accordion__button usa-nav__link usa-current" aria-expanded="false" aria-controls="basic-nav-section-two"> <span> Resources for You <i class="fas fa-caret-down margin-left-05"></i></span> </button>
<ul id="basic-nav-section-two" class="usa-nav__submenu bg-secondary" hidden="">
<li class="usa-nav__submenu-item"> <a href="/portals/researchers.html"><span>For Researchers</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/portals/publishers.html "><span>For Publishers</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/portals/librarians.html"><span>For Librarians</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/training.html "><span>For Educators/Trainers </span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/portals/healthcare.html"><span>For Health care Professionals</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/portals/public.html "><span>For the Public</span></a> </li>
</ul>
</li>
<li class="usa-nav__primary-item desktop-lg:margin-x-5 desktop:margin-x-3 tablet:margin-x-0">
<button type="button" class="usa-accordion__button usa-nav__link usa-current" aria-expanded="false" aria-controls="basic-nav-section-three"> <span>Explore NLM <i class="fas fa-caret-down margin-left-05"></i> </span> </button>
<ul id="basic-nav-section-three" class="usa-nav__submenu bg-secondary" hidden="">
<li class="usa-nav__submenu-item"> <a href="/about/index.html"><span>About the Library</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/about/visitor.html"><span>Visit the Library</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/hmd/index.html"><span>History of Medicine</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/about/org.html"><span>NLM by Organization</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/news/newsandevents.html"><span>News, Events, and Updates</span></a> </li>
</ul>
</li>
<li class="usa-nav__primary-item desktop-lg:margin-x-5 desktop:margin-x-3 tablet:margin-x-0">
<button type="button" class="usa-accordion__button usa-nav__link usa-current" aria-expanded="false" aria-controls="basic-nav-section-four"> <span> Grants and Research <i class="fas fa-caret-down margin-left-05"></i> </span> </button>
<ul id="basic-nav-section-four" class="usa-nav__submenu bg-secondary" hidden="">
<li class="usa-nav__submenu-item"> <a href="/ep/index.html"><span>NLM Extramural Programs</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="/research/index.html"><span>NLM Division of Intramural Research</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="https://www.ncbi.nlm.nih.gov/"><span>National Center for Biotechnology Information</span></a> </li>
<li class="usa-nav__submenu-item"> <a href="//lhncbc.nlm.nih.gov/"><span>Lister Hill National Center for Biomedical Communications</span></a> </li>
</ul>
</li>
</ul>
</nav>
</div>
</div>
<!-- End of TOP NAV -->
<!-- Breadcrumbs -->
<div class="grid-container">
<nav class="usa-breadcrumb usa-breadcrumb--wrap padding-top-1" aria-label="Breadcrumbs">
<ol class="usa-breadcrumb__list">
<li class="usa-breadcrumb__list-item"> <a href="/" class="usa-breadcrumb__link"><span>Home</span></a></li>
<li class="usa-breadcrumb__list-item"> <a href="/news/newsandevents.html" class="usa-breadcrumb__link"><span>News, Events, and Updates</span></a></li>
</ol>
</nav>
</div>
<!-- End Breadcrumbs -->
<main id="main" class="padding-bottom-5">
<div class="grid-container">
<div class="grid-row">
<div class="grid-col">
<h1>NIH-developed AI algorithm matches potential volunteers to clinical trials</h1>
<h2><em>Such an algorithm may save clinicians time and accelerate clinical enrollment and research</em></h2>
</div>
</div>
<div class="grid-row">
<div class="grid-col">
<small>November 18, 2024</small><br/><br/>
<p>Researchers from the National Institutes of Health (NIH) have developed an artificial intelligence (AI) algorithm to help speed up the process of matching potential volunteers to relevant clinical research trials listed on <a href="https://clinicaltrials.gov/">ClinicalTrials.gov</a>. A study published in <a href="https://www.nature.com/articles/s41467-024-53081-z"><em>Nature Communications</em></a> found that the AI algorithm, called TrialGPT, could successfully identify relevant clinical trials for which a person is eligible and provide a summary that clearly explains how that person meets the criteria for study enrollment. The researchers concluded that this tool could help clinicians navigate the vast and ever-changing range of clinical trials available to their patients, which may lead to improved clinical trial enrollment and faster progress in medical research.</p>
<div class="float-right mobile:grid-col-12 desktop:grid-col-4 padding-left-2">
<div><a title="" href="https://www.youtube.com/embed/Sys9Ki6t4DQ?autoplay=1" rel="shadowbox[gallery];"><img src="https://www.nih.gov/sites/default/files/styles/video_sidebar/public/media-youtube/Sys9Ki6t4DQ.jpg?itok=Xi7SIHil" alt="Photo of Dr. Lu presenting the framework for TrialGPT" /></a></div>
</div>
<p>A team of researchers from NIH&rsquo;s National Library of Medicine (NLM) and National Cancer Institute harnessed the power of large language models (LLMs) to develop an innovative framework for TrialGPT to streamline the clinical trial matching process. TrialGPT first processes a patient summary, which contains relevant medical and demographic information. The algorithm then identifies relevant clinical trials from ClinicalTrials.gov for which a patient is eligible and excludes trials for which they are ineligible. TrialGPT then explains how the person meets the study enrollment criteria. The final output is an annotated list of clinical trials&mdash;ranked by relevance and eligibility&mdash;that clinicians can use to discuss clinical trial opportunities with their patient.</p>
<p>&ldquo;Machine learning and AI technology have held promise in matching patients with clinical trials, but their practical application across diverse populations still needed exploration,&rdquo; said NLM Acting Director, Stephen Sherry, PhD. &ldquo;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.&rdquo;</p>
<p>To assess how well TrialGPT predicted if a patient met a specific requirement for a clinical trial, the researchers compared TrialGPT&rsquo;s results to those of three human clinicians who assessed over 1,000 patient-criterion pairs. They found that TrialGPT achieved nearly the same level of accuracy as the clinicians.</p>
<p>Additionally, the researchers conducted a pilot user study, where they asked two human clinicians to review six anonymous patient summaries and match them to six clinical trials. For each patient and trial pair, one clinician was asked to manually review the patient summaries, check if the person was eligible, and decide if the patient might qualify for the trial. For the same patient-trial pair, another clinician used TrialGPT to assess the patient&rsquo;s eligibility. The researchers found that when clinicians use TrialGPT, they spent 40% less time screening patients but maintained the same level of accuracy.</p>
<p>Clinical trials uncover important medical discoveries that improve health, and potential participants often learn about these opportunities through their clinicians. However, finding the right clinical trial for interested participants is a time-consuming and resource-intensive process, which can slow down important medical research.</p>
<p>&ldquo;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,&rdquo; said NLM Senior Investigator and corresponding author of the study, Zhiyong Lu, PhD.</p>
<p>Given the promising benchmarking results, the research team was recently selected for The<a href="https://oir.nih.gov/sourcebook/awards-fellowships-grant-opportunities/directors-challenge-innovation-award-program/2024-directors-challenge-awards#2024-directors-lu"> Director&rsquo;s Challenge Innovation Award</a> to further assess the model&rsquo;s performance and fairness in real-world clinical settings. The researchers anticipate that this work could make clinical trial recruitment more effective and help reduce barriers to participation for populations underrepresented in clinical research.</p>
<p>The study was co-authored by collaborators from Albert Einstein College of Medicine, New York City; University of Pittsburgh; University of Illinois Urbana-Champaign; and University of Maryland, College Park.</p>
<p>See also: <a href="https://www.nih.gov/news-events/news-releases/nih-developed-ai-algorithm-matches-potential-volunteers-clinical-trials">NIH news release</a> on this research.</p>
<p>Reference: Qiao Jin, et al. <strong>Matching Patients to Clinical</strong> <strong>Trials with</strong> <strong>Large Language Models</strong>. <em>Nature Communications</em>. DOI: 10.1038/s41467-024-53081-z. (2024).</p>
<p><em>NLM is a leader in research in biomedical informatics and data science and the world&rsquo;s largest biomedical library. NLM conducts and supports research in methods for recording, storing, retrieving, preserving, and communicating health information. NLM creates resources and tools that are used billions of times each year by millions of people to access and analyze molecular biology, biotechnology, toxicology, environmental health, and health services information. Additional information is available at</em><em></em><a href="https://www.nlm.nih.gov/"><em>https://www.nlm.nih.gov/</em></a><em>.</em></p>
</div>
</div>
</div>
</main>
<!-- FOOTER -->
<footer class="usa-footer__primary-section padding-top-5 padding-bottom-3 insertfooter">
<div class="container-fluid">
<div class="container pt-5">
<div class="row mt-3">
<div class="col-md-3 col-sm-6 col-6">
<p class="mb-0"><a href="https://www.nlm.nih.gov/socialmedia/index.html" class="text-white">Connect with NLM</a></p>
<ul class="list-inline">
<li class="list-inline-item me-2 social_media"><a title="External link: please review our privacy policy." href="https://www.facebook.com/nationallibraryofmedicine"><img src="//www.nlm.nih.gov/images/facebook.svg" class="img-fluid bg-secondary" alt="Facebook"></a></li>
<li class="list-inline-item me-2 social_media"><a title="External link: please review our privacy policy." href="https://www.linkedin.com/company/national-library-of-medicine-nlm/"><img src="//www.nlm.nih.gov/images/linkedin.svg" class="img-fluid bg-secondary" alt="LinkedIn"></a></li>
<li class="list-inline-item me-2 social_media"><a title="External link: please review our privacy policy." href="https://twitter.com/NLM_NIH"><img src="//www.nlm.nih.gov/images/twitter.svg" class="p-2 bg-secondary" alt="Twitter"></a></li>
<li class="list-inline-item me-2 social_media"><a title="External link: please review our privacy policy." href="https://www.youtube.com/user/NLMNIH"><img src="//www.nlm.nih.gov/images/youtube.svg" class="img-fluid bg-secondary" alt="You Tube"></a></li>
<li class="list-inline-item me-2 social_media"><a title="External link: please review our privacy policy." href="https://public.govdelivery.com/accounts/USNLMOCPL/subscriber/new?preferences=true"><img src="//www.nlm.nih.gov/images/mail.svg" class="img-fluid bg-secondary" alt="Government Delivery"></a></li>
</ul>
</div>
<div class="col-md-3 col-sm-6 col-6">
<p class="address_footer text-white"> National Library of Medicine <br>
<a href="https://www.google.com/maps/place/8600+Rockville+Pike,+Bethesda,+MD+20894/@38.9959508,-77.101021,17z/data=!3m1!4b1!4m5!3m4!1s0x89b7c95e25765ddb:0x19156f88b27635b8!8m2!3d38.9959508!4d-77.0988323" class="text-white"> 8600 Rockville Pike <br>
Bethesda, MD 20894 </a></p>
</div>
<div class="col-md-3 col-sm-6 col-6">
<p><a href="https://www.nlm.nih.gov/web_policies.html" class="text-white"> Web Policies </a><br>
<a href="https://www.nih.gov/institutes-nih/nih-office-director/office-communications-public-liaison/freedom-information-act-office" class="text-white"> FOIA </a><br><a href="https://www.hhs.gov/vulnerability-disclosure-policy/index.html" class="text-white">HHS Vulnerability Disclosure</a></p>
</div>
<div class="col-md-3 col-sm-6 col-6">
<p><a class="supportLink text-white" href="//support.nlm.nih.gov?from="> NLM Support Center </a> <br>
<a href="https://www.nlm.nih.gov/accessibility.html" class="text-white"> Accessibility </a><br>
<a href="https://www.nlm.nih.gov/careers/careers.html" class="text-white"> Careers </a></p>
</div>
</div>
<div class="row">
<div class="col-lg-12">
<p class="mt-2 text-center text-white"> <a class="text-white" href="//www.nlm.nih.gov/">NLM</a> | <a class="text-white" href="https://www.nih.gov/">NIH</a> | <a class="text-white" href="https://www.hhs.gov/">HHS</a> | <a class="text-white" href="https://www.usa.gov/">USA.gov</a></p>
</div>
</div>
</div>
</div>
</footer>
<script src="//assets.nlm.nih.gov/uswds/js/uswds.min.js"></script>
<script src="//assets.nlm.nih.gov/jquery/jquery-latest.min.js"></script>
<script src="//assets.nlm.nih.gov/jquery/jquery-migrate-latest.min.js"></script>
<script src="/scripts/nlm_autocomplete.js"></script>
<script src="/scripts/nlm_uswds.js"></script>
</body>
</html>