Artificial Intelligence is Helping Older Adults

AI for Finding a Clinical Trial for Specific Ailments

Researchers from the National Institutes of Health (NIH) have come up with an AI algorithm to help speed up the process of matching potential volunteers to relevant clinical research trials listed on ClinicalTrials.gov. The AI algorithm, called TrialGPT, may be able to 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. 

This tool could help doctors and their patients navigate the vast and ever-changing range of clinical trials. Researchers hope TrialGPT also may lead to improved clinical trial enrollment and faster progress in medical research. A team of researchers from NIH’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, ranked by relevance and eligibility, that clinicians can use to discuss clinical trial opportunities with their patient.

“Machine learning and AI technology have held promise in matching patients with clinical trials, but their practical application across diverse populations still needed exploration,” said NLM Acting Director, Stephen Sherry. “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.”

But How Can I Trust This?

Everybody, regardless of age, has immense trouble finding reliable information on the Internet. However, optimists believe AI could help solve some of those problems. Dr. Gary Franklin is with the University of Washington and is a research professor of environmental & occupational health sciences and of neurology in the UW School of Medicine in Seattle. In a recently published article, he described a troubling experience with Google’s Gemini chatbot. When Dr. Franklin asked Gemini for information on the outcomes of a specific procedure (a decompressive brachial plexus surgery) the bot gave a detailed answer that cited two medical studies, neither of which existed.  

Dr. Franklin says it’s “buyer beware” when it comes to using AI Chatbots for the purposes of extracting accurate scientific information or evidence-based guidance. He recommends that AI experts develop specialized chatbots that pull information only from verified sources.  

Dr. Franklin and his associates say adults have historically trusted Google search to only index documents that people have written, maybe putting the ones that are more trustworthy at the top. However, that AI-generated response can be full of misinformation. The big concern currently is that many individuals are losing trust in traditional searches, and it is going to be hard to build back trust.

The current chatbots are general-purpose tools, but they are starting to transition and contain mixtures of specific models underneath. In the future, it is hoped that chatbots are going to get better at routing people’s queries to the correct expert models, whether that’s to the model hooked up to PubMed or to trusted documents published by various investigators related to health care. 

Augmented Reality May Help Millions of Older Adults

Augmented reality is an interactive experience. It enhances the real-world with computer-generated perception information. Augmented reality uses software, apps, hardware such as augmented reality glasses. It overlays digital content combined with real-life environments and objects. 

Thanks to new augmented reality, it is now possible to classify older adults in a new way based on their complex age-related conditions (CACs). These include injuries from falls and symptoms of Parkinson’s disease and dementia. 

“My goal is to design innovative, AI-powered personalized tools to help understand and treat the many factors that contribute to CACs and improve the lives of older adults and their caregivers,” said Dr. Mina Nouredanesh, who is an assistant professor of community health sciences at the Max Rady College of Medicine in the Rady Faculty of Health Science in Canada.

Despite many technological advancements in recent years, knowledge gaps persist, including a lack of precise tools to proactively assess individual-level risks associated with CACs. Every case is unique due to the complexity of symptoms or injury experienced by older adults.

There are no effective cures to many CACs, so identifying early signs well in advance of their onset -- or detecting factors that trigger them in those already affected -- is crucial for developing targeted interventions to delay their progression and mitigate impact," says Dr. Nouredanesh. "One-size-fits-all prevention and rehabilitation strategies often fall short because each individual may experience a specific interplay between various risk factors that contribute to the development of these adverse conditions."

Dr. Nouredanesh and her colleagues are using AI to expand personalized medicine and improve diagnostic, prognostic and treatment methods. While AI has shown promise in addressing health problems, she says, it is in the early stages of development when it comes to predicting and managing CACs, such as falling. 

John Schieszer is an award-winning national journalist and radio and podcast broadcaster of The Medical Minute. He can be reached at medicalminutes@gmail.com