How Mayo Clinic uses real-world data to advance precision medicine

Mayo Clinic physicians are beginning to explore how they can use healthcare-specific large language models – accessed through a generative artificial intelligence chat application – to improve patient care and improve clinical decisions.

While in healthcare ChatGPT and Google Gemini can only deliver relevant, evidence-based answers a fraction of the time, California-based Atropos Health says its federated healthcare data network can provide healthcare users with detailed, accurate advice for even the most obscure medical questions because it is based only on peer-reviewed, practice-oriented data.

For example, when doctors consider how to treat a patient with an unusual genetic condition that predisposes them to a certain heart disease, using data from millions of patients to identify similar patients and learn about their outcomes can help inform treatment, according to Dr. . Peter Noseworthy, chairman of cardiac electrophysiology at Mayo Clinic.

Last year, Atropos launched a generative AI-enhanced platform that allows users to query their wealth of clinical data. It claimed it had become the largest healthcare data network in the US in June. Recently, the company released its chat-based interface, ChatRWD.

“This is a way to interact with real-world data in real time and then surface those insights at the point of care,” Noseworthy, who leads control trials and research using national datasets, told ChatRWD Testing . Healthcare IT news on Friday.

Scoring healthcare-specific data reliability

Atropos’ platform offers a Real World Data Score – a moment-in-time snapshot of data quality measured by size, completeness, patient timelines and more – and a Real World Fitness Score – based on a proprietary algorithm that takes into account how well the demand criteria are represented within the dataset – for each dataset.

These ratings can help users select the dataset most suitable to answer all their questions on the platform, the company said in June.

Saurabh Gombar, adjunct faculty at Stanford Healthcare and chief medical officer at Atropos, said he led a study that analyzed the accuracy and efficacy of five LLMs, including healthcare-specific OpenEvidence and ChatRWD, to examine the accuracy and efficacy of model outcomes.

Looking at reliability, the general-purpose LLMs fell far short of answering physicians’ questions, he said.

“While OpenEvidence and ChatRWD were able to produce useful, reliable evidence 42% or 60% of the time – a whole magnitude greater than the general purpose LLMs,” Gombar told Healthcare IT news in July.

Since 2022, Atropos has been working with Mayo Clinic testing and development data-driven methods that can improve healthcare – both techniques and improving care delivery to historically underrepresented patients – by offering real-world evidence the new one through automated reports called Prognostograms.

The collaboration allowed clinicians and researchers to access Mayo Clinic’s anonymized data repository and analytical tools on Atropos’ digital consultation platform.

“This is a way to interact with real-world data in real time and then surface those insights at the point of care.”

Dr. Peter Noseworthy, Mayo Clinic

For patients in critical care, the ability of their care teams to find answers to research questions through the platform can save time. While it may take many weeks to determine treatment with traditional means, AI-powered prognosis can be completed within days, according to Atropos.

Noseworthy noted that observational clinical researchers have access to large real-world data, “but the timeline to generate insights from it is months.” They not only need to retrieve data, but also clean and analyze it.

“You need a statistician to work with,” he said.

“With a tool like this that can essentially set up these studies in real time and pull that data, you can get pretty close to research-quality or publication-quality information through a chat interface.”

Atropos said it expects more than 200% growth in the availability of additional data sets in the coming year.

The power of patient data emerges with AI

While experienced physicians can recognize patterns in patient outcomes and responses to treatments based on experience, capturing the totality of the experience with a drug or treatment – ​​’the gestalt of patient outcomes’ – is limited by traditional modalities of medical research , Noseworthy explains.

“We could achieve that with clinical trials, but that is a slow process and patients are highly selected.”

However, LLMs can provide doctors with faster answers to medical questions, and that can help improve treatments for patients that have historically been beyond the reach of clinical trials.

“Rare or unusual disease presentations or rare conditions or a rare co-occurrence of conditions are not well characterized in clinical trials, but they are present in a large data sample,” Noseworthy said.

Mayo Clinic has been working to expand the boundaries of clinical trials beyond the walls of major academic medical centers, through a decentralized clinical trial program last year.

Access to clinical trials has exacerbated health disparities, according to Dr. Tufia Haddad, a medical oncologist, chair of faculty development for the Mayo Clinic Department of Oncology and co-lead of the clinic’s Comprehensive Cancer Center Office of Platform and Digital Innovation.

“We have an underrepresentation of racial-ethnic minority and patient populations in our processes, as well as an underrepresentation of those in underserved rural communities,” she said.

The overarching goal of improving access to clinical trials is to “bring more treatments to more people,” she said Healthcare IT news after the program was launched.

While some practices within the Mayo Clinic have tested ChatRWD, Noseworthy said he became interested because colleagues in his heart group have experience using real-world data from other data engines.

“It was attractive to me that we could actually generate the data in real time and at the point of care,” he said.

Using real-world clinical data – “it’s very different than just using ChatGBT” or other LLMs.

Although ChatRWD has yet to be widely deployed at Mayo Clinic, “it has been able to give us some interesting insight,” Noseworthy said.

Andrea Fox is editor-in-chief of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.