In a groundbreaking development, researchers have unveiled a digital artificial intelligence (AI) tool that detects dementia without incurring extra costs or requiring additional clinician time. This innovation, tested across primary care clinics, promises to transform the timely detection of Alzheimer’s disease and related dementias, a process that has historically been fraught with challenges.
The announcement comes as primary care practices struggle with limited time and resources to address dementia, often overshadowed by more immediate health concerns. The stigma surrounding Alzheimer’s disease further complicates early recognition and diagnosis. However, the new AI method, developed by the Regenstrief Institute and its partners, offers a scalable solution that could significantly enhance early detection rates.
Revolutionizing Dementia Detection
In a pragmatic real-world randomized clinical trial involving over 5,000 patients, researchers from institutions including the Indiana University School of Medicine and the University of Miami School of Medicine tested a dual approach. This method combined the Quick Dementia Rating System (QDRS), a 10-question patient-reported tool, with an AI tool known as a passive digital marker. The results were remarkable, showing a 31 percent increase in new diagnoses of Alzheimer’s and related dementias compared to usual care, all without demanding additional clinician time or expensive testing.
The AI tool, a decade in the making at the Regenstrief Institute by Dr. Malaz Boustani and his team, utilizes a machine learning algorithm that processes data from electronic health records (EHRs). It identifies markers such as memory issues and vascular concerns linked to dementia.
“Building on more than 50 years of innovation in digital health data science and machine learning, this passive digital marker developed at the Regenstrief Institute is now open source,” said Dr. Boustani. “In keeping with Regenstrief’s tradition of open medical record methodology, there’s no licensing fee — just the basic cost of deploying it, similar to how you would deploy any app.”
Implications for Healthcare Systems
Beyond increasing detection rates, this combined digital approach also led to a 41 percent rise in follow-up diagnostic assessments, such as neuroimaging and cognitive testing. This suggests that the method could facilitate earlier and more accessible dementia care for populations traditionally underserved by the healthcare system.
Dr. Boustani emphasized the scalability of this approach, noting that most early detection methods require clinician time and often involve licensing fees. “Our dual approach, by contrast, requires zero clinician time or money,” he stated.
The trial was conducted at nine Eskenazi Health Center federally qualified health centers in Indianapolis. The QDRS and passive digital marker were embedded directly into the Epic EHR system, automatically inviting patients aged 65 and older to complete the QDRS survey through their patient portal. The passive digital marker algorithm continuously analyzed existing clinical data to flag patients at risk, with results appearing automatically in the clinician’s EHR inbox.
“What’s powerful about this approach is that it helps level the playing field,” said Zina Ben Miled, PhD, a Regenstrief affiliate scientist. “By embedding these tools directly into the electronic health record, we can reach patients who might otherwise be overlooked.”
Future Prospects and Broader Impact
This breakthrough represents a significant step forward in integrating AI and patient-reported outcomes into everyday clinical care. By embedding scalable digital tools within existing health systems, the research team has demonstrated how technology can enhance early detection, reduce burdens on primary care teams, and improve outcomes for older adults.
Dr. James E. Galvin, a professor of neurology at the University of Miami, highlighted the potential of combining the QDRS with digital tools like the Regenstrief passive digital marker. “We can bring early detection to scale — efficiently and effectively,” he said.
The study, “Digital Detection of Dementia in Primary Care: A Randomized Clinical Trial,” is published in JAMA Network Open. Supported by grants from the National Institutes of Health’s National Institute on Aging, this research underscores the potential of AI in transforming healthcare delivery.
“This work represents the next phase of our half-century legacy at Regenstrief — using data, innovation, and compassion to transform healthcare delivery,” said Dr. Boustani. “We’ve shown that it’s possible to bring the power of AI and patient-reported outcomes directly into the clinic — seamlessly, affordably, and at scale.”
As healthcare systems worldwide grapple with aging populations and increasing dementia cases, this AI tool offers a promising avenue for early detection and intervention, potentially reshaping the landscape of dementia care.
