No-cost, AI-based digital detection identifies Alzheimer’s disease without additional clinician time

Few primary care practices are designed to rapidly detect Alzheimer’s disease and related dementias. The limited time that primary care clinicians can spend with patients, the need to focus on the health issues that brought the patient to the clinic, and the stigma associated with Alzheimer’s disease and dementia are the main reasons for the lack of recognition of this disease.

In a real clinical trial, published in Open JAMA NetworkResearchers demonstrate that a free, fully digital AI method for detecting dementia can be scaled up to primary care clinics without additional physician time.

For the trial of more than 5,000 patients from primary care practices, researchers from the Regenstrief Institute, Indiana University School of Medicine, Eskenazi Health, University of Miami School of Medicine and Lamar University tested a dual approach combining the Rapid Dementia Rating System (QDRS) – a 10-question patient-reported tool – and an artificial intelligence tool (IA), called passive digital marker.

The method of combining these tools increased the rate of new diagnoses of Alzheimer’s disease and related dementias by 31% compared to usual care, all without requiring additional clinician time or costly testing.

The AI ​​tool, developed for more than 10 years at Regenstrief by researcher Malaz Boustani, MD, MPH, and his team, is a machine learning algorithm that uses natural language processing to analyze data from electronic health records (EHRs). It identifies information such as memory problems, vascular problems and other factors related 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, a faculty member at Regenstrief and the IU School of Medicine.

“In keeping with Regenstrief’s tradition of open health record methodology, there are no licensing fees, just the base cost of deploying it, similar to that of any application. Any health system with an electronic health record and the appropriate staff can implement it. It’s zero and requires no clinician time.

Beyond increased screening, the combined digital approach also led to a 41% increase in follow-up diagnostic assessments, such as neuroimaging and cognitive testing, suggesting earlier and more accessible dementia care for populations traditionally underserved by the healthcare system.

“This is the most scalable early detection approach that I know of,” said Dr. Boustani, lead author of the clinical trial on digital detection of dementia in primary care. “Most early detection methods require at least five minutes of a physician’s time and often come with licensing fees. Our dual approach, in contrast, requires no clinician time or money.”

The trial, conducted at nine federally qualified health centers in Indianapolis, integrated QDRS and the passive digital marker directly into the Epic electronic health record. The system automatically prompted patients aged 65 and older to complete the short QDRS survey through their patient portal, while the passive digital marker algorithm continuously analyzed existing clinical data to flag patients at risk. Results automatically appeared in the clinician’s EHR inbox, prompting further assessment only when necessary, without requiring additional time, staff, or manual screening.

“What’s powerful about this approach is that it helps level the playing field,” said Zina Ben Miled, Ph.D., a Regenstrief affiliated scientist and professor at Lamar University, who developed the passive digital marker tool alongside Dr. Boustani. “By integrating these tools directly into the electronic health record, we can reach patients who might otherwise be overlooked, ensuring that everyone, regardless of background or resources, has the same opportunity for early detection and care.” »

“The Rapid Dementia Assessment System was designed to allow patients and their families to easily and quickly report cognitive changes,” said James E. Galvin, MD, MPH, professor of neurology and director of the Comprehensive Center for Brain Health at the University of Miami Miller School of Medicine. “When used with digital tools such as the Regenstrief passive digital marker, we can expand early detection effectively and efficiently.”

This advancement represents a major breakthrough in the translation of AI and patient-reported outcomes into everyday clinical care. By integrating scalable digital tools that work seamlessly within existing healthcare systems, the research team demonstrated how technology can strengthen early detection, reduce the burden on primary care teams, and improve outcomes for older adults.

“This work represents the next phase of our half-century legacy at Regenstrief: using data, innovation and compassion to transform health care delivery,” said Dr. Boustani. “We have shown that it is possible to bring the power of AI and patient-reported outcomes directly into the clinic, transparently, affordably and at scale. »