A groundbreaking new study shows that artificial intelligence can help detect Alzheimer’s disease and other dementias early—without adding any extra work for doctors or cost for patients.
Researchers found that a fully digital, zero-cost AI tool can be built into everyday primary care systems, making early dementia detection possible on a large scale.
The study, published in JAMA Network Open, was led by scientists from the Regenstrief Institute, Indiana University School of Medicine, Eskenazi Health, the University of Miami, and Lamar University. They tested the system across more than 5,000 patients in real-world primary care clinics.
Doctors often struggle to detect dementia early. Primary care visits are short, and physicians must focus on the patient’s immediate health concerns. In addition, dementia can carry social stigma, leading to delays in diagnosis.
As a result, many people with early Alzheimer’s or related conditions go undiagnosed for years, missing the chance to receive early treatment and support.
To solve this problem, the research team combined two digital tools: a short, patient-reported survey called the Quick Dementia Rating System (QDRS) and an artificial intelligence tool known as a “passive digital marker.”
The QDRS consists of just 10 simple questions about memory, mood, and daily functioning. The AI tool uses natural language processing—a type of machine learning—to scan electronic health records for signs linked to dementia, such as memory complaints or vascular problems.
Together, these tools increased new dementia diagnoses by 31% compared with usual care. Importantly, the approach required no additional time from doctors or nurses, and it did not depend on expensive brain scans or lab tests.
The combined digital system also led to a 41% increase in follow-up testing, such as brain imaging and cognitive assessments, suggesting that more people received the care they needed earlier.
Dr. Malaz Boustani, the study’s lead author and a research scientist at the Regenstrief Institute, said this approach is both practical and accessible. “Our passive digital marker is open-source and zero cost.
Any health system that uses electronic health records can deploy it just like an app—no licensing fees, no extra clinician time,” he said. “This is the most scalable approach to early dementia detection that I know of.”
The study was carried out at nine federally qualified health centers within Eskenazi Health in Indianapolis. The QDRS survey and the AI tool were integrated directly into the Epic electronic health record system. Patients aged 65 and older were automatically invited to complete the brief survey through their online patient portal.
At the same time, the AI algorithm continuously analyzed each patient’s existing medical data. If it detected signs of cognitive decline, an alert automatically appeared in the doctor’s inbox, prompting a follow-up evaluation—without requiring manual screening.
Dr. Zina Ben Miled, a computer science professor at Lamar University who helped develop the AI tool, said the system helps make early detection more equitable.
“By embedding these tools into electronic health records, we can reach patients who might otherwise be overlooked. It ensures that everyone, regardless of background or resources, has the same chance for early diagnosis and care.”
Dr. James Galvin, a neurologist at the University of Miami Miller School of Medicine and co-developer of the QDRS, explained that combining patient self-reports with AI analysis allows for a powerful new model of dementia detection.
“When used together, these tools make early detection fast, accurate, and scalable. They can transform how primary care teams identify cognitive decline.”
Beyond improving detection, the researchers say this work is a major step toward integrating AI into everyday clinical practice. By using data already available in health records, the system supports doctors instead of replacing them—helping them focus on patient care rather than paperwork.
“This is the next phase of Regenstrief’s 50-year legacy of using data and innovation to transform healthcare,” said Dr. Boustani. “We’ve proven that it’s possible to bring AI directly into the clinic, seamlessly and affordably, to improve patient outcomes on a massive scale.”
If you care about Alzheimer’s, please read studies about the likely cause of Alzheimer’s disease , and new non-drug treatment that could help prevent Alzheimer’s.
For more health information, please see recent studies about diet that may help prevent Alzheimer’s, and results showing some dementia cases could be prevented by changing these 12 things.
The study is published in AMA Network Open.
Copyright © 2025 Knowridge Science Report. All rights reserved.
