Using AI to identify undiagnosed dementia

Using AI to identify undiagnosed dementia

Newswise – INDIANAPOLIS – Rising to meet the formidable challenge of timely diagnosis of dementia, research scientists from Regenstrief Institute, IUPUI and the medical schools of Indiana University and University of Miami are conducting the Digital Detection of Dementia Study, a real-world evaluating the use of an artificial intelligence (AI) tool they developed for early identification of Alzheimer’s disease and related dementias in primary care, the setting where most adults receive health care. Individuals identified as cognitively impaired will be referred for diagnostic services.

The AI ​​tool, called a passive digital tag, is a machine learning algorithm that the researchers developed, trained and tested. The tool uses natural language processing to extract unstructured information in combination with structured data from a patient’s electronic health record. This may include mention of memory problems, a notation of vascular concerns, comorbid conditions, or other factors that may be related to dementia.

“Between 50 to 80 percent of dementia cases go unrecognized by the health care system in the U.S., and if you include patients living with mild cognitive impairment, that number can actually climb to more than 80 percent of unrecognized cases,” Regenstrief said. Institute and Indiana University School of Medicine faculty member Malaz Boustani, MD, MPH, senior author of the Digital Detection of Dementia study protocol paper, published in the peer-reviewed journal Trials. “In this new study, we evaluate the practicality of our tool when used alone and when used with an accompanying patient-reported outcomes survey.

“Unfortunately, the lay public believes there is nothing you can do if you find out that you or a family member has Alzheimer’s disease, but this is not true. Over the past 20 years, we have developed, validated and operate a comprehensive dementia care collaborative model that reduces the disease burden for the patient, reduces caregiver stress and reduces inappropriate hospitalizations, allows people to stay at home longer and lowers overall costs for them. and to the health care system,” he said.

Few primary care practices are designed for early detection of Alzheimer’s disease. The limited time that primary care clinicians have to spend with patients, the need to focus on the health problems that brought the patient to the clinic, as well as the stigma of dementia are the main reasons for a lack of recognition of the condition, according to Dr Boustani. In addition, he notes, there is no public demand for dementia diagnosis, most likely driven by the stigma of dementia, lack of public knowledge about benefits of early recognition of Alzheimer’s disease and issues related to health insurance coverage.

The first aspect of the Digital Detection of Dementia study is a clinical trial already underway in Indianapolis, enrolling patients in primary care clinics at federally qualified health centers affiliated with Eskenazi Health. The participants in this trial are expected to be predominantly people who are Black and live in urban areas. The second clinical trial of the study begins in early 2023 in Miami, Florida, at the University of Miami Primary Care Clinics. The participants are expected to be predominantly Hispanic and include a high percentage of rural residents.

Each trial is the same and has three arms: (1) usual primary care approach; (2) the specially designed passive digital tag that relies on artificial intelligence; and (3) the new passive digital marker plus a specially designed patient-reported outcomes survey.

Patients in all three arms will be followed for two consecutive years to determine how many new cases of Alzheimer’s disease are recognized and documented in patients’ electronic health records.

The 7,200 expected study participants (3,600 in Indiana and 3,600 in Florida) must be 65 years of age or older, have had at least one visit to a primary care practice in the past year and be able to communicate in English or Spanish. Electronic health record data from at least the past three years must be available to be enrolled in the study. Individuals living in a nursing home or suffering from serious mental illness are not eligible.

“Passive digital markers are developed using data from electronic health records,” said Zina Ben Miled, PhD, a Regenstrief Institute-affiliated scientist and an IUPUI associate professor of electrical and computer engineering, who developed the passive digital marker tool with Dr. Boustani developed. . “The advantage of this approach is that the information is already collected and requires no extra effort from the patient or the provider. Through machine learning algorithms and natural language processing, we can use this data to identify people who may be at risk for Alzheimer’s disease without the need for invasive and expensive tests.”

“Through this project, we hope to demonstrate that these approaches can be successfully implemented in the real world, resulting in benefits for both patients and their families,” said cognitive neurologist James E. Galvin, MD, MPH, a professor of neurology at the University of Miami’s Miller School of Medicine. “Combining a patient-reported outcome with a passive digital marker is an innovative and highly sensitive way to detect mild cognitive impairment, Alzheimer’s disease and related disorders, yet low burden for patients and clinicians for ease of use.” Dr. Galvin developed the Patient Reported Outcomes Tool.

Both the passive digital marker tool and the patient-reported outcomes tool are low cost. The Digital Detection of Dementia study will confirm their suitability for use in primary care practice as well as their scalability.

It is estimated that the prevalence of dementia in primary care in the US is about 6 percent of patients, but only 2 percent of patients are recognized by the health care system as having the condition. The researchers believe that using their passive digital marker, possibly in tandem with the patient-reported outcomes tool, could potentially double the number of cases identified, improving the lives of more individuals living with dementia and their caregivers. .

“We don’t just recognize patients with cognitive impairment and say, ‘See you later.’ We also provide computerized decision support to the primary care clinician that will help them refer these patients for confirmatory dementia screening. If the screening is positive, they can receive care based on our successful, evidence-based collaborative dementia care model,” said Dr. Boustani said.

“Digital detection of dementia (D3): a study protocol for a pragmatic cluster-randomized trial investigating the application of patient-reported outcomes and passive clinical decision support systems,” was supported by a five-year grant from the National Institutes of Health’s National Institute on Aging. Authors, in addition to Dr. Boustani, Ben Miled, and Galvin are Randall W. Grout, MD, MS, Paul Richard Dexter, MD, and Nicole Fowler, PhD, all of Regenstrief Institute and IU School of Medicine; Arthur Owora, PhD, IU Bloomington School of Public Health; and joint first authors Michael J. Kleiman, PhD, University of Miami, and Abbi D. Plewes, IU School of Medicine.

About Malaz Boustani, MD, MPH

In addition to his role as a research scientist at Regenstrief Institute, Malaz Boustani, MD, MPH, is the founding director of the Center for Health Innovation and Implementation Science. He is a professor and the Richard M. Fairbanks Professor of Aging Research at the Indiana University School of Medicine. Dr. Boustani is also director of care innovation at Eskenazi Health.

About Zina Ben Miled, PhD, MS

Zina Ben Miled, PhD, MS, is an associate professor of electrical and computer engineering in the Purdue School of Engineering and Technology at IUPUI and a research scientist in the Center for Health Innovation and Implementation Science. She is also a Regenstrief Institute-affiliated scientist.

About James E. Galvin, MD, MPH

James E. Galvin, MD, MPH, is a professor of neurology at the University of Miami Miller School of Medicine. He is the founding director of the Comprehensive Center for Brain Health and head of the cognitive neurology section in the Department of Neurology.

About Regenstrief Institute

Founded in Indianapolis in 1969, the Regenstrief Institute is a local, national and global leader dedicated to a world where better information empowers people to end disease and realize true health. A key research partner for Indiana University, Regenstrief and his research scientists are responsible for a growing number of major healthcare innovations and studies. Examples range from developing global health information technology standards that enable the use and interoperability of electronic health records to improving patient-physician communication, to creating models of care that inform practice and improve the lives of patients around the world.

Sam Regenstrief, a nationally successful entrepreneur from Connersville, Indiana, founded the institute with the goal of making health care more efficient and accessible for all. His vision continues to guide the institute’s research mission.

About IU School of Medicine

IU School of Medicine is the largest medical school in the US and is annually ranked among the top medical schools in the country by US News & World Report. The school offers high-quality medical education, access to leading medical research and rich campus life in nine Indiana cities, including rural and urban locations consistently recognized for livability.


As Indiana’s leading urban public research university, IUPUI believes in the power of transformation. It is committed to providing educational opportunities that transform the lives of students, the community and the changing world. It offers more than 450 undergraduate, graduate and professional programs from Indiana University and Purdue University.

About the University of Miami Miller School of Medicine

The University of Miami Miller School of Medicine is an innovative institution that empowers students and trainees to transform lives and inspires them to serve the global community. Founded in 1952, it was Florida’s first medical school. It now includes 21 clinical departments, 6 basic science departments, 45 centers and institutes, and more than 1,400 faculty members. South Florida’s cultural diversity makes it a medical training ground of unparalleled opportunity

Leave a Reply

Your email address will not be published. Required fields are marked *