Scientists develop non-invasive method to predict onset of dementia

February 11, 2020

INDIANAPOLIS -- Information gathered from routine visits to the doctor is enough to accurately predict a person's risk of developing Alzheimer's disease and related dementias, according to new research led by scientists from Regenstrief Institute, Indiana University and Merck. The researchers developed and tested machine learning algorithms using data from electronic medical records to identify patients who may be at risk for developing the dementia.

At least 50 percent of older primary care patients living with Alzheimer's disease and related dementias never receive a diagnosis. And many more live with symptoms for two to five years before being diagnosed. Currently, tests to screen for dementia risk are invasive, time-consuming and expensive.

"The great thing about this method is that it's passive, and it provides similar accuracy to the more intrusive tests that are currently used," said lead researcher Malaz Boustani, M.D., MPH, a research scientist at Regenstrief Institute and a professor at Indiana University School of Medicine. "This is a low cost, scalable solution that can provide substantial benefit to patients and their families by helping them prepare for the possibility of life with dementia and enabling them to take action."

Developing machine learning algorithms for predicting dementia

The research team, which also included scientists from Georgia State, Albert Einstein College of Medicine and Solid Research Group, recently published its findings on two different machine learning approaches. The paper published in the Journal of the American Geriatrics Society analyzed the results of a natural language processing algorithm, which learns rules by analyzing examples, and the Artificial Intelligence in Medicine article shared the results from a random forest model, which is built using an ensemble of decision trees. Both methods showed similar accuracy at predicting the onset of dementia within one and three years of diagnosis.

In order to train the algorithms, researchers gathered data on patients from the Indiana Network for Patient Care. The models used information on prescriptions and diagnoses, which are structured fields, as well as medical notes, which are free text, to predict the onset of dementia. Researchers found that the free text notes were the most valuable to helping identify people at risk of developing the disease.

"This research is exciting because it potentially provides significant benefit to patients and their families," said Patrick Monahan, PhD, study author from IU School of Medicine and a Regenstrief affiliate scientist. "Clinicians can provide education on behavior and habits to help patients cope with their symptoms and live a better quality of life."

Zina Ben Miled, PhD, M.S., a study author from the Purdue School of Engineering and Technology at IUPUI and a Regenstrief affiliate scientist, said, "The early risk identification allows an opportunity for doctors and families to put a care plan in place. I know from experience what a burden it can be to deal with a dementia diagnosis. The window provided by this test is so important to help improve the quality of life for both patients and their families."

In addition to the benefit to families, these methods can also provide significant cost savings for patients and health systems. They replace the need for expensive tests and allow clinicians to screen entire populations to identify those most at risk. Delaying the onset of symptoms also saves a significant amount of money on treatment.

The next step is to deploy these machine learning algorithms in real-life clinics to test if they help identify more true cases of dementia as well as to learn how they impact a patient's willingness to follow up on the results.
About the papers

Dr. Ben Miled is first author on "Predicting dementia with routine care EMR data," which has been published online ahead of print in the Journal of Artificial Intelligence in Medicine. Dr. Boustani is the senior author. Other authors are Kyle Haas, M.S. from the Purdue School of Engineering and Technology at IUPUI; Christopher M. Black, PhD, MPH, Rezaul Karim Khandker, PhD, MBA, and Vasu Chandrasekaran, PhD, from Merck and Co., Inc.; and Richard Lipton, M.D. from Albert Einstein College of Medicine. This research was supported in part by Merck Sharp & Dohme Corp., a subsidiary of Merck & Co., Inc.

Dr. Boustani is the first author on "Passive Digital Signature for Early Identification of Alzheimer's Disease and Related Dementia," which has been published online ahead of print in the Journal of the American Geriatrics Society. Dr. Monahan is the senior author. Other authors are Paul R. Dexter, M.D., a Regenstrief Institute scientist and associate professor of medicine at IU School of Medicine; Anthony J. Perkins, M.S., IU School of Medicine; Stephen Duong, M.A., M.S., Georgia State; Christopher M. Black, PhD, MPH, Rezaul Karim Khandker, PhD, MBA, and Vasu Chandrasekaran, PhD, Merck and Co., Inc.; Richard Lipton, M.D., Albert Einstein College of Medicine; and Craig A. Solid, PhD, Solid Research Group, LLC. This study was supported by Merck Sharp & Dohme Corp., a subsidiary of Merck & Co., Inc. It was also supported in part by the Einstein Aging Study: NIH/NIA 2PO1 AG 003949.

More about Malaz Boustani, M.D., MPH

In addition to his role as a research scientist at Regenstrief Institute, Malaz Boustani, M.D., MPH, is the founding director of the Center for Health Innovation and Implementation Science and a professor and the Richard M. Fairbanks Chair in Aging Research at Indiana University School of Medicine. He is also the founding director and chief innovation and implementation officer at the Sandra Eskenazi Center for Brain Care Innovation, in addition to being the director of senior care innovation at Eskenazi Health.

More about Patrick Monahan, PhD, M.S.

Patrick Monahan, PhD, M.S., is a professor of biostatistics at Indiana University School of Medicine and Indiana University Richard M. Fairbanks School of Public Health at IUPUI. He is a Regenstrief Institute affiliate scientist as well as director of analytics for the Sandra Eskenazi Center for Brain Care Innovation, IU Cancer Control & Prevention Program, and the Center for Health Innovation & Implementation Science.

More about Zina Ben Miled, PhD, M.S.

Zina Ben Miled, PhD, M.S., 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 affiliate scientist.

About Regenstrief Institute

Founded in 1969 in Indianapolis, 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 to Indiana University, Regenstrief and its researchers are responsible for a growing number of major healthcare innovations and studies. Examples range from the development of global health information technology standards that enable the use and interoperability of electronic health records to improving patient-physician communications, to creating models of care that inform practice and improve the lives of patients around the globe.

Regenstrief Institute is celebrating 50 years of healthcare innovation. Sam Regenstrief, a successful entrepreneur from Connersville, Indiana, founded the institute with the goal of making healthcare more efficient and accessible for everyone. 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 U.S. and is annually ranked among the top medical schools in the nation by U.S. 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.

Regenstrief Institute

Related Dementia Articles from Brightsurf:

The danger of Z-drugs for dementia patients
Strong sleeping pills known as 'Z-drugs' are linked with an increased risk of falls, fractures and stroke among people with dementia, according to new research.

The long road to dementia
Alzheimer's disease develops over decades. It begins with a fatal chain reaction in which masses of misfolded beta-amyloid proteins are produced that in the end literally flood the brain.

Why people with dementia go missing
People with dementia are more likely to go missing in areas where road networks are dense, complicated and disordered - according to new research from the University of East Anglia.

PTSD may double risk of dementia
People who have experienced post-traumatic stress disorder (PTSD) are up to twice as likely to develop dementia later in life, according to a new study by UCL researchers, published in the British Journal of Psychiatry.

Dementia education
School-based dementia education could deliver much needed empathy and understanding for older generations as new research from the University of South Australia shows it can significantly improve dementia knowledge and awareness among younger generations.

Building dementia friendly churches
A project to help church communities become more 'dementia friendly' has had a significant impact across the country.

A "feeling" for dementia?
A research team led by the DZNE concludes that personal perception can be an important indicator for the early detection of Alzheimer's disease.

New biomarker for dementia diagnosis
Medical researchers in the UK and Australia have identified a new marker which could support the search for novel preventative and therapeutic treatments for dementia.

Digital solutions for dementia care
Telehealth delivery of dementia care in the home can be as effective as face-to-face home visit services if carers and recipients take advantage of the technologies available, Australian researchers say.

Despite a marked reduction in the prevalence of dementia, the number of people with dementia is set to double by 2050 according to new Alzheimer Europe report
Today, at a European Parliament lunch debate, Alzheimer Europe launched a new report presenting the findings of its collaborative analysis of recent prevalence studies and setting out updated prevalence rates for dementia in Europe.

Read More: Dementia News and Dementia Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to