A powerful new real-world data platform has the potential to change the way scientists predict and understand Alzheimer’s disease and Alzheimer’s disease-related dementia (AD/ADRD), reports a new study by collaborators at Columbia University’s Mailman School of Public Health and Vagelos College of Physicians and Surgeons, School of Nursing, University of Miami, and University of Chicago. The project, known as the M3AD Research and Real-World Data Metaplatform, represents one of the most comprehensive efforts to date to use large-scale clinical data to advance precision aging research and accelerate discoveries in the prevention and treatment of Alzheimer’s disease. The research will be published in a journal Alzheimer’s disease and dementia.
The platform leverages electronic health records from three U.S. cities containing approximately 60,000 people with AD/ADRD and allows researchers to track how multiple chronic diseases, behaviors, and social circumstances interact to shape dementia risk over time, creating one of the largest and most comprehensive datasets ever collected to study dementia.
Unlike traditional research that investigates a limited number of individual diseases, this platform analyzes interacting health, behavioral, and social factors simultaneously and over time. This will help us fully understand the complexity of aging and complex diseases, and improve predictions of dementia risk and progression.
As people live longer, chronic diseases become more prevalent, creating complex health trajectories that are not easily captured by traditional disease-specific studies. The new platform will address this challenge by integrating and harmonizing electronic health records (EHRs) from approximately 10 million patients across three major health systems in New York City, Chicago, and Miami, including approximately 60,000 patients with Alzheimer’s disease and related dementias. ”
Moise Desvarieux, MD, PhD, Associate Professor of Epidemiology, Corresponding Author
The study is motivated by the growing scope of dementia in the United States. More than 7.2 million older Americans are living with Alzheimer’s disease, including approximately 35 percent of people age 85 and older.
At the same time, nearly 90% of adults over the age of 60 have a complex disease with two or more chronic conditions, complicating diagnosis, treatment, and care. “This work challenges the long-held view that dementia is a single, isolated disease. Alzheimer’s disease and related dementias do not occur in isolation. They result from complex interactions between multiple diseases, behaviors, epigenetics, and life circumstances that influence each other over time,” continued Devereux.
“Electronic health records make it possible to analyze the trajectory of these interactions over decades of care. By examining longitudinal clinical history, this platform can help identify previously unrecognized early warning signs of dementia while providing a broader picture of a patient’s life,” said co-author George Flipsak, MD, MSc, Professor of Biomedical Informatics at Columbia University, Vivian Beaumont Allen.
The three-city consortium includes: The NewYork-Presbyterian Hospital Clinical Data Warehouse contains 32 years of data from approximately 6 million patients, including 33,000 patients with AD/ADRD. University of Chicago Clinical Research Data Warehouse – Collects data from over 2 million patients, including 11,000 patients with AD/ADRD. The other is the University of Miami Health System, which has approximately 1.4 million patients, including 13,000 patients with AD/ADRD.
When combined, these datasets form a multi-ethnic population spanning whites, blacks, Hispanics, and Asians, allowing researchers to study dementia risk across diverse populations.
The project also incorporates advanced analytics approaches, including machine learning models and federated platforms that allow agencies to collaboratively analyze data while protecting privacy. “These models can be extended to integrate additional real-world data sources, such as images, genetic information, and new biomarkers being identified,” added co-author Habibul Ahsan, MD, MMedSc, Lewis Block Distinguished Service Professor of Public Health Sciences, Family Medicine, and Human Genetics, and director of the Institute for Population and Precision Medicine at the University of Chicago.
“Medicine has traditionally focused on treating individual organs and diseases,” said co-author Tatiana Landek, professor of neurology and director of the Evelyn F. McKnight Brain Institute at the University of Miami. “However, aging is not just about one symptom, but the interaction of multiple health issues over time. To truly understand and prevent dementia, we need to look at the whole person, even before symptoms appear,” Landek continues. “This groundbreaking research gives us a unique opportunity to uncover early signs of dementia, providing insights that could transform real-world care, especially for individuals managing multiple health issues at the same time.”
The new platform also integrates predictive tools such as the Electronic Health Record Alzheimer’s Disease and Dementia Assessment Rules (eRADAR). eRADAR is an algorithm that uses routine EHR data to identify individuals who may have undiagnosed dementia and should undergo further clinical evaluation.
Beyond prediction, this platform allows researchers to test prevention hypotheses in real-world populations. For example, how smoking cessation, healthy weight, and blood pressure management in midlife affect cognitive decline later in life.
The initiative will also create an interdisciplinary research environment that brings together epidemiology, neurology, biostatistics, informatics, machine learning, and social science by linking clinical data with neighborhood-level contextual and social factors. “We are also embedding these clinical data with information from nearby census tracts, allowing us to examine how social and environmental conditions shape Alzheimer’s disease risk and progression over time,” added co-author Alison Aiello, Ph.D., James S. Jackson Professor of Health and Longevity Epidemiology and interim director of the Columbia Aging Center.
“Our multidisciplinary approach builds a dynamic platform to improve risk prediction, guide complex clinical management, and evaluate future treatments for Alzheimer’s disease in real-world settings,” the researchers said.
sauce:
Columbia University Postman School of Public Health
