Using EHR data, a machine learning tool was able to predict dementia risk up to eight years in advance.
A machine learning algorithm analyzed EHR data to estimate the risk that a healthy person will receive a dementia diagnosis in the future, a study published in the journal Alzheimer’s and Dementia found.
Alzheimer’s currently affects 5.5 million Americans, the researchers noted, and that number is only expected to grow in the coming years. Early detection tools typically require additional data collection, which can be expensive.
A team from Massachusetts General Hospital (MGH) developed a machine learning algorithm that would use data already collected during routine clinical care. The tool built a list of clinical terms associated with cognitive symptoms identified by experts. Then, using natural language processing, researchers combed through EHRs looking for those terms, and used those results to estimate patients’ risk of developing dementia.
Want to publish your own articles on DistilINFO Publications?
Send us an email, we will get in touch with you.
The team used the algorithm to analyze data from 267,855 patients admitted to one of two hospital systems. The results showed that 2.4 percent of these patients received a new dementia diagnosis in the subsequent years of follow-up.
“The most exciting thing is that we are able to predict risk of new dementia diagnosis up to eight years in advance,” said Thomas McCoy, Jr., MD, first author of the paper.
In earlier studies, the team used machine learning tools to predict patients’ risk of suicide and accidental death, as well as the likelihood of admission and length of stay among children with psychiatric symptoms in emergency rooms.
“This method was originally developed as a general ‘cognitive symptom’ assessment tool. But we were able to apply it to answer particular questions about dementia,” said McCoy. “This study contributes to a growing body of work on the usefulness of calculating broad symptom burden scores across neuropsychiatric conditions.”
Researchers expect that if the tool is properly tailored, it can be applied to more specific questions about other brain diseases as well.
“We need to detect dementia as early as possible to have the best opportunity to bend the curve,” says Roy Perlis, MD, senior author of the study and director of the MGH Center for Quantitative Health. “With this approach we are using clinical data that is already in the health record, that doesn’t require anything but a willingness to make use of the data.”
Many studies have demonstrated the potential for machine learning and other advanced analytics tools to improve Alzheimer’s diagnosis. In 2017, a team from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) developed a machine learning algorithm that used protein biomarkers to identify Alzheimer’s disease.
The tool was able to accurately identify imaging studies of patients progressing into dementia 84 percent of the time.
“Given the high prevalence of cognitively normal elderly individuals carrying the Alzheimer’s disease pathophysiology, accurately identifying individuals who are in the early stages of Alzheimer’s disease has been a significant challenge,” explained ADNI researchers at the time.
With this machine learning tool, the MGH team believes healthcare professionals could accelerate Alzheimer’s and dementia research, leading to earlier treatment and improved outcomes.
“This approach could be duplicated around the world, giving us more data and more evidence for trials looking at potential treatments,” says Rudolph Tanzi, PhD, a member of the research team, vice-chair of Neurology, and Co-Director of the MGH McCance Center for Brain Health at the MGH Institute for Neurodegenerative Diseases.
Source: Health IT Analytics