NLP tool combs EHRs, predicts onset of dementia
Researchers from Massachusetts General Hospital have used natural language processing and electronic health records to identify patients at risk for dementia up to eight years in advance.
Researchers from Massachusetts General Hospital have used natural language processing and electronic health records to identify patients at risk for dementia up to eight years in advance.
“We need to detect dementia as early as possible to have the best opportunity to bend the curve,” says Roy Perlis, MD, director of the MGH Center for Quantitative Health. “With this approach, we are using clinical data that is already in the health record, which doesn’t require anything but a willingness to make use of the data.”
A study, published in Alzheimer's & Dementia, leveraged data on 267,855 patients and utilized NLP to comb through EHRs looking for key clinical terms associated with cognitive symptoms. The method extracts the relevant symptoms from information in the notes recorded by clinicians in patients’ EHRs.
“We used longitudinal electronic health records from two large academic medical centers and applied a validated natural language processing tool to estimate cognitive symptomatology,” state the study’s authors. “A cognitive symptom measure identified in discharge notes facilitated stratification of risk for dementia.”
Investigators discovered that 2.4 percent of patients developed dementia over the eight 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,” says first author Thomas McCoy, Jr., MD, director of research at the MGH Center for Quantitative Health. "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.”
According to researchers, the software-based approach to early risk detection has the potential to accelerate research efforts to slow progression or reverse early disease.
“This approach could be duplicated around the world, giving us more data and more evidence for trials looking at potential treatments,” says Rudolph Tanzi, 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.
“We need to detect dementia as early as possible to have the best opportunity to bend the curve,” says Roy Perlis, MD, director of the MGH Center for Quantitative Health. “With this approach, we are using clinical data that is already in the health record, which doesn’t require anything but a willingness to make use of the data.”
A study, published in Alzheimer's & Dementia, leveraged data on 267,855 patients and utilized NLP to comb through EHRs looking for key clinical terms associated with cognitive symptoms. The method extracts the relevant symptoms from information in the notes recorded by clinicians in patients’ EHRs.
“We used longitudinal electronic health records from two large academic medical centers and applied a validated natural language processing tool to estimate cognitive symptomatology,” state the study’s authors. “A cognitive symptom measure identified in discharge notes facilitated stratification of risk for dementia.”
Investigators discovered that 2.4 percent of patients developed dementia over the eight 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,” says first author Thomas McCoy, Jr., MD, director of research at the MGH Center for Quantitative Health. "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.”
According to researchers, the software-based approach to early risk detection has the potential to accelerate research efforts to slow progression or reverse early disease.
“This approach could be duplicated around the world, giving us more data and more evidence for trials looking at potential treatments,” says Rudolph Tanzi, 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.
More for you
Loading data for hdm_tax_topic #better-outcomes...