Nursing home providers may soon be able to accurately estimate an individual’s risk for developing Alzheimer’s disease simply by scanning a patient’s electronic health record (EHR). This is thanks to a machine learning tool developed by Massachusetts General Hospital (MGH) scientists.
The software-based approach works by making better use of data already generated during routine clinical care. It has the potential to predict dementia risk up to eight years in advance of the onset of the disease.
The researchers’ algorithm employed machine learning to first build a list of clinical terms associated with cognitive symptoms identified by experts. Then, using natural language processing, the researchers combed through EHRs looking for those terms, and used their results to estimate patients’ risk of developing dementia.
The study, published in Alzheimer’s & Dementia, includes data on nearly 270,000 patients admitted to one of two hospital systems. It found that 2.4% of patients developed dementia over the eight years of follow-up.
The MGH researchers hope their findings can help accelerate research efforts aimed at slowing progression or reversing early Alzheimer’s disease. Current early detection tools typically require additional data collection, which can be expensive.
Previous studies by this team of researchers used a similar tool to predict 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. The researchers expect that if the tool is properly tailored, it can be applied to more specific questions about other neurological diseases as well.
“We need to detect dementia as early as possible to have the best opportunity to bend the curve,” noted Roy Perlis, M.D., 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.”
From the February 2020 Issue of McKnight's Long-Term Care News
