By Katie Wike, contributing writer
Vanderbilt University Medical Center is using natural language processors in an EHR to collect data on patients identified as suffering from multiple sclerosis
According to HealthData Management, researchers at Vanderbilt University Medical Center “have used natural language processing technology in an electronic medical records system to identify patients with multiple sclerosis and collect data on traits of their disease course.”
“Most research studies have focused on the origin of the disease, partly because of the difficulty in ascertaining sufficient longitudinal clinical data to study the disease course,” according to the study published in the Journal of the American Medical Informatics Association. “Electronic medical records may provide such a tool. We have previously shown that genomic signals of MS risk may be replicated using EMR-derived cohorts. In this paper, we evaluated algorithms to extract detailed clinical information for the disease course of MS.”
Researchers used ICD-9 codes, medications, and text keywords to identify relevant electronic records according to iHealth Beat. The study found that for all clinical traits examined precision was 87 percent and specificity was greater than 80 percent. "This dataset provides a rich resource for better understanding MS and also shows that extraction of detailed disease states and markers of prognosis in patients with chronic disease is possible and may yield a powerful tool in chronic disease research,” researchers wrote. “This information is extractable from clinic notes by simple algorithms, with high specificity, precision, and recall."
Authors of the study also note it is “one of the first … to focus on specific traits of a disease by text mining of the EMR. A few other studies have used text mining approaches to extract blood pressures, pacemaker implantations, and left ventricular ejection fractions as a marker of heart failure. We have shown that detailed clinical information valuable to research studies is recorded in medical records of individuals with MS, and that this information can be extracted in a highly reliable manner.”
Want to publish your opinion?
Contact us to become part of our Editorial Community.