University of California researchers have developed an algorithm to help identify undiagnosed Type 2 diabetes patients based on data found in EHRs. Their work is published in the Journal of Biomedical Informatics.
"With widespread implementation, these discoveries have the potential to dramatically decrease the number of undetected cases of Type 2 diabetes, prevent complications from the disease and save lives," Ariana Anderson, lead author and an assistant research professor and statistician at UCLA's Semel Institute for Neuroscience and Human Behavior, said in a statement.
An examination of nearly 10,000 electronic records from patients across all 50 states revealed certain characteristics that may indicate undiagnosed Type 2 diabetes, including a diagnosis of sexual and gender identity disorders, a history of viral infections and a history of intestinal infections. Some of these characteristic correlations were nearly as strong as well-established Type 2 diabetes risk factors, such as having a high body mass index or high blood pressure.
Half of the electronic records reviewed for the study were used to hone the algorithm, which was then applied as a pre-screening tool for the other half to identify patients who may have undiagnosed Type 2 diabetes. The researchers note the current risk factors they've identified are based on diagnostic codes rather than individual diagnoses, making them more generalized than would be ideal to draw concrete conclusions about which conditions are truly risk factors. However, they calculate that if the algorithm was used for patients nationwide, it would likely identify 400,000 people currently living with undiagnosed Type 2 diabetes.
"There's so much more information available in the medical record that could be used to determine whether a patient needs to be screened, and this information isn't currently being used," Mark Cohen, PhD, director of UCLA's Laboratory of Integrative Neuroimaging Technology, said in a statement. "This is a treasure trove of information that has not begun to be exploited to the full extent possible."