Study: EHRs Can Help Find Undiagnosed Cases of Type-2 Diabetes

Data link sexual and gender-identity disorders to the disease

In 2012, researchers at the University of California at Los Angeles (UCLA) set out to review thousands of electronic health records (EHRs) for a more accurate and less expensive way to identify people with undiagnosed type-2 diabetes. The team has now reported several previously unknown risk factors for diabetes, including a history of sexual and gender-identity disorders, intestinal infections, and a category of illnesses that includes such sexually transmitted diseases as chlamydia infection. Their findings were 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,” said lead author Dr. Ariana Anderson, an assistant research professor and statistician at UCLA’s Semel Institute for Neuroscience and Human Behavior.

Anderson led a team that examined EHRs for 9,948 people at hospitals, clinics, and doctors’ offices in all 50 states. Although the patients themselves were not identifiable, the records included their vital signs, prescription medications, and reported ailments, categorized according to the International Classification of Diseases (ICD) diagnostic codes.

The researchers used half of the records to design an algorithm that allowed them to predict the likelihood of an individual having diabetes, and then tested this prescreening tool on the other half. They found that having any diagnosis of sexual and gender-identity disorders increased the risk for type-2 diabetes by approximately 130%—about the same as hypertension, which is a leading risk factor.

Other health conditions were shown to be nearly as important risk factors for the disease. Among them were a history of viral infections and chlamydia (which increased people’s risk for diabetes by 82%) and a history of intestinal infections, such as colitis, enteritis, and gastroenteritis (an 88% increase). Those predictors were nearly as strong as having a high body mass index (BMI, a 101% increase).

Herpes zoster (HZ) has been shown to have a link to diabetes, and the UCLA project confirmed that connection, finding that HZ increases the risk by approximately 90%. Chicken pox, shingles, and a range of other viral infections (which are grouped together under one ICD diagnostic code) increased the risk for type-2 diabetes as much as hypercholesterolemia, the team found.

The researchers also determined that certain factors appeared to be related to a lower risk for diabetes. Being prone to migraines, for instance, reduced an individual’s risk for diabetes by the same amount as being 29 years younger. People taking antianxiety and antiseizure medications, such as clonazepam and diazepam, also had a significantly lower risk.

Additional research will be required to determine the medical reasons that certain factors correlate with greater or lesser diabetes risk, the researchers said. And because the analysis was based largely on diagnostic codes rather than on actual diagnoses, the findings are not “fine-grained” enough to tell precisely which conditions are linked to diabetes, they noted.

Traditionally, medical providers have determined whom to screen for type-2 diabetes based on a limited number of factors, including blood pressure, BMI, age, gender, and whether they smoke. The UCLA’s prescreening tool based on the entirety of a patient’s EHR proved 2.5% better at identifying people with diabetes than the standard approach, and 14% better at identifying those who did not have diabetes. The researchers calculated that if the new method were used nationally, it would identify 400,000 people who have not yet been diagnosed with the disease.

Source: Medical Xpress; February 16, 2016.