Electronic health records (EHRs), which are quickly replacing paper files in doctors’ offices and hospitals across the country, may provide a new and unexpected weapon in combating the U.S. epidemic of diabetes.

UCLA researchers have determined EHRs are a more accurate and less expensive way for doctors to identify people who have undiagnosed Type 2 diabetes than current testing methods.

Lead researcher Ariana Anderson, an assistant research professor and statistician at the University of California-Los Angeles Semel Institute for Neuroscience and Human Behavior, said the team was able to develop an EHR-based screening system with the potential to vastly increase the number of correct diabetes diagnoses by refining the pool of candidates who are typically screened.

The team also uncovered 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.

"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 Anderson of the findings, published in the Journal of Biomedical Informatics.

For the study, Anderson and colleagues examined electronic records for 9,948 people from hospitals, clinics, and doctor's offices in all 50 states. Although the patients were not identifiable, the records included their vital signs, prescription medications and reported ailments, categorized according to the International Classification of Diseases diagnostic codes.

The researchers used half of the records to come up with a screening system that allowed them to predict the likelihood of an individual having diabetes, and then tested this tool on the other half.

By doing so, they found that having any diagnosis of sexual and gender identity disorders increased the risk for Type 2 diabetes by roughly 130 percent — about the same as high blood pressure, which is a leading risk factor.

Other health conditions were shown to be nearly as important risk factors for the disease. Among them: a history of viral infections and chlamydia (which increase people's risk for diabetes by 82 percent); and intestinal infections such as colitis, enteritis, and gastroenteritis (88 percent increase). In fact, those predictors were nearly as strong as having a high body mass index (101 percent increase).

Herpes zoster was also found to increase the risk of diabetes by about 90 percent. And chicken pox, shingles, and other viral infections (grouped together under one diagnostic code) increased the risk for Type 2 diabetes as much as high cholesterol, the team found.

Curiously, the researchers also determined certain factors appeared to lower the risk for diabetes. Being prone to migraines, for instance, reduced an individual's risk for the disease by the same amount as being 29 years younger. And people taking anti-anxiety and anti-seizure medications such as clonazepam and diazepam had a significantly lower risk.

Traditionally, medical providers decide whom to screen for diabetes based on a limited range of factors, including blood pressure, BMI, age, gender, and whether or not they smoke. But the pre-screening tool based on a a patient's EHR proved 2.5 percent better at identifying people with diabetes than the standard approach, and 14 percent better at identifying those who do not have it.

The researchers calculated that if the new method were used nationally, it would identify 400,000 people who unknowingly have the disease.

"Given that one in four people with diabetes don't know they have the disease," Anderson said, "it's very important to be able to say, 'This person has all these other diagnoses, so we're a little bit more confident that she is likely to have diabetes. We need to be sure to give her the formal laboratory test, even if she's asymptomatic.'"

Mining EHRs for ways to improve healthcare has allowed researcher to use computers to uncover unexpected patterns in vast amounts of data — or machine learning — that some argue has the potential to revolutionize medicine.