Screening algorithm could identify undiagnosed cases of type 2 diabetes

A new screening algorithm provides a cheaper and more accurate way to identify people with undiagnosed type 2 diabetes, according to a new study.
The research, which was conducted at the University of California, Los Angeles Semel Institute for Neuroscience and Human Behaviour, also found a number of new risk factors.
Previously unknown risk factors include a history of sexual and gender identity disorders, intestinal infections and Chlamydia (which increases the risk of type 2 diabetes by 82 per cent).
How was the study conducted?
The researchers examined the electronic records of 9,948 people. The anonymous data was taken from hospitals, clinics and doctor’s offices throughout the US, evaluating vital signs, prescription medications taken by each patient, and their reported ailments.
Half of the data was used to develop an algorithm that could predict the likelihood of type 2 diabetes in a person. Once this had been developed, the researchers used the other half of the data to test it.
Through testing the algorithm, the researchers found several previously undiscovered risk factors for type 2 diabetes, including the sexual and gender identity disorders, which increased the risk by 130 per cent, and Chlamydia, which increased the risk by 82 per cent. Intestinal infections such as colitis, enteritis and gastroenteritis increased the risk by 88 per cent. By comparison, high body mass index (BMI), a known risk factor for type 2 diabetes, increased the risk by 101 per cent.
Other factors linked to type 2 diabetes included herpes, chicken pox and shingles.
Several factors, which were previously thought to have no effect on type 2 diabetes risk, were found to decrease the risk. These factors included being prone to migraines and taking anti-anxiety medication.
How might this study change the way we screen people for type 2 diabetes?
Further research is needed to work out why these new factors might affect type 2 diabetes risk.
These findings have the potential to change how people are screened for type 2 diabetes. Traditional risk factors, such as BMI, age and family history, may not be the most effective way of screening.
“With widespread implementatio, 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 Ariana Anderson, assistant research professor and statistician at UCLA’s Semel Institute for Neuroscience and Human Behaviour.
“Given that one in four people with diabetes don’t know they have the disease, 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.'”
The study does not suggest that current screening methods don’t work. Generally, they are accurate. What this study does suggest is that they could be made even more accurate – and also cheaper.
“There’s so much 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,” said Mark Cohe, a Semel Institute professor in residence, who also acts as the director of UCLA’s Laboratory of Integrative Neuroimaging Technology. “This is a treasure trove of information that has not begun to be exploited to full extent possible.”
The findings are published in the Journal of Biomedical Informatics.