Algorithm Could Identify Hidden Type 2 Cases

A simple algorithm used to scan electronic health records could be a breakthrough in identifying cases of type 2 diabetes, according to a study published in BMC Medical Informatics and Decision Making. And that could lead to timely treatment and prevention of diabetes complications.

In layman’s terms, an algorithm is a set of instructions that can be turned into a piece of software or computer program. Used on a set of electronic health records, an algorithm focused on finding people with type 2 diabetes had remarkable results: a 90 percent accuracy rate in identifying actual type 2s. In 78 percent of cases, it could actually predict when the patient would be diagnosed.

While both of those numbers are impressive, it’s a third number that has the greatest implications for people with diabetes and their doctors. The algorithm could prevent a delayed diagnosis in 11 percent of type 2 diabetes cases. That means those people could start treatment to preserve their health earlier and stay healthy longer.

“Achieving early glycemic control in patients with newly diagnosed diabetes reduces the risk of microvascular complications, myocardial infarction, and all-cause mortality,” the study’s authors wrote. “The distinct advantage of our automated, real-time algorithm is the timely recognition of diabetes.”

Delays in recognizing and treating diabetes can be a big problem, according to the study. There is an average 2.4-year gap between the onset and diagnosis of type 2 diabetes, and some 7 percent of cases go a full seven years without being treated.

The researchers continued, “Health care systems may additionally apply this algorithm to provide feedback to providers on the quality of their care, generate letters to patients, identify underperforming clinics for quality improvement initiatives, link clinical decision support tools to inform decision making at the point-of-care, and risk stratify diabetic patients to direct limited resources to patients at greatest risk for developing complications.”

With this new algorithm approach, along with the widespread use of electronic health records, doctors and other health care providers can have a big-picture view of type 2 cases. But they will also be able to help individuals. And that’s great news for type 2 patients’ long-term health.

Sources:

http://ehrintelligence.com/2013/08/07/ehr-analytics-can-identify-diabetes-earlier-and-in-real-time/

http://www.biomedcentral.com/content/pdf/1472-6947-13-81.pdf