Researchers have developed a tool used to identify diabetes patients who are at-risk for being admitted to the hospital due to severe hypoglycemia, according to a study published today in JAMA Internal Medicine.
“Sometimes a person with diabetes is unaware that their blood sugar is dropping and can progress quickly into severe hypoglycemia, which has been associated with falls, automobile accidents, heart attacks, coma, and even death,” Andrew Karter, senior research scientist at Kaiser Permanente, said in prepared remarks. “Hypoglycemia is often preventable with the proper clinical attention, and we believe this tool will help focus that attention on the patients who most need it.”
Hypoglycemia is one of the most common adverse events in patients with Type II diabetes, and elderly patients or those who have a long history of diabetes are especially susceptible.
The research team first identified 156 hypoglycemia risk factors and collected data from more than 200,000 Type II diabetes patients. The scientists used machine-learning to develop a model that can predict a patient’s 12-month risk of hospitalization due to severe low blood sugar.
The analytical model was based on six variables – the number of prior hypoglycemia-related ED visits, insulin use, use of a common oral diabetes medicine, severe or end-stage kidney disease, number of ED visits for any reason in the last year and a patient’s age.
According to the model, the team devised a tool that categorizes patients into high (>5%), intermediate (1-5%) or low (<1%) 12-month risk of hospitalization due to hypoglycemia. The tool was validated using data from 1.3 milliom members of the U.S. Veterans Health Administration and thousands of Kaiser Permanente members in Washington.
The FDA helped to fund the development of this tool under its Safe Use Initiative.
“This work is an example of how federal agencies can work with private researchers to reduce preventable adverse drug events,” Dr. John Whyte, FDA’s director of professional affairs & stakeholder engagement, added. “The goal is to identify the patients who are at highest hypoglycemic risk, so that health care providers can focus their attention on the specific needs of these patients and reduce preventable hypoglycemia harm.”