Novel Tool Identifies Diabetes Patients at Risk of Hypoglycemia-Related Hospitalization

Researchers have created and validated a novel tool to identify patients with diabetes who have a high risk of being hospitalized due to hypoglycemia, according to a study published by JAMA Internal Medicine.

While better treatment options have significantly reduced complications of diabetes, some patients may experience hypoglycemia due to prescription drugs, exercise, or skipping a meal, according to the authors.

“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, dementia, coma, and even death,” said senior researcher Andrew J Karter, PhD. “Hypoglycemia is often preventable with the proper clinical attention. We believe this tool will help focus that attention on the patients who most need it.”

Hypoglycemia is among the most common adverse events experienced by patients with type 2 diabetes, accounting for more than 100,000 emergency department visits each year, according to the study. The authors report that older patients with a long history of the condition are more likely to be hospitalized for hypoglycemia.

The authors developed the risk stratification tool by including 156 risk factors for hypoglycemia and integrating data from more than 200,000 patients with type 2 diabetes. Through machine learning, the authors created a model that can predict a patient’s 12-month risk of emergency department visits or hospitalization due to hypoglycemia, according to the study.

The finalized model included: the number of prior hypoglycemia-related emergency department visits or hospitalizations; insulin use; sulfonylurea use; severe or end-stage kidney disease; the number of emergency room visits for any reason in the past year; and age, according to the study.

The investigators then created a tool that stratifies patients by annual risk of a hypoglycemic event that leads to hospitalization or emergency department use. Patients with a greater than 5% risk were categorized as high-risk, while patients with a less than 1% risk were categorized as low-risk.

The tool was validated using data from 1.3 million patients in the US Veterans Health Administration and 15,000 commercially-insured patients with type 2 diabetes, according to the authors.

“This hypoglycemia model is a great example of how we can leverage data that is contained within our health systems to improve the safety of the care we provide to our patients,” Dr Huang said. “I think it is going to become a model that is widely adopted by health systems throughout the country and it has the potential to really reduce hypoglycemia.”

Multiple large healthcare systems and organizations, including the Centers for Medicare & Medicaid Services (CMS), the Mayo Clinic, and Kaiser Permanente, are looking for ways to implement the tool to determine how to best prevent hypoglycemic events among patients with type 2 diabetes, according to the study.

The tool was funded by the FDA under the Safe Use Initiative to reduce drug-related adverse events, such as those used to treat diabetes. The authors report that the CMS is currently distributing the results of the study.

“This work is an example of how federal agencies can work with researchers to reduce preventable adverse drug events,” said John Whyte, MD, MPH, director of Professional Affairs and Stakeholder Engagement at the FDA. “The goal is to identify the patients who are at highest hypoglycemic risk, so that healthcare providers can focus their attention on the specific needs of these patients and reduce preventable hypoglycemia harm.”