A new tool developed by researchers at the University of Maryland School of Medicine can estimate the likelihood of a diabetes patient developing complications. The tool, called the Diabetes Complications Risk Calculator (DCRC), uses machine learning to analyze insurance claims and electronic health record data.
According to the CDC, about 40 million people in the United States, or about 12% of the U.S. population, have diabetes. These individuals are at risk for heart disease, kidney disease, nerve damage, eye disease, and emergencies caused by very high or very low blood sugar.
In 2021, there were about 16.5 million emergency department visits among people with diabetes, resulting in 8.1 million hospitalizations. Of these, 1.78 million were for major cardiovascular diseases, while 230,000 were for a hyperglycemic crisis and 52,000 were for hypoglycemia.
The DCRC can estimate risk for nine different acute and chronic complications, including cardiovascular disease, stroke, kidney disease, nerve damage, and blood sugar crises. This is a significant improvement over existing risk assessment tools, which often focus on just one complication at a time.
Related: FDA clears new drug for rare skin condition
Rozalina G. McCoy, M.D., MS, and her colleagues created the DCRC using claims data from over 400,000 adults newly diagnosed with diabetes Type 1 or Type 2. They also used data from electronic health records from Mayo Clinic for validation. The models incorporate commonly available information such as age, existing health conditions, medications, and laboratory tests.
The DCRC produces monthly risk estimates that change as a patient’s health status evolves. In testing, the models showed good to strong accuracy in predicting whether patients would develop specific complications.
One of the key benefits of the DCRC is its ability to update risk estimates over time, allowing clinicians to better understand what complications their patients are most likely to experience. This can ultimately support more informed and actionable conversations between patients and their clinicians.
While the DCRC has shown promise, it does have some limitations. The tool uses data only from insured patients, which may not fully reflect patients without consistent access to medical care. Additionally, some of its predictions were less accurate for certain complications.
Related: Sparsentan Access Guidance for Kidney Disease Patients
The research team plans to evaluate how the calculator performs when integrated into real-world clinical workflows and whether it can improve shared decision-making and long-term health outcomes. As the CDC continues to track diabetes-related complications, tools like the DCRC may become increasingly important in supporting patient care.
In practice, the DCRC could help clinicians identify high-risk patients and develop targeted treatment plans to reduce the likelihood of complications. By providing more accurate and up-to-date risk estimates, the tool could also help patients make more informed decisions about their care.
The DCRC has the potential to be applicable in real-world settings, but more testing is needed to understand how the tool performs in everyday clinical practice. As researchers continue to refine and test the DCRC, it may become a valuable resource for clinicians and patients alike.
