Predictive Analytics Model Forecasts Diabetic Kidney Disease
New computational approach may help identify risk and predict kidney disease in type 2 diabetes patients, which may help optimize clinical interventions.
Source: Getty Images
By - Researchers from Sanford Burnham Prebys and the Chinese University of Hong Kong validated a predictive analytics approach to forecast whether type 2 diabetes patients will develop kidney disease, according to a study published today in Nature Communications.
Mayo Clinic indicates that diabetic kidney disease, or diabetic nephropathy, is a serious complication associated with both type 1 and type 2 diabetes. In the US, approximately one in three diabetes patients also have diabetic kidney disease.
Poorly controlled diabetes can lead to kidney damage, and eventually kidney disease, spurring researchers to pursue predictive technologies to improve patient outcomes.
“This study provides a glimpse into the powerful future of predictive diagnostics,” said study co-senior author Kevin Yip, PhD, a professor and director of Bioinformatics at Sanford Burnham Prebys, in a press release. “Our team has demonstrated that by combining clinical data with cutting-edge technology, it’s possible to develop computational models to help clinicians optimize the treatment of type 2 diabetes to prevent kidney disease.”
Diabetes and high blood pressure are two of the most common causes of kidney failure, and research suggests that diabetes causes 44 to 45 percent of end-stage kidney disease cases, making predicting patient risk crucial.
“There has been significant progress developing treatments for kidney disease in people with diabetes,” explained study co-senior author Ronald Ma, MB BChir, a professor in the Department of Medicine and Therapeutics at the Chinese University of Hong Kong. “However, it can be difficult to assess an individual patient’s risk for developing kidney disease based on clinical factors alone, so determining who is at greatest risk of developing diabetic kidney disease is an important clinical need.”
To develop their risk prediction model, the researchers leveraged clinical data from over 1,200 patients with type 2 diabetes in the Hong Kong Diabetes Register. Using these data, the algorithm identifies biomarkers for diabetic kidney disease by measuring DNA methylation, a biological process characterize by subtle changes in DNA that can alter gene expression.
DNA methylation can be measured via simple blood tests, and the researchers used the biomarkers identified during this process to predict current and future kidney function. These predictions, the research team indicated, could be used alongside standard methods for evaluating a patient’s kidney disease risk.
The model was validated on a separate cohort of 326 Native Americans with type 2 diabetes.
Moving forward, the researchers aim to refine and expand their approach to other conditions, such as treatment-resistant cancer.
“The science is still evolving, but we are working on incorporating additional information into our model to further empower precision medicine in diabetes,” stated Ma.
