Machine learning predicts heart failure risk for type 2 diabetes patients
Researchers have identified the 10 top predictors of future heart failure for patients living with type 2 diabetes by using a machine learning model that generates a risk score.
The risk score, called WATCH-DM, was developed by a team of investigators—led by Brigham and Women's Hospital and UT Southwestern Medical Center—that leveraged data from more than 8,700 diabetic patients enrolled in the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial.
Using a nonparametric decision tree machine learning approach, they found 10 top-performing predictors of heart failure: weight (BMI), age, hypertension, creatinine, HDL-C, diabetes control (fasting plasma glucose), QRS duration, myocardial infarction and coronary artery bypass grafting.
Results of their study were published in the journal Diabetes Care and presented at the Heart Failure Society of America Annual Scientific Meeting, held September 13 to 16 in Philadelphia.
In their study, diabetic patients with the highest scores from WATCH-DM—which is currently available as an online tool for clinicians to use—had a five-year risk of heart failure approaching 20 percent.
“Our risk score provides a novel prediction tool to identify patients who face a heart failure risk in the next five years,” said co-first author Matthew Segar, MD, a resident physician at UT Southwestern. “By not requiring specific clinical cardiovascular biomarkers or advanced imaging, this risk score is readily integrable into bedside practice or electronic health record systems and may identify patients who would benefit from therapeutic interventions.”
Going forward, researchers are working to integrate the risk score for clinical use into EHR systems at both Brigham and Women's and UT Southwestern.
“We hope that this risk score can be useful to clinicians on the ground—primary care physicians, endocrinologists, nephrologists and cardiologists—who are caring for patients with diabetes and thinking about what strategies can be used to help them," said co-first author Muthiah Vaduganathan, MD, a cardiologist at Brigham and Women's.