UT Southwestern researchers have developed a machine learning-based algorithm combining three variables routinely collected during clinic visits. The breakthrough showcases how bioinformatics can transform patient care. The team’s work will be published July 15 in the American Journal of Cardiology. According to MedicalXpress it “describes a risk prediction model in which patient age, urinary albumin/creatinine ratio (UACR), and cardiovascular disease history successfully identified hypertensive patients for which the benefits of intensive therapy outweigh the risks.”
A lead study author was Dr. Yang Xie, Director of the Quantitative Biomedical Research Center, UT Southwestern and of the University’s Bioinformatics Core Facility.
The researchers leveraged National Institutes of Health-funded data. The NIH randomized controlled trials tested intensive vs. standard blood pressure-lowering treatments; the Systolic Blood Pressure Intervention Trial (SPRINT) and the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial. The SPRINT trial included 9,361 nondiabetic hypertensive adults at an elevated risk of cardiovascular event; ACCORD enrolled 10,251 patients with Type 2 diabetes.
Dr. Xie and the team are to be commended for leveraging the power of machine learning in bioinformatics to help medical community identify high risk patients that most likely benefit from intensive blood pressure reduction. There are undoubtedly breakthrough potential but also implications As Wanpen Vongpatanasin Professor of Internal Medicine explained “long-term intensive HBP drug therapy can reduce risk of heart failure and death but it also carries an increased risk of side effects.”
Dr Xie stated “we feel that our findings have major clinical implications, since in addition to its predictive effects, the model generated here is simple and easy to implement in clinical practice without additional lab tests or computational tools.”
View article hereSource: Medical Xpress