Using big data analytics can predict the risk for developing metabolic syndrome, and help guide individualized treatments, a recent study says.
Big data is being touted as a game changer in healthcare because it can process huge amounts and complex types of information to solve problems. One among many initiatives toward this end is for the screening and prevention of one of the most insidious conditions afflicting many people worldwide: metabolic syndrome.
Metabolic syndrome is a worsening problem globally. According to Medscape, approximately one-fourth of the population in the United States, Europe, and Latin America is believed to have metabolic syndrome. Its incidence is also rising in East Asia and the Middle East, where a parallel epidemic of obesity is happening.
There are five metabolic risk factors: abdominal obesity, high triglycerides, low HDL cholesterol, high blood pressure, and high fasting blood sugar. One must have three of these to be diagnosed, but it is not that hard to have these risk factors all at the same time because they tend to occur together.
Having metabolic syndrome dramatically raises the risk for developing heart disease, diabetes, and stroke -- all major killers. Applying lifestyle changes -- weight loss, healthy diet, exercise -- can lower the risk.
But another key step could be timely screening for metabolic risks so that early intervention could be done.
The insurance company Aetna and GNS Healthcare Inc. recently conducted such an early screening program for nearly 37,000 volunteer members. The volunteers consented to the use of their medical records to be accessed and analyzed using GNS’ proprietary, supercomputer-enabled, big data analytics platform called Reverse Engineering and Forward Simulation (REFS). The data sets from two “Comprehensive Metabolic Syndrome Screenings” analyzed included demographic data, medical/pharmaceutical claims, laboratory tests, and biometric screening results, as well as responses to questionnaires.
Results of the study published recently in the American Journal of Managed Care, showed that in just three months, the big data analytical models accurately “predicted subsequent risk of metabolic syndrome, both overall and by risk factor, on population and individual levels, with ROC/AUC varying from 0.80 to 0.88.”
Using all the demographic and clinical data for every volunteer, the platform calculated the risk of developing one or additional metabolic risk factors in terms of percentage. It also accounted for adherence to treatment and patient compliance in determining individual risk.
The authors, wrote, “We demonstrated that improving waist circumference and blood glucose yielded the largest benefits on subsequent risk and medical costs. We also showed that adherence to prescribed medications and, particularly, adherence to routine scheduled outpatient doctor visits, reduced subsequent risk.”
“The breakthrough in this study is that we are able to bring to light hyper-individualized patient predictions, including quantitatively identifying which individual patients are most at risk, which syndrome factors are most likely to push that patient past a threshold, and which interventions will have the greatest impact on that individual,” Colin Hill, chief executive officer of GNS, said in a press release.
Addressing metabolic syndrome is of great interest to all stakeholders in healthcare. The trio of heart disease, diabetes and stroke -- all sequels of metabolic syndrome -- collectively costs the U.S. healthcare system more than half a trillion dollars, and claims 800,000 lives per year, according to the American Heart Association and American Diabetes Association.
Screening tests and interventional programs using big data analytics can provide an accurate risk assessment for patients and can lower the chance of developing metabolic risk factors. The researchers believe that there is great potential for big data in helping curb this increasingly prevalent problem in many countries worldwide.
