Predicting Disease Risk with Big Data

June 30, 2014
Marie Daghlian

Study shows large-scale patient data analytics can help with early interventions for patients at risk of metabolic syndrome and reduce their medical costs.

This article published with permission from The Burrill Report.

A study analyzing 37,000 patient healthcare records demonstrated that big data analytics of the medical records could predict future risk of metabolic syndrome. Health insurance provider Aetna and big data analytics firm GNS Healthcare conducted the research, which was published in the American Journal of Managed Care.

“This study demonstrates how integration of multiple sources of patient data can help predict patient-specific medical problems,” says lead author Gregory Steinberg, head of clinical innovation at Aetna Innovation Labs. “We believe the personalized clinical outreach and engagement strategies, informed by data from this study, can help improve the health of people with metabolic syndrome and reduce the associated costs.”

More than a third of Americans have metabolic syndrome, a group of 5 risk factors—large waist size, high blood pressure, high triglycerides, low HDL cholesterol, and high blood sugar. When an adult has 3 or more of these risk factors, he is 5 times as likely to develop diabetes, and twice as likely to develop heart disease or have a stroke. Combined, these conditions account for almost 20% of overall health care costs in the United States.

The study not only predicted future risk, but also revealed personalized interventions that could mitigate the 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,” says Colin Hill, co-founder and CEO of GNS.

The GNS automated data analytics platform was paired with Aetna’s deep clinical expertise to produce results on extremely large datasets in just three months. GNS analyzed data from nearly 37,000 members of one of Aetna's employer customers who had voluntarily participated in screening for metabolic syndrome. The data analyzed included medical claims records, demographics, pharmacy claims, lab tests and biometric screening results over a 2-year period.

Aetna and GNS used 2 distinct analytical models in the study: a claims-based-only model to predict the probability of each of the 5 metabolic syndrome factors occurring for each study subject; and a model based on both claims and biometric data to predict whether each study subject is likely to get worse, improve or stay the same for each metabolic syndrome factor.

Both analytical models predicted future risk of metabolic syndrome on both a population and an individual level. The researchers were able to develop detailed risk profiles for each individual that included which combination of the 5 metabolic syndrome factors that person exhibited and are at risk for developing. For example, in an individual patient who exhibited 2 of the 5 risk factors, researchers could predict which third factor is the most likely to develop.

The models also helped identify individual variable impact on risk associated with adherence to prescribed medications, as well as adherence to routine scheduled doctor visits. A scheduled visit with a primary care doctor lowers the one-year probability of having metabolic syndrome in nearly 90% of individuals. In addition, the study found that improving waist circumference and blood glucose yielded the largest benefits on patients’ subsequent risk and medical costs.

Copyright 2013 Burrill & Company. For more life sciences news and information, visit The Burrill Report.