A study of a unique collection of data could help to determine the variables that contribute to substance abuse disorder, according to Ohio University officials.

The state of Ohio has created its first data lake project by building an infrastructure that allows data sets from across state agencies to be shared, compared for different variables and then analyzed. Ohio University is one of three state universities chosen to study the information.

The Ohio Alliance for Innovation in Population Health (The Alliance) — a joint venture created by OHIO’s College of Health Sciences and Professions and the University of Toledo — is partnering with DeLoitte Inc. to comb through more than four petabytes of data. One petabyte equals 1,024 terabytes. As a comparison, the Hubble Telescope transmits around 10 terabytes of data each year and has a total archive of just over 150 terabytes, according to NASA.

Much of the data lake’s information has to do with health, said Rick Hodges, director of The Alliance.

“Being able to pull all of those data sources from across the state into one place allows researchers to compare variables across agencies. That includes law enforcement data on people who have overdosed on opiates. This is new science for health and not just for health but all disciplines of state government,” said Hodges.

Hodges shared that studying the data could yield additional insight into addiction, including job loss, criminal activity, the illegal use of prescription medication and more.

“We’re trying to do regression analysis to see which factors are most leading to addiction and if they in fact show a higher risk of addiction when those factors are present,” Hodges said. “Health providers and law enforcement would be able to intervene a lot faster and earlier in the disease.”

Deloitte Inc., has been tasked with sorting all the data lake’s information while The Alliance will identify the important social determinants and ensure appropriate and accurate results.

“We’re excited for this project and to be able to work collaboratively with OHIO to solve a number of questions,” said Jeremy Jackson, senior manager of Deloitte. “Who is at risk, who is likely to overdose … We want to be able to use that data to provide insight to help triage resources to focus more acutely on individuals.”

The scope of the data for Deloitte refers to the population of those who are or have been incarcerated; however, Jackson pointed out that the data will be applicable to other groups of people too.

“Healthcare providers could use the data for prediction, create a focus for particular segments of the population and affect prescribed medication and treatments,” Jackson said. “This can potentially change how we think about solving the epidemic and addiction problem. We’d like to tip the balance toward identifying at-risk populations and intervene earlier to help create a better trajectory and not have to deal with all the challenges of opioid addiction. This has the potential to change the game.”

Deloitte is hoping to have preliminary results ready by April and work completed by the end of June.