Skip to main content

Our Employee Was Inspired To Hack New Ways To Solve Opioid Misuse

By Samantha Poole and Taylor Shaw | March 25, 2019 | Life at Blue Cross NC

Feature Blog Image

Opioid misuse is a big problem in North Carolina. Over the past year, Blue Cross and Blue Shield of North Carolina (Blue Cross NC) has made significant progress in solving the problem. This issue, which touches every corner of our state, inspired one Blue Cross NC employee to act, or should we say “hack.”

On February 22, Data and Analytics employee Olajide “Ola” Ajayi participated in the Queen City Hackathon — Charlotte’s largest data science and machine learning hackathon. This event, organized by the Analytics and Big Data Society of Charlotte, aimed to use data to solve social issues. One of the topics this year was opioid substance abuse prevention.

The Challenge

Event participants were tasked with creating a tool, policy, predictive model, or other pieces of software to help government officials and health professionals more effectively use their time and resources to combat the negative effects of opioid misuse in the United States.

Oh, and one more thing. The event began at 5 p.m. on a Friday and ended at 11 a.m. the next day.

Ajayi used his skills to understand more than one million rows of data on patients and prescriptions to come up with insights on which actions would be most impactful for lowering opioid misuse in North Carolina.

“The data they gave us came from [the Centers for Medicare and Medicaid Services] – so it was real, national data that contained over a million records and about 82 variables,” Ajayi said.

He and his team also looked at variables for loneliness — marital status, number of people in the household — in addition to other variables like physical activity, physical environment, and dentist visit rate.

While writing the code for the model, the team realized that the most important variable happened to be education level.

“It was clear that counties with a high percentage of college graduates have a lower proportion of opioid usage and vice versa,” said Ajayi.

He coded until 2 a.m. and woke up at 5 a.m. to finish the job.

Next Steps

The team is waiting to find out exactly how the Analytics and Big Data Society of Charlotte will use their predictive model to help address opioid misuse, but they’re excited for what’s next.

This is just one of the many examples of how our Data and Analytics team works to make breakthroughs like this every day.

During his time at Blue Cross NC, Ajayi has also created an artificial intelligence model that can look at mammograms and other factors, like blood work, to diagnose breast cancer at a 99.7 percent accuracy rate.