Three big data tools win HHS opioid code-a-thon

By Jonah Comstock
04:05 pm

Last week, the HHS' opioid crisis code-a-thon concluded with presentations by nine of the 50 teams that participated. Three of these teams were chosen as the competition's winners, and will receive $10,000 to further develop their ideas.

“When the government holds a code-a-thon, there’s an admission in society that we have hit a roadblock, that we need help, and we go out to the polity to help us,” HHS Chief Technology Officer Bruce Greenstein said at October's Connected Health Conference, where the event was announced. “Maybe it’s not unique around the world, but it’s certainly rare when a government admits that it’s stuck and needs help from its people. And this is one of the most participatory forms of the relationship between a government and its polity, for maybe one of the most important, pressing questions and problems in our society today. I take it very, very seriously.”

Over two days, more than 300 coders got access to federal, state, and private datasets, including HHS datasets that had never before been made public. They also saw presentations from different stakeholders who talked about their own experience with the opioid crisis. Ultimately, teams had 24 hours to create a prototype in one of three categories: opioid abuse prevention, access to treatment, and healthy clinical opioid usage.

The winning team in the prevention category was from Visionist, an IT company in Columbia, Maryland. They created a program to help opioid users locate drug takeback programs. The data visualization tool allows public health specialists as well as individuals to see not only where the takeback programs are, but what areas have negative ratios, with a lot of opioid abuse and few takeback programs. This can help target interventions and new programs to the areas where they'll do the most good.

"We really started the hackathon by asking ourselves, if we wanted to have an impact on individuals, preventing them from developing an opioid addication in the first place, where would we start?" Taylor Corbett, the Visionist spokesperson at Friday's team presentations, said. "So we looked at CDC data and we found that, for the most part, individuals that abuse opioids are not obtaining them from drug dealers. The majority are obtaining them from their families. Over 70 percent of individuals that abuse opioids obtain them or borrow them or steal them from their families. Our hypothesis was, individuals are getting these meds because they’re left over from an operation or something like this. What can we do to get those drugs out of circulation?"

The other two finalists in the prevention track took other interesting approaches. One used social media to identify illicit online pharmacies and report them to the authorities. Another used big data to predict outbreaks and warn first responders to stock up on Narcan or make other preperations.

The winner in the treatment track was called Oragami Innovations and hailed from Yale University. They used the data provided to focus specifically on their community in North Haven, and created a model to track and predict overdoses. 

"By prediciting the future and working on resource allocation, regardless of size or data collection abilities, we believe this platform can save lives as soon as tomorrow in New Haven and in your community," Matthew Erlendson, an Origami Innovations team member, said at the event.

Another finalist in the treatment category, Pivot Health, created an app for opioid abusers that would give them coupons for buying Narcan, promote safer routines for drug use, and allow them to report bad drugs and dealers. The third finalist, a team from Mobile Commons, built a text message intervention to help family members of opioid abusers to support their loved ones.

OPAT (Opioid Prescriber Awareness Tool) was the winner of the usage category. They used the data to create a tool for physicians that would help them understand their own prescribing patterns relative to those of colleagues to get a sense of when they might be prescribing too much. The tool also helps physicians choose better referrals for patients at risk for abuse by seeing how likely those specialists are to prescribe opioids.

"As a society we’ve changed the rules for you as a physician," OPAT team leader Alex Rich said during his presentation. "We’ve decided we taught you something that wasn’t true. And we’ve decided that you and your colleagues are partially at fault for one of the greatest public health epidemics in the history of this country. It’s not fair and it’s difficult."

Another team in the usage category created a patient-facing web app that lets people assess their own risk for opioid addiction, which can inform conversations with doctors. Another team built an app for Epic's App Orchard that would intervene with physicians as they wrote opioid prescriptions, asking questions and providing prompts that might help prevent overprescribing.


The latest news in digital health delivered daily to your inbox.

Thank you for subscribing!
Error! Something went wrong!