On October 14th-15th, 2018, teams of computer and data scientists, public health officials, researchers, and patients/families affected by the opioid crisis traveled across the country to compete on finding software and big data-based solutions to the opioid crisis at the University of California Institute for Prediction Technology’s (UCIPT’s) “The Opioid Hackathon”.
To kick off the two-day event, UCIPT held an opioid-focused speaking symposium, including federal, state, and local politicians, researchers, and patients/families affected by the opioid crisis.
After the conclusion of the symposium, the hackathon officially began, allowing teams 24 hours to think of and develop new solutions across 4 opioid crisis-related tracks. Prizes included $5,000 for each of the 4 tracks, mentorship with design experts, and travel expenses for teams to continue meeting with key stakeholders and develop and implement their solutions into public health settings.
The Opioid Hackathon 2018 demonstrated that dynamic, effective solutions for saving lives may be possible and should be further explored using the hackathon model. UCIPT is excited to explore using hackathons in other public health applications in the future. We wish to thank the following sponsors for their funding and/or in-kind sponsorship: NIH, NIDA, NIAID, IEEE Standards Association (IEEE SA), Socrata, Clinical Blockchain, and the UCI Institute for Clinical and Translational Science (ICTS). The project received funding through grant R01AI 132030 [NIAID].
The four winners focused on:
- iPill, an application that regulates opioid dispensing for a patient while offering alternatives to taking the opioid pill.
- A Recovery intervention that incorporates clinical trial data to improve treatment
- Use of machine learning to predict opioid overdose deaths in California.
- Use of open source data analysis to predict opioid overdose and help reduce opioid
For more information, please contact:
Dr. Sean Young, Executive Director/Associate Professor, University of California Institute for Prediction Technology, UCLA School of Medicine at [email protected].