The opioid epidemic has had a major impact in Long Island, in particular on underrepresented groups. Long Island, made up of Nassau County and Suffolk County, has a total population of 2.8 million. The region has experienced the highest number of opioid deaths in New York State, and the state has one of the highest rates (top 5) of drug overdoses in the nation.
This map demonstrates the "Opioid Health Burden" by county in New York State by the 2019 crude rate per 100,000 population. This health burden is quantified using a collection of the following data:
- Opioid overdose deaths
- Non-fatal opioid-related emergency department visits
- Non-fatal opioid-related hospital discharges
Visit the New York State Department of Health for more detailed opioid-related data.
Methods and studies to address the epidemic at the community or patient level are needed in order create targeted interventions.
AI and Big Data Driven Opioid Epidemic Research (AI4OE)
SBU researchers created AI4OE to coordinate research efforts to Long Island's opioid epidemic on by integrating New York State's published county level data, community input, and informatics tools. They aim to break through bottlenecks in clinical and translational science addressing opioid use on Long Island and across the nation.
Predictive Modeling for Early Opioid Risk Identification
Only about 22% of people with Opioid Use Disorder (OUD) receive specific treatment. Most remain at high overdose (OD) risk that is clinically under-identified. There is a critical need to identify individuals at using opioids who would then be at increased risk for escalating prescription opioids use, OUD severity, or opioid overdose. Our opioid risk prediction models use temporal deep learning with big EHR Data, taking advantage of large number of EHR features and sequential deep learning methods for both OD and OUD.
Geospatial Modeling
Taking a data driven approach to study community and region level patterns and variations at fine spatial resolutions, and the impact of demographic and socio-economical factors on opioid epidemic. We also discover resource disparities in NY, which needs to be improved.
Social Media Analytics
Analyzing opioid-related social media posts has the potential to reveal patterns of opioid abuse at a national scale, and understand opinions of the public and opioid users. We have performed various analysis on social media, including spatial-temporal trends of opioid use, content analysis, types of users and their background, and suicide intention.