Harnessing the Power of Data: Predicting Opioid Overdose Deaths with Machine Learning

The opioid crisis is one of the most pressing public health concerns facing the United States today.
According to the Centers for Disease Control and Prevention (CDC), more than 500,000 people have died from opioid overdoses since 2000.
This crisis has had devastating effects on families and communities across the country, and it has become clear that a more comprehensive approach is needed to address the problem.

Our team, consisting of Anastassia Tatarskaja, Iris Belensky, Milos Popov, Olga Mironova, and Patrick Gilchrist from the University of Denver, has chosen to tackle this issue by using machine learning algorithms to predict the rate of opioid overdose deaths in US counties.
By analyzing various socio-economic variables and opioid dispensing rates, we hope to identify patterns in historical data that can be used to predict future trends and inform more effective allocation of resources.

Our data sources include:

• Detailed mortality data from the CDC WONDER database
• Educational attainment data from the USDA
• Unemployment and median household income data from the USDA
• Personal income data from the Bureau of Economic Analysis
• Opioid dispensing rates based on prescriber location, provided by the CDC

Our ultimate goal is to use this analysis to inform targeted prevention and intervention strategies that can help reduce the number of opioid overdose deaths in the United States.
We believe that by taking a data-driven approach, we can make a meaningful contribution to this critical issue and help improve the lives of those affected by the opioid crisis.

Year: State: County: Filter

Year	State	County Code	County	Population	Deaths	Crude Rate	Dispense Rate	Personal Income	Per Capita Personal Income	Less Than High School	High School Diploma Only	Some College	Bachelor or Higher	Poverty Population	Poverty Rate	Unemployed Population	Unemployed Rate