More and more Americans are dying from drug overdoses, and this predictive model could tell us where there will be an outbreak

More and more Americans are dying from drug overdoses, and this predictive model could tell us where there will be an outbreak

Researchers at the University of California, San Diego School of Medicine, San Diego State University (SDSU) have designed and validated a predictive model to target people at risk for future outbreaks of overdose death .

To do this, they have used the patterns of these drug-related deaths in the United States in the last twenty years: the number of Americans dying each year from drug overdoses has risen steadily, from less than 20,000 in 1999 to more than 80,000 in 2020.

Opioid overdose

The opioid epidemic has been described as a triple overlapping wave of fatal overdoses due to prescription opioids, heroin, and highly potent synthetic opioids, including fentanyl. The researchers used this third wave to investigate whether a tool could be developed to predict and prevent deaths . According to first author Charlie Marks:

This study provides a novel and rigorously validated tool to inform policy planning in the context of emerging drug-driven overdose epidemics and sets a new standard for developing a data-driven response to drug use epidemics.

Using CDC data from 2013 (when the fentanyl epidemic began) to 2018 (the most recent data available at that time), the research team designed and trained a retrospective statistical model to find patterns in the relationship between county characteristics. and overdose deaths, then used the data to predict death rates in the next year. Finally, the predictions were compared to the actual overdose death rates in each county .

Further refinement of the model and the security of access to restricted data through extensive collaborations will be the next steps to improve model performance. Imagine if we could develop prediction tools for substance use epidemics, similar to what was developed to predict COVID-19 infections and deaths .