Can A Google Search Predict An Overdose?

By Kelly Burch 12/18/18

Researchers examined whether Internet search data from Google could help them predict where an overdose will occur.

Men around a globe predict overdose after viewing Google Search

Technology has no doubt played a role in the opioid epidemic, with drug users and dealers able to order narcotics online and have them delivered directly to their homes. Now a new study suggests that the internet could also play an important role in alleviating the crisis by helping to predict opioid overdoses. 

The study, titled “Internet searches for opioids predict future emergency department heroin admissions,” was published in the September issue of the journal Drug and Alcohol Dependence and reported in Scientific American last week

Sean D. Young, a researcher at the University of California Institute for Prediction Technology, led a team that analyzed Google search prevalence of opioid-related terms, including “Avinza,” “Brown Sugar,” “China White,” “Codeine,” “Kadian,” “Methadone,” and “Oxymorphone.”

The researchers compared that data to heroin-related emergency room visits in nine different areas around the US over the following year. They found that in the best model, search data could explain 72% of the variance in emergency department visits. Overall, the more a keyword was searched, the more opioid-related hospitalizations were likely to happen in that region in the next year. 

“Internet search-based modeling should be explored as a new source of insights for predicting heroin-related admissions,” the study authors wrote

Internet search data could be particularly important in areas where there is little information on the drug epidemic. Analyzing the data is a cost-effective way of predicting how opioid abuse might change in the upcoming year, they said. 

“In geographic regions where no current heroin-related data exist, Internet search modeling might be a particularly valuable and inexpensive tool for estimating changing heroin use trends,” the authors wrote. “We discuss the immediate implications for using this approach to assist in managing opioid-related morbidity and mortality in the United States.”

Researchers said this tool could be important for helping to understand and prevent overdose deaths. For example, in areas expecting to see an increase in drug-related hospital visits, community organizations could distribute more doses of naloxone, the opioid overdose reversal drug. 

“For a number of fiscal and practical reasons, data on heroin use have been of poor quality, which has hampered the ability to halt the growing epidemic," the researchers wrote. “Internet search data, such as those made available by Google Trends, have been used as a low-cost, real-time data source for monitoring and predicting a variety of public health outcomes.”

Please read our comment policy. - The Fix
Kelly Burch Contrib.jpg

Kelly Burch writes about addiction and mental health issues, particularly as they affect families. Follow her on TwitterFacebook, and LinkedIn.