Google Searches Might Successfully Predict Heroin Overdoses

Data on heroin overdose continues to be scarce.

Considering the global health epidemic that death due to drug overdose has become, efforts are being taken worldwide to explore different avenues to improve the situation.

One such initiative is a study to determine whether data on opioid-related internet searches can predict future heroin-related admissions to emergency departments.

The basic assumption underlying the research was the understanding that some people searching for information on heroin and other opioids might overdose in the near future.

In order to test this, the researchers obtained data on Google searches for prescription and non-prescription opioids and Susbtantive Abuse and Mental Health Services Administration (SAMHSA) data on heroin-related emergency department visits, across nine metropolitan statistical areas in the United States.

The best-fitting model explained 72% of the variance inheroin-related ED visits. The final model included the search keywords“Avinza,” “Brown Sugar,” “China White,” “Codeine,” “Kadian,” “Methadone,” and“Oxymorphone.”     

They also found regional differences in where and how people searched for opioid-related information.

The researchers concluded that internet search-based modeling can be explored as a new source of insights for predicting heroin-related admissions. They wrote,

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.