A unique approach using artificial intelligence and social media posts could predict opioid mortality rates, researchers report.

The findings revealed that a sophisticated AI algorithm was able to predict opioid death rates—going back from previous years 2011 to 2017—much more accurately than using traditional information researchers and clinicians often use, such as prior rates in communities and socio-economic measures.

Clinicians and other professionals trying to stop the opioid crisis in the United States need all the tools they can to accurately identify communities at risk of large increases in deaths from opioid use and prevent deaths.

According to the National Center for Health Statistics, the US has been tackling an opioid epidemic for more than two decades. Age-adjusted opioid-related deaths have increased by some 350% over the 20 years of 1999 to 2020.

As reported in Nature Digital Medicine, the researchers created TrOP (Transformer for Opioid Prediction), a new model for community-specific trend projections that uses community-specific social media language, along with past opioid-related mortality data to predict future changes in opioid-related deaths.

According to the authors, TrOP builds on recent advances in sequence modeling, namely transformer networks, to use changes in yearly language on Twitter, as well as past mortality, to project the following year’s mortality rates in many US counties.

They used language data derived from the County Tweet Lexical Bank, a dataset that contains word usage on Twitter collected from more than 2,000 US counties starting from 2011. They built yearly topics or groupings that appeared together for each county from 2011 to 2017.

Using this language data as a central point, they combined it with data queried from the Centers for Disease Control and Prevention to gather the yearly opioid-related deaths per county. They then limited the full dataset to only US counties that reported opioid-related deaths for all of the years 2011 to 2017. This totaled data from 357 counties, which includes some 212 million people thus nearly two-thirds the population of the US.

Read the full article about tracking opioid deaths with AI by Gregory Filiano at Futurity.