JMIR Publications

ABSTRACT

Background:

There was an estimated 100,000 drug overdose deaths between April 2020 and April 2021, a three-quarters increase from the prior 12-month period. There is an approximate six-month reporting lag for provisional counts of drug overdose deaths from the National Vital Statistics System, and the highest level of geospatial resolution is at the state level. By contrast, public social media data are available close to real-time and are often accessible with precise coordinates.

Objective:

We sought to assess whether small area overdose mortality burden could be estimated using opioid-related social media data.

Methods:

ICD codes for poisoning/exposure to overdose at the county level were obtained from CDC Wonder. Demographics were collected from the American Community Survey. The Twitter API was used to obtain tweets which contained any of 36 terms with drug names. An unsupervised classification approach was used for clustering tweets. Population-normalized variables and polynomial population-normalized variables were produced. Furthermore, z-scores of the Getis Ord Gi clustering statistic were produced, and both these scores and their polynomial counterparts were explored in regression modeling of small area overdose mortality burden.

Results:

Modeling of overdose mortality with normalized demographic variables alone explained only 7.4% of the variability in county-level overdose mortality, whereas this was approximately doubled by the use of specific demographic and social media covariates based on a backwards selection approach.

Conclusions:

Social media data, when transformed using certain statistical approaches, may add utility in the goal of producing closer to real-time small area estimates of overdose mortality.