JMIR Publications

ABSTRACT

Background:

Opioid overdose deaths (OODs) constitute a significant public health burden for the United States. The most recent statistics indicate that of the 70,237 drug-overdose related deaths in 2017, 68% (47,600) were attributed to opioids. OODs involving synthetic opioids (e.g., fentanyl) increased notably (46%) from 2016 to 2017. Reflecting on the shifting nature of the OOD crisis, Dasgupta, Beletsky, and Ciccarone [2] offer a tri-phasic framework to explain that OODs shifted from prescription opioids for pain (beginning in 2000), to heroin (2010-2015), and then to synthetic opioids (beginning in 2013). Given the rapidly shifting nature of OODs, timelier surveillance data are critical to inform strategies that combat the opioid crisis. Using easily accessible and near real-time social media data to improve public health surveillance efforts related to the opioid crisis is a promising area of research.

Objective:

The current study explored the potential of using Twitter data to monitor the opioid epidemic. Specifically, this study investigated the extent to which content of opioid-related tweets (1) corresponds with the triphasic nature of the opioid crisis as well as (2) correlates with and (3) predicts OODs in North Carolina between 2009-2017.

Methods:

Opioid-related Twitter posts were obtained using Crimson Hexagon, and were classified as relating to prescription opioids, heroin, and synthetic opioids using natural language processing (NLP). This process resulted in a corpus of 100,777 posts consisting of tweets, retweets, mentions, and replies. Using a random sample of 10,000 posts from the corpus, we identified opioid-related terms by analyzing word frequency for each year. In addition, OODs were obtained from the Multiple Cause of Death database from CDC WONDER [10]. Least squares regression and Granger tests compared patterns of opioid-related posts with OODs.

Results:

The pattern of tweets related to prescription opioids, heroin, and synthetic opioids resembled the tri-phasic nature of OODs. For prescription opioids, tweet counts and OODs were statistically unrelated. Tweets mentioning heroin and synthetic opioids were significantly associated with heroin OODs and synthetic OODs in the same year (p=.01 and p<.001, respectively), as well as in the following year (p=.03 and p=.01, respectively). Moreover, heroin tweets in a given year predicted heroin deaths better than lagged heroin OODs alone (p=.03).

Conclusions:

Findings support using Twitter data as a timely indicator of opioid-overdose mortality, especially for heroin.