Short Attention Span Summary
Tweet says, “I’m fixin’ to get plastered.”
Not surprisingly, when lots of people are tweeting about alcohol, more people show up in the ED with alcohol related problems. This seems intuitive, but it’s the first time this has been studied and the association made scientifically. The future seems to be that staffing decisions and surge capacity measures be anticipated based on aggregate data from social media. Twitter has already been studied to predict ED visits for asthma. You smart guys get to work @grahamwalker @M_Lin!
Take Home
Using smart software, aggregate data from social media has the potential to inform us as to what we may expect to see in the ED.
Abstract
Acad Emerg Med. 2016 Jul;23(7):831-4. doi: 10.1111/acem.12983. Epub 2016 Jun 20.
Ranney ML1, Chang B2, Freeman JR3, Norris B4, Silverberg M5, Choo EK1.
Author information:
1Emergency Digital Health Innovation Program, Department of Emergency Medicine, Rhode Island Hospital/Alpert Medical School, Brown University, Providence, RI.
2Department of Emergency Medicine, University of California at San Francisco, San Francisco, CA.
3Department of Biostatistics and Epidemiology, School of Public Health and Health Sciences, University of Massachusetts-Amherst, Amherst, MA.
4Perscio, Fishers, IN.
5Socrata, Washington, DC.
Abstract
BACKGROUND:
Alcohol use is a major and unpredictable driver of emergency department (ED) visits. Regional Twitter activity correlates ecologically with behavioral outcomes. No such correlation has been established in real time.
OBJECTIVES:
The objective was to examine the correlation between real-time, alcohol-related tweets and alcohol-related ED visits.
METHODS:
We developed and piloted a set of 11 keywords that identified tweets related to alcohol use. In-state tweets were identified using self-declared profile information or geographic coordinates. Using Datasift, a third-party vendor, a random sample of 1% of eligible tweets containing the keywords and originating in state were downloaded (including tweet date/time) over 3 discrete weeks in 3 different months. In the same time frame, we examined visits to an urban, high-volume, Level I trauma center that receives > 25% of the emergency care volume in the state. Alcohol-related ED visits were defined as visits with a chief complaint of alcohol use, positive blood alcohol, or alcohol-related ICD-9 code. Spearman’s correlation coefficient was used to examine the hourly correlation between alcohol-related tweets, alcohol-related ED visits, and all ED visits.
RESULTS:
A total of 7,820 tweets (representing 782,000 in-state alcohol-related tweets during the 3 weeks) were identified. Concurrently, 404 ED visits met criteria for being alcohol-related versus 2939 non-alcohol-related ED visits. There was a statistically significant relationship between hourly alcohol-related tweet volume and number of alcohol-related ED visits (rs = 0.31, p < 0.00001), but not between hourly alcohol-related tweet volume and number of non-alcohol-related ED visits (rs = -0.07, p = 0.11).
CONCLUSION:
In a single state, a statistically significant relationship was observed between the hourly number of alcohol-related tweets and the hourly number of alcohol-related ED visits. Real-time Twitter monitoring may help predict alcohol-related surges in ED visits. Future studies should include larger numbers of EDs and natural language processing.
© 2016 by the Society for Academic Emergency Medicine.
PMID: 27062454 [PubMed – in process]
