Need to Know How Busy Your ED Will Be? Google It.
October 9th, 2016
STOCKHOLM, SWEDEN – Need to know how many patients will show up at your ED tomorrow? In the near future, you might just be able to ask Google and other search engines.
That’s according to a study finding that the correlation between Internet searches on a regional medical website and next-day visits to regional emergency departments was “significant.” The report was published online recently in the Annals of Emergency Medicine.
“Website visits may be used to predict ER visits for a geographic region as well as for individual hospitals,” said lead study author Andreas Ekstrom, MD, of Karolinska Institutet in Stockholm. “Looking forward, we might be able to create a model to predict emergency department visits that would enable better matching of personnel scheduling to ER volumes.”
For the study, the researchers used Google Analytics, tallying and graphing Internet searches of the Stockholm Health Care Guide (SHCG), a regional medical website, over a 1-year period. ED visits were then compared over the same time period.
The study included all types of ED visits – such as adult and pediatric – and used the period of Aug. 13, 2011, to Aug. 12, 2012, as a training set for the model. The hourly variation of visits was analyzed for both website and the ED visits to determine the interval of hours to be used for the prediction, and the model was then validated with mean absolute percentage error for Aug. 13, 2012, to Oct. 31, 2012.
Results indicate that online visits to the SHCG between 6 p.m. and midnight were significantly correlated to the number of ED visits the next day.
Overall, the error rate when individual hospitals ED visits were based on Internet searches ranged from 5.2% to 13.1%.
The study found that ED visits typically were highest on Mondays and lowest during weekends, with peak visits occurring at noon and then slowly decreasing during the rest of the day. With the lowest number of ED visits three days around Christmas, New Year and the midsummer holidays, the fewest number of Internet searches occurred during the same time period.
“Website visits may be used in this fashion to predict attendance to the ED,” the authors conclude. “The model works both for the entire region and for individual hospitals. The possibility of using Internet data to predict ED visits is promising.”
“For this type of information to be useful, it is important that we be able to predict emergency department visits further into the future than the next day,” Ekstrom added. “This may be possible by further investigating the correlation between website statistics and ER visits. This has the potential benefit of reflecting ongoing behavioral trends, which may allow us to adapt to sudden changes in patient behavior when predicting ER visits."