Using Internet Searches To Forecast Emergency Room Visits

In order to provide adequate service, hospitals need to anticipate how many patients will visit at any given time.

While seasonal flu viruses are somewhat predictable, on most occasions the flow of patients is less certain.

In a new study, Swedish researchers were able to use Internet searches to accurately predict the approximate number of emergency room visits, reports Science Daily.

For the study, the researchers used Google Analytics to compare Internet searches on a regional medical website with visits to the emergency room on the following day for a one-year period.

The researchers found that the number of searches for the Stockholm Health Care Guide between 6:00 p.m. and midnight were highly correlated to the number of emergency room visits the following day.

Overall, the data showed the highest correlation for the whole country. While individual hospital data showed a correlation, it varied among hospitals.

For scheduling personal, the number of visits was usually highest on Mondays and the least busy on the weekends. The busiest time during the day was usually around noon.

“Website visits may be used to predict ER visits for a geographic region as well as for individual hospitals,” said Andreas Ekstrom, of the Karolinska Institutet in Stockholm, Sweden and the lead author of the study. “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 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 said.

“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,” Ekstrom added.

The research was published in the journal Annals of Emergency Medicine.
Read more: http://www.designntrend.com/articles/29983/20141210/using-internet-searches-forecast-emergency-room-visits.htm#ixzz3LbRLNyBm