The CDC has generally been on the leading edge of influenza outbreak data, providing the latest and most accurate information for the public and hospitals alike. But what if that information were available faster in an EHR? A new Nature study suggests that's a realistic expectation.
In a review of data from athenahealth's EHR, including weekly total visit counts for flu, vaccine visit counts and visits for influenza-like illness, among others, researchers found that accurate data about region-specific flu activity could be drummed up much faster than waiting for the CDC to publish its results, which can have a lag time of up to two weeks.
"In this study we have shown that EHR data in combination with historical patterns of flu activity and a robust dynamical machine learning algorithm, are capable of accurately predicting real-time influenza activity at the national and regional scales in the U.S.," the authors wrote. " Here we show that incorporating CDC's influenza-like illness historical information and more of the available EHR information, using a suitable machine learning methodology, can improve flu estimates."
They conclude their study helps demonstrate the value of tapping cloud-based EHRs for local public health surveillance.