Identifying SSIs using electronic health record data

Editor's Note

In this study, researchers developed an algorithm model that accurately identified surgical site infections (SSIs) using independent variables from electronic health record data and outcomes from the American College of Surgeons National Surgical Quality Improvement Program (ACS NSQIP).

Researchers fit 3 models to data from patients having surgery at the University of Colorado Hospital between 2013 and 2015 (ie, a similar model reported previously in the literature, a comprehensive model with 136 possible predictors, and a combination of those) and then tested the models on data from patients having surgery in 2016.

Of 6,840 patients analyzed, 230 (3.4%) had an SSI. The comprehensive model fit to the full set of training data performed the best, classifying 80% of SSIs and 90% of no SSIs correctly.

The framework for developing the model can be easily implemented by other ACS NSQIP participating hospitals, the researchers concluded.