Identification of surgical site infections using electronic health record data

• Published in: American journal of infection control 2018-11, Vol.46 (11), p.1230-1235
• Main Authors: Colborn, Kathryn L., Bronsert, Michael, Amioka, Elise, Hammermeister, Karl, Henderson, William G., Meguid, Robert
• Format: Article
• Language: English
• Subjects: Adult; Aged; Algorithms; Databases, Factual; Electronic Health Records; Female; Humans; lasso; Machine Learning; Male; Middle Aged; NSQIP; postoperative; Quality Improvement; Retrospective Studies; Risk Factors; supervised learning; Surgical Wound Infection - diagnosis
• ISSN: 0196-6553; 1527-3296
• DOI: 10.1016/j.ajic.2018.05.011

•The model correctly classified 89% of patients within 30 days after surgery.•The comprehensive model was better than available methods.•The best model classified 80% of SSIs and 90% of no-SSIs correctly.•The best model used 35 variables from the electronic health record. The objective of this study was to develop an algorithm for identifying 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 to supplement manual chart review. We fit 3 models to data from patients undergoing operations at the University of Colorado Hospital between 2013 and 2015: a similar model reported previously in the literature, a comprehensive model with 136 possible predictors, and a combination of those. All models used a generalized linear model with a lasso penalty. Several techniques for handling imbalance in the outcome were also used: Youden's J statistic to optimize the probability cutoff and sampling techniques combined with Youden's J. The models were then tested on data from patients undergoing operations during 2016. Two hundred thirty of 6,840 patients (3.4%) had an SSI. The comprehensive model fit to the full set of training data performed the best, achieving 90% specificity, 80% sensitivity, and an area under the receiver operating characteristic curve of 0.89. We identified a model that accurately identified SSIs. The framework presented can be easily implemented by other American College of Surgeons National Surgical Quality Improvement Program-participating hospitals to develop models for enhancing surveillance of SSIs.