Preoperative Prediction of Postoperative Infections Using Machine Learning and Electronic Health Record Data

Abstract

Objective: Estimate preoperative risk of postoperative infections using structured electronic health record (EHR) data. Summary Background Data: Surveillance and reporting of postoperative infections is primarily done through costly, labor-intensive manual chart review on a small sample of patients. Automated methods using statistical models applied to postoperative EHR data have shown promise to augment manual review as they can cover all operations in a timely manner. However, there are no specific models for risk-adjusting infectious complication rates using EHR data. Methods: Preoperative EHR data from 30,639 patients (2013-2019) were linked to American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) preoperative data and postoperative infection outcomes data from five hospitals in the University of Colorado Health System. EHR data included diagnoses, procedures, operative variables, patient characteristics, and medications. Lasso and the knockoff filter was used to perform controlled variable selection. Outcomes included surgical site infection (SSI), urinary tract infection (UTI), sepsis/septic shock, and pneumonia up to 30 days post-operatively. Results: Among >15,000 candidate predictors, seven were chosen for the SSI model and six for each of the UTI, sepsis, and pneumonia models. Important variables included preoperative presence of the specific outcome, wound classification, comorbidities, and American Society of Anesthesiologists physical status classification (ASA Class). Area under the receiver operating characteristic curve for each model ranged from 0.73-0.89. Conclusion: Parsimonious preoperative models for predicting postoperative infection risk using EHR data were developed and showed comparable performance to existing ACS-NSQIP risk models that use manual chart review. These models can be used to estimate risk-adjusted postoperative infection rates applied to large volumes of EHR data in a timely manner.