Identifying and Predicting Postoperative Infections Based on Readily Available Electronic Health Record Data

Identification of postoperative infections based on retrospective patient data is currently done using manual chart review. We used a validated, automated labelling method based on registrations and treatments to develop a high-quality prediction model (AUC 0.81) for postoperative infections.

Automated summary

Currently, postoperative infections are identified through manual chart review. In this study, a validated automated labeling method based on registrations and treatments was used to develop a high-quality prediction model (AUC 0.81) for postoperative infections.