Automated Identification of Postoperative Infections to Allow Prediction and Surveillance Based on Electronic Health Record Data: Scoping Review

Background: Postoperative infections remain a crucial challenge in health care, resulting in high morbidity, mortality, andcosts. Accurate identification and labeling of patients with postoperative bacterial infections is crucial for developing predictionmodels, validating biomarkers, and implementing surveillance systems in clinical practice. Objective: This scoping review aimed to explore methods for identifying patients with postoperative infections using electronichealth record (EHR) data to go beyond the reference standard of manual chart review. Methods: We performed a systematic search strategy across PubMed, Embase, Web of Science (Core Collection), the CochraneLibrary, and Emcare (Ovid), targeting studies addressing the prediction and fully automated surveillance (ie, without manualcheck) of diverse bacterial infections in the postoperative setting. For prediction modeling studies, we assessed the labelingmethods used, categorizing them as either manual or automated. We evaluated the different types of EHR data needed for thesurveillance and labeling of postoperative infections, as well as the performance of fully automated surveillance systems comparedwith manual chart review. Results: We identified 75 different methods and definitions used to identify patients with postoperative infections in studiespublished between 2003 and 2023. Manual labeling was the predominant method in prediction modeling research, 65% (49/75)of the identified methods use structured data, and 45% (34/75) use free text and clinical notes as one of their data sources. Fullyautomated surveillance systems should be used with caution because the reported positive predictive values are between 0.31and 0.76. Conclusions: There is currently no evidence to support fully automated labeling and identification of patients with infectionsbased solely on structured EHR data. Future research should focus on defining uniform definitions, as well as prioritizing thedevelopment of more scalable, automated methods for infection detection using structured EHR data.