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

Studies in health technology and informatics, vol. 302, pp. 348–349

Abstract

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.

Authors 8

1. Siri Lise van der Meijden Aachen

   Leiden University Medical Center

   Affiliation as printed

   Healthplus.ai, Amsterdam, The Netherlands

   Leiden University Medical Center, Leiden, The Netherlands

   Healthplus.ai, Amsterdam, The Netherlands; Leiden University Medical Center, Leiden, The Netherlands

2. Anna M van Boekel Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center, Leiden, The Netherlands

3. Laurens Schinkelshoek
   Affiliation as printed

   Healthplus.ai, Amsterdam, The Netherlands

4. Harry van Goor

   Radboud University Medical Center

   Affiliation as printed

   Radboud University Medical Center, Nijmegen, The Netherlands

5. Mark G. J. de Boer Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center, Leiden, The Netherlands

6. Ewout Willem Steyerberg Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center, Leiden, The Netherlands

7. Bart F. Geerts
   Affiliation as printed

   Healthplus.ai, Amsterdam, The Netherlands

8. M. Sesmu Arbous Aachen

   Leiden University Medical Center

   Affiliation as printed

   Leiden University Medical Center, Leiden, The Netherlands