The accuracy of fully automated algorithms for surveillance of healthcare-onset Clostridioides difficile infections in hospitalized patients

Suzanne Desirée van der Werff; Mikael Fritzing; Hideyuki Tanushi; Aron Henriksson; Hercules Dalianis; Anders Ternhag; Anna Färnert; Pontus Nauclér

doi:10.1017/ash.2022.32

The accuracy of fully automated algorithms for surveillance of healthcare-onset Clostridioides difficile infections in hospitalized patients

Antimicrob Steward Healthc Epidemiol. 2022 Mar 16;2(1):e43. doi: 10.1017/ash.2022.32. eCollection 2022.

Authors

Suzanne Desirée van der Werff^{1

2}, Mikael Fritzing^{1

3}, Hideyuki Tanushi^{1

4}, Aron Henriksson⁵, Hercules Dalianis⁵, Anders Ternhag^{1

2}, Anna Färnert^{1

2}, Pontus Nauclér^{1

2}

Affiliations

¹ Division of Infectious Diseases, Department of Medicine Solna, Karolinska Institutet, Stockholm, Sweden.
² Department of Infectious Diseases, Karolinska University Hospital, Stockholm, Sweden.
³ Uppsala University Hospital, Uppsala, Sweden.
⁴ Department of Data Processing & Analysis, Karolinska University Hospital, Stockholm, Sweden.
⁵ Department of Computer and Systems Sciences, Stockholm University, Stockholm, Sweden.

Abstract

We developed and validated a set of fully automated surveillance algorithms for healthcare-onset CDI using electronic health records. In a validation data set of 750 manually annotated admissions, the algorithm based on International Classification of Disease, Tenth Revision (ICD-10) code A04.7 had insufficient sensitivity. Algorithms based on microbiological test results with or without addition of symptoms performed well.