Methods Inf Med 2022; 61(01/02): 046-054
DOI: 10.1055/a-1817-7208
Original Article

Automated Identification of Immunocompromised Status in Critically Ill Children

Swaminathan Kandaswamy
1   Department of Pediatrics, Emory University, Atlanta, Georgia, United States
,
Evan W. Orenstein
1   Department of Pediatrics, Emory University, Atlanta, Georgia, United States
2   Division of Hospital Medicine, Children's Healthcare of Atlanta, Atlanta, Georgia, United States
,
Elizabeth Quincer
3   Division of Infectious Diseases, Department of Pediatrics, Emory University and Children's Healthcare of Atlanta, Atlanta, Georgia, United States
,
Alfred J. Fernandez
2   Division of Hospital Medicine, Children's Healthcare of Atlanta, Atlanta, Georgia, United States
,
Mark D. Gonzalez
4   Department of Pathology, Children's Healthcare of Atlanta, Atlanta, Georgia, United States
,
Lydia Lu
2   Division of Hospital Medicine, Children's Healthcare of Atlanta, Atlanta, Georgia, United States
,
Rishikesan Kamaleswaran
5   Department of Biomedical Informatics, Emory University, Atlanta, Georgia, United States
,
Imon Banerjee
6   Department of Radiology, Mayo Clinic, Phoenix, Arizona, United States
,
Preeti Jaggi
3   Division of Infectious Diseases, Department of Pediatrics, Emory University and Children's Healthcare of Atlanta, Atlanta, Georgia, United States
› Author Affiliations

Abstract

Background Easy identification of immunocompromised hosts (ICHs) would allow for stratification of culture results based on host type.

Methods We utilized antimicrobial stewardship program (ASP) team notes written during handshake stewardship rounds in the pediatric intensive care unit (PICU) as the gold standard for host status; clinical notes from the primary team, medication orders during the encounter, problem list, and billing diagnoses documented prior to the ASP documentation were extracted to develop models that predict host status. We calculated performance for three models based on diagnoses/medications, with and without natural language processing from clinical notes. The susceptibility of pathogens causing bacteremia to commonly used empiric antibiotic regimens was then stratified by host status.

Results We identified 844 antimicrobial episodes from 666 unique patients; 160 (18.9%) were identified as ICHs. We randomly selected 675 initiations (80%) for model training and 169 initiations (20%) for testing. A rule-based model using diagnoses and medications alone yielded a sensitivity of 0.87 (08.6–0.88), specificity of 0.93 (0.92–0.93), and positive predictive value (PPV) of 0.74 (0.73–0.75). Adding clinical notes into XGBoost model led to improved specificity of 0.98 (0.98–0.98) and PPV of 0.9 (0.88–0.91), but with decreased sensitivity 0.77 (0.76–0.79). There were 77 bacteremia episodes during the study period identified and a host-specific visualization was created.

Conclusions An electronic health record–based phenotype based on notes, diagnoses, and medications identifies ICH in the PICU with high specificity.

Note

This study was approved by the Emory University Institutional Review Board.


Supplementary Material



Publication History

Received: 07 December 2021

Accepted: 02 April 2022

Accepted Manuscript online:
05 April 2022

Article published online:
19 August 2022

© 2022. Thieme. All rights reserved.

Georg Thieme Verlag KG
Rüdigerstraße 14, 70469 Stuttgart, Germany