Sequences of Events from the Electronic Medical Record and the Onset of Infection.

Autor: Coombes CE; Department of Anesthesiology, Stanford University, 300 Pasteur Dr., Palo Alto, CA 94305, USA., Coombes KR; Department of Population Health Sciences, Medical College of Georgia, 1420 Laney Walker Blvd, Augusta, GA 30912, USA., Fareed N; Department of Biomedical Informatics, The Ohio State University College of Medicine, 370 W 9th Ave, Columbus, OH 43210, USA.
Jazyk: angličtina
Zdroj: Chemistry & biodiversity [Chem Biodivers] 2022 Nov; Vol. 19 (11), pp. e202200657. Date of Electronic Publication: 2022 Oct 10.
DOI: 10.1002/cbdv.202200657
Abstrakt: We present a novel model of time-series analysis to learn from electronic health record (EHR) data when infection occurred in the intensive care unit (ICU) by translating methods from proteomics and Bayesian statistics. Using 48,536 patients hospitalized in an ICU, we describe each hospital course as an 'alphabet' of 23 physician actions ('events') in temporal order. We analyze these as k-mers of length 3-12 events and apply a Bayesian model of (cumulative) relative risk (RR). The log2-transformed RR (median=0.248, mean=0.226) supported the conclusion that the events selected were individually associated with increased risk of infection. Selecting from all possible cutoffs of maximum gain (MG), MG>0.0244 predicts administration of antibiotics with PPV 82.0 %, NPV 44.4 %, and AUC 0.706. Our approach holds value for retrospective analysis of other clinical syndromes for which time-of-onset is critical to analysis but poorly marked in EHRs, including delirium and decompensation.
(© 2022 Wiley-VHCA AG, Zurich, Switzerland.)
Databáze: MEDLINE
Externí odkaz: