Identifying Antibiotic Use Targets for the Management of Antibiotic Resistance Using an Extended-Spectrum β-Lactamase-Producing Escherichia coli Case: A Threshold Logistic Modeling Approach

Abstract

The aim of this study was to develop a logistic modeling concept to improve understanding of the relationship between antibiotic use thresholds and the incidence of resistant pathogens. A combined approach of nonlinear modeling and logistic regression, named threshold logistic, was used to identify thresholds and risk scores in hospital-level antibiotic use associated with hospital-level incidence rates of extended-spectrum β-lactamase (ESBL)-producing Escherichia coli (E. coli). Threshold logistic models identified thresholds for fluoroquinolones (61.1 DDD/1000 occupied bed days (OBD)) and third-generation cephalosporins (9.2 DDD/1000 OBD) to control hospital ESBL-producing E. coli incidence. The 60th percentile of ESBL-producing E. coli was determined as the cutoff for defining high incidence rates. Threshold logistic analysis showed that for every one-unit increase in fluoroquinolones and third-generation cephalosporins above 61.1 and 9.2 DDD/1000 OBD levels, the average odds of the ESBL-producing E. coli incidence rate being ≥60th percentile of historical levels increased by 4.5% and 12%, respectively. Threshold logistic models estimated the risk scores of exceeding the 60th percentile of a historical ESBL-producing E. coli incidence rate. Threshold logistic models can help hospitals in defining critical levels of antibiotic use and resistant pathogen incidence and provide targets for antibiotic consumption and a near real-time performance monitoring feedback system.

Keywords: ESBL-producing E. coli; antibiotic prescribing; antibiotic resistance; antibiotic stewardship; antibiotic use; clinical practice; epidemiology; threshold logistic modeling; thresholds.

Figure 1

Monthly ESBL-producing E. coli incidence versus use of selected antibiotic classes (thick line, ESBL-producing E. coli, no. of cases/1000 OBD, 5-month moving averages, left-hand y-axis; thin line, antimicrobial use, DDD/1000 OBD, 5-month moving averages, right-hand y-axis): (a) fluoroquinolones; (b) third-generation cephalosporins.

Figure 2

Illustrations of associations between antibiotic use above their identified thresholds and predicted ESBL-producing E. coli incidence rates.

Figure 3

The empirical cumulative distribution function for ESBL-producing E. coli historical data. The solid vertical line represents the 60th percentile (0.288 cases/1000 OBD).

Figure 4

Receiver operator characteristic (ROC) chart plots the true positive classification rate against the false positive classification rate at different probability cutoff thresholds. The area under the curve (AUC) is an aggregate measure of performance across all possible classification thresholds.

Figure 5

The cumulative ESBL-producing E. coli incidence rates relative to fluoroquinolone and third-generation cephalosporin use being above or below their respective thresholds.

Figure 6

Results of triangulating antibiotic unit changes above identified threshold levels and the predicted probability of exceeding the 60th percentile of historical ESBL-producing E. coli using the identified threshold logistic model.