Reassessing the management of uncomplicated urinary tract infection: A retrospective analysis using machine learning causal inference

Abstract

Background: Uncomplicated urinary tract infection (UTI) is a common indication for outpatient antimicrobial therapy. National guidelines for the management of uncomplicated UTI were published by the Infectious Diseases Society of America in 2011, however it is not fully known the extent to which they align with current practices, patient diversity, and pathogen biology, all of which have evolved significantly in the time since their publication.

Objective: We aimed to re-evaluate efficacy and adverse events for first-line antibiotics (nitrofurantoin, and trimethoprim-sulfamethoxazole), versus second-line antibiotics (fluoroquinolones) and versus alternative agents (oral β-lactams) for uncomplicated UTI in contemporary clinical practice by applying machine learning algorithms to a large claims database formatted into the Observational Medical Outcomes Partnership (OMOP) common data model.

Outcomes: Our primary outcome was a composite endpoint for treatment failure, defined as outpatient or inpatient re-visit within 30 days for UTI, pyelonephritis or sepsis. Secondary outcomes were the risk of 4 common antibiotic-associated adverse events: gastrointestinal symptoms, rash, kidney injury and C. difficile infection.

Statistical methods: We adjusted for covariate-dependent censoring and treatment indication using a broad set of domain-expert derived features. Sensitivity analyses were conducted using OMOP-learn, an automated feature engineering package for OMOP datasets.

Results: Our study included 57,585 episodes of UTI from 49,037 patients. First-line antibiotics were prescribed in 35,018 (61%) episodes, second-line antibiotics were prescribed in 21,140 (37%) episodes and alternative antibiotics were prescribed in 1,427 (2%) episodes. After adjustment, patients receiving first-line therapies had an absolute risk difference of -2.1% [95% CI -2.9% to -1.6%] for having a revisit for UTI within 30 days of diagnosis relative to second-line antibiotics. First-line therapies had an absolute risk difference of -6.6% [95% CI -9.4% to -3.8%] for 30-day revisit compared to alternative β-lactam antibiotics. Differences in adverse events were clinically similar between first and second line agents, but lower for first-line agents relative to alternative antibiotics (-3.5% [95% CI -5.9% to -1.2%]). Results were similar for models built with OMOPlearn.

Conclusion: Our study provides support for the continued use of first-line antibiotics for the management of uncomplicated UTI. Our results also provide proof-of-principle that automated feature extraction methods for OMOP formatted data can emulate manually curated models, thereby promoting reproducibility and generalizability.

Figure 1:. Cohort inclusion criteria and definitions for outcomes and feature.

Static features were evaluated at T₀. Abbreviations, T, time.

Figure 2:. Analytic pipeline.

We built and separately analyzed cohorts for first-line versus second-line and first-line versus alternative treatment. Eighty percent of the total data was set aside for training and this was further split 75/25 into development (blue) and validation (green) datasets. Two models were then run to estimate the probability of treatment and of being observed through the outcome period post-diagnosis. We used a 3-fold cross-validation to select the model with the highest AUROC, indicated by the asterisk. Average treatment effect for a given outcome was estimated on test data (yellow) by the risk difference between those receiving first-line treatment or another treatment (second-line or alternative) after normalizing for the probability of receiving a treatment and of being observed at the end of the outcome’s follow-up period (e.g 30 days). Abbreviations, T, treatment, X, covariates, D, observed.

Figure 3:. Study flow diagram.

Sample sizes indicate UTI diagnoses.

Figure 4.

Adjusted rate difference for revisits for patients receiving first-line versus second-line antibiotics, and first-line versus alternative treatments, after adjusting for potential confounding factors and censoring.

Figure 5.

Adjusted rate difference for treatment-related adverse effects for patients receiving first-line versus second-line antibiotics, and first-line versus alternative treatments, after adjusting for potential confounding factors and censoring.