Predicting Risk of Multidrug-Resistant Enterobacterales Infections Among People With HIV

Abstract

Background Medically vulnerable individuals are at increased risk of acquiring multidrug-resistant Enterobacterales (MDR-E) infections. People with HIV (PWH) experience a greater burden of comorbidities and may be more susceptible to MDR-E due to HIV-specific factors. Methods We performed an observational study of PWH participating in an HIV clinical cohort and engaged in care at a tertiary care center in the southeastern US from 2000-2018. We evaluated demographic and clinical predictors of MDR-E by estimating prevalence ratios (PRs) and employing machine learning classification algorithms. In addition, we created a predictive model to estimate risk of MDR-E among PWH using a machine learning approach. Results Among 4,734 study participants, MDR-E was isolated from 1.6% (95% CI: 1.2-2.1%). In unadjusted analyses, MDR-E was strongly associated with nadir CD4 cell count ≤200 cells/mm 3 (PR: 4.0; 95% CI: 2.3-7.4), history of an AIDS-defining clinical condition (PR: 3.7; 95% CI: 2.3-6.2), and hospital admission in the prior 12 months(PR: 5.0; 95% CI: 3.2-7.9). With all variables included in machine learning algorithms, the most important clinical predictors of MDR-E were hospitalization, history of renal disease, history of an AIDS-defining clinical condition, CD4 cell count nadir ≤200 cells/mm 3 , and current CD4 cell count 201-500 cells/mm 3 . Female gender was the most important demographic predictor. Conclusions PWH are at risk for MDR-E infection due to HIV-specific factors, in addition to established risk factors. Early HIV diagnosis, linkage to care, and antiretroviral therapy to prevent immunosuppression, comorbidities, and coinfections protects against antimicrobial-resistant bacterial infections.

Tackling the Antimicrobial Resistance “Pandemic” with Machine Learning Tools: A Summary of Available Evidence

“…Machine learning algorithms can identify risk and clinical predictors of multidrugresistant Enterobacterales infections in persons infected with HIV [120]. Moreover, different machine learning approaches have been utilised to predict the drug resistance of HIV [121][122][123][124][125][126][127][128][129][130][131][132].…”

Using Machine Learning to Predict Antimicrobial Resistance―A Literature Review

“…The authors suggest that although ML certainly cannot substitute rapid molecular testing, it may be able to empower the appropriate selection of antimicrobials in advance, in case of real-time integration into the EHR. Henderson et al evaluated an ML classification model to discriminate possible predictors of MDR Enterobacterales infection in human immunodeficiency virus (HIV)-infected patients, who, compared to the general population, present increased vulnerability [ 30 ]. In the study population, the outcome of interest was rare, which restricted the performance of the classification algorithms as well as the number of predictors to be analyzed as a result.…”

In vitro antibacterial activity of antiretroviral drugs on key commensal bacteria from the human microbiota

“…Additionally, PLWH are at higher risk of acquiring and being infected by multidrug-resistant (MDR) microorganisms. This is because they are more likely to present known risk factors for MDR microorganism acquisition, including more hospital admissions, higher rates of antibiotic intake, the previously mentioned chronic clinical complications and changes in the intestinal microbiome composition ( Olaru et al., 2021a ; Olaru et al., 2021b ; Henderson et al., 2022 ). The emergence and dissemination of MDR microorganisms is an important public health problem due to high morbidity and mortality of infections caused by these agents ( Huemer et al., 2020 ).…”