Prevalence, outcomes, and predictors of multidrug-resistant nosocomial lower respiratory tract infections among patients in an ICU

Oliveira1, Ana Beatriz Souza de; Sacillotto, Guilherme Hirassawa; Neves2, Manuela Francisco Balthazar; Silva2, Andressa Hellen Nora da; Moimaz3, Tamiris Adriane; Gandolfi, Joelma Villafanha; Nogueira, Mara Corrêa Lelles; Lobo, Suzana Margareth

doi:10.36416/1806-3756/e20220235

Cited by 3 publications

(1 citation statement)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous retrospective studies in several countries have shown that the occurrence of infections caused by MDRO in patients admitted to the intensive care unit (ICU) is a signi cant concern [3], and will greatly affect the treatment effect of the disease. MDRO infection in the ICU is associated with increased inpatient mortality, readmission rates, medical costs, and length of stay [4][5][6]. According to a retrospective study of carbapenem-resistant Gramnegative bacilli (CR-GNB) infections in Malaysia, pneumonia (40.7%) and bacteremia (25.5%) were the most common, and the overall hospital mortality rate was high (41.4%) [7].…”

Section: Introductionmentioning

confidence: 99%

Interpretable Machine Learning for Early Prediction of Multidrug-Resistant Organism Infection：A Discovery and Validation Study

Sun,

Zhao,

Wen

et al. 2023

Preprint

View full text Add to dashboard Cite

Background Multidrug-resistant organisms (MDRO) infection is a major public health threat in the world. We aim to predict risk of MDRO infections in Intensive Care Unit (ICU) patients by developing and validating a machine learning (ML) model.Methods This study included patients in the ICU from January 1, 2020 to December 31, 2022, and retrospectively analyzed the clinical characteristics of the patients. Lasso regression was used for feature selection. We use 6 machine learning methods to analyze clinical features and build prediction models. Furthermore, we illustrate the effects of the features attributed to the model and interpret the prediction process based on the SHapley Additive exPlanation(SHAP).Results A total of 888 cases were collected, 63 cases were excluded based on inclusion and exclusion criteria, and 825 final cases were included in the analysis, of which 375 were MDRO-infected patients. A total of 45 clinical variables were collected, and after selection, 31 variables were associated with outcomes and were used to develop machine learning models. We have build six ML models to predict MDRO infections, among which, the Random Forest (RF) model performs the best with an AUC of 0.83 and an accuracy of 0.767.Conclusions We built and validated an ML model for predicting patients who will develop MDRO infections, and the SHAP improves the interpretability of machine learning models and helps clinicians better understand the mechanisms behind the results. The model can provide guidance to ICU healthcare professionals in the prevention and control of patients at high risk of infection.

show abstract

Section: Introductionmentioning

confidence: 99%

Interpretable Machine Learning for Early Prediction of Multidrug-Resistant Organism Infection：A Discovery and Validation Study

Sun,

Zhao,

Wen

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

Optimizing patient outcomes in severe pneumonia: the role of multiplex PCR in the treatment of critically ill patients

Zhang,

Chou,

Wang

et al. 2024

Front. Med.

View full text Add to dashboard Cite

Herein, we evaluated the optimal timing for implementing the BioFire® FilmArray® Pneumonia Panel (FA-PP) in the medical intensive care unit (MICU). Respiratory samples from 135 MICU-admitted patients with acute respiratory failure and severe pneumonia were examined using FA-PP. The cohort had an average age of 67.1 years, and 69.6% were male. Notably, 38.5% were smokers, and the mean acute physiology and chronic health evaluation-II (APACHE-II) score at initial MICU admission was 30.62, and the mean sequential organ failure assessment score (SOFA) was 11.23, indicating sever illness. Furthermore, 28.9, 52.6, and 43% of patients had a history of malignancy, hypertension, and diabetes mellitus, respectively. Community-acquired pneumonia accounted for 42.2% of cases, whereas hospital-acquired pneumonia accounted for 37%. The average time interval between pneumonia diagnosis and FA-PP implementation was 1.9 days, and the mean MICU length of stay was 19.42 days. The mortality rate was 50.4%. Multivariate logistic regression analysis identified two variables as significant independent predictors of mortality: APACHE-II score (p = 0.033, OR = 1.06, 95% CI 1.00–1.11), history of malignancy (OR = 3.89, 95% CI 1.64–9.26). The Kaplan–Meier survival analysis indicated that early FA-PP testing did not provide a survival benefit. The study suggested that the FA-PP test did not significantly impact the mortality rate of patients with severe pneumonia with acute respiratory failure. However, a history of cancer and a higher APACHE-II score remain important independent risk factors for mortality.

show abstract

Drug resistance of <i>Pseudomonas aeruginosa</i> based on the isolation sites and types of gastrointestinal diseases: An observational study

Tsujimoto,

Fujikura,

Hamamoto

et al. 2024

FJMS

View full text Add to dashboard Cite

Prevalence, outcomes, and predictors of multidrug-resistant nosocomial lower respiratory tract infections among patients in an ICU

Cited by 3 publications

References 24 publications

Interpretable Machine Learning for Early Prediction of Multidrug-Resistant Organism Infection：A Discovery and Validation Study

Interpretable Machine Learning for Early Prediction of Multidrug-Resistant Organism Infection：A Discovery and Validation Study

Optimizing patient outcomes in severe pneumonia: the role of multiplex PCR in the treatment of critically ill patients

Drug resistance of <i>Pseudomonas aeruginosa</i> based on the isolation sites and types of gastrointestinal diseases: An observational study

Contact Info

Product

Resources

About