Related Experiment Video
Updated: Jun 16, 2025
Author Spotlight: Exploring the Antibacterial Effects of Zinc Oxide Nanoparticles in Overcoming Antibiotic Resistance
Published on: September 27, 2024
Prediction of multidrug-resistant bacteria (MDR) hospital-acquired infection (HAI) and colonisation: A systematic
Leila Figueiredo Dantas1, Igor Tona Peres1, Bianca Brandão de Paula Antunes1
1Department of Industrial Engineering, Pontifical Catholic University of Rio de Janeiro, Rio de Janeiro, RJ, Brazil.
Background:
Hospital-Acquired Infections (HAI) represent a public health priority in most countries worldwide. Our main objective was to systematically review the quality of the predictive modeling literature regarding multidrug-resistant gram-negative bacteria in Intensive Care Units (ICUs).
Methods:
We conducted and reported a Systematic Literature Review according to the recommendations of the PRISMA statement. We analysed the quality of the articles in terms of adherence to the TRIPOD checklist.
Results:
The initial search identified 1935 papers and 15 final articles were included in the review. Most studies analysed used traditional prediction models (logistic regression), and only three developed machine-learning techniques. We noted poor adherence to the main methodological issues recommended in the TRIPOD checklist to develop prediction models, such as handling missing data (20% adherence), model-building procedures (20% adherence), assessing model performance (47% adherence), and reporting performance measures (33% adherence).
Conclusions:
Our review found few studies that use efficient alternatives to predict the acquisition of multidrug-resistant gram-negative bacteria in ICUs. Furthermore, we noted a lack of strategies for dealing with missing data, feature selection, and imbalanced datasets, a common problem in HAI studies.
Insights
This review found few studies effectively predict multidrug-resistant gram-negative bacteria in Intensive Care Units (ICUs). Methodological quality was poor, with significant gaps in data handling and model reporting for hospital-acquired infections (HAI).
Area of Science:
- Infectious Disease Epidemiology
- Critical Care Medicine
- Biostatistics
Background:
- Hospital-Acquired Infections (HAI) are a significant global public health concern.
- Multidrug-resistant gram-negative bacteria in Intensive Care Units (ICUs) pose a particular threat.
- Predictive modeling is crucial for managing and preventing HAI.
Purpose of the Study:
- To systematically review the quality of predictive modeling literature for multidrug-resistant gram-negative bacteria in ICUs.
- To assess adherence to methodological standards in HAI prediction model development.
- To identify gaps in current research practices.
Main Methods:
- A Systematic Literature Review was conducted following PRISMA guidelines.
- The quality of included articles was assessed using the TRIPOD checklist.
- 1935 papers were initially screened, with 15 articles included in the final review.
Main Results:
- Most studies utilized traditional logistic regression models; machine learning techniques were underrepresented (3 studies).
- Poor adherence to TRIPOD checklist recommendations was observed, particularly in handling missing data (20%) and model-building (20%).
- Model performance assessment (47%) and reporting (33%) also showed significant deficiencies.
Conclusions:
- There is a scarcity of studies employing robust methods to predict multidrug-resistant gram-negative bacteria acquisition in ICUs.
- Common issues identified include inadequate strategies for missing data, feature selection, and imbalanced datasets.
- Improving methodological rigor in predictive modeling is essential for effective HAI control.
