Related Experiment Videos
Machine learning-based prediction of E. coli infection in hospitalized patients using a no-code analytical framework
Mona Gharib1, Mahmoud E F Abdel-Haliem2, Nagham M Nassar3
1Department of Mathematics, Faculty of Science, Zagazig University, Zagazig, 44519, Egypt.
Scientific Reports
|July 4, 2026
Summary
A no-code machine learning model shows promise for predicting Escherichia coli (E. coli) infections in hospitalized patients early. This approach aids in identifying at-risk individuals and could improve infection control strategies.
Area of Science:
- Medical Informatics
- Infectious Diseases
- Machine Learning
Background:
- Hospital-acquired infections (HAIs) pose a significant global health burden, increasing patient morbidity, mortality, and healthcare expenses.
- Escherichia coli (E. coli) is a primary cause of HAIs, particularly urinary tract infections, bloodstream infections, and surgical site infections.
- Early prediction of E. coli infections and identification of risk factors are crucial for effective patient management and targeted infection control.
Purpose of the Study:
- To evaluate a no-code machine learning (ML) approach for the early prediction of E. coli infections in hospitalized patients.
- To identify patient-related risk factors associated with E. coli infections using ML.
- To assess the feasibility of using ML for real-time E. coli infection risk stratification.
Main Methods:
- A no-code ML pipeline was developed using the Orange visual programming platform.
- A training dataset of 300 clinical samples and an independent validation dataset of 100 samples were collected from Zagazig University Hospital.
- Standard biochemical methods were used for bacterial identification, and the Naive Bayes model was implemented for prediction.
Main Results:
- The Naive Bayes model demonstrated potential in predicting E. coli infections based on clinical data.
- The model aims to provide predictions before final culture results are available, facilitating timely interventions.
- The study successfully integrated data preprocessing, feature handling, and model training within a no-code environment.
Conclusions:
- A no-code ML approach offers a viable strategy for the early prediction of E. coli infections in hospital settings.
- Identifying associated risk factors through ML can enhance targeted infection control measures.
- Further validation in larger, multi-center prospective studies is recommended prior to clinical implementation.
Related Concept Videos
01:18Steps in Outbreak Investigation
In the ever-evolving field of public health, statistical analysis serves as a cornerstone for understanding and managing disease outbreaks. By leveraging various statistical tools, health professionals can predict potential outbreaks, analyze ongoing situations, and devise effective responses to mitigate impact. For that to happen, there are a few possible stages of the analysis:
01:25Rapid Identification of Pathogens
MALDI-TOF MS has transformed clinical microbiology by offering a rapid and reliable method for pathogen identification. The traditional approach to microbial identification typically involves time-consuming culture techniques and biochemical tests, which can delay the initiation of appropriate antimicrobial therapy. MALDI-TOF MS avoids these delays by using characteristic ribosomal protein mass patterns of microbial cells, enabling accurate species-level identification within minutes.Principle...
01:24Automated Microbial Diagnostics
Automated diagnostic analyzers have transformed clinical microbiology by providing rapid and reliable methods for pathogen identification and antibiotic susceptibility testing. Among these systems, the Vitek 2 is widely used because it automates the traditionally labor-intensive processes of microbial identification (ID) and antibiotic susceptibility testing (AST), delivering standardized and timely results that are essential for effective patient care.Microbial Identification with ID CardsThe...