Related Experiment Video
Updated: Jun 23, 2025
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Improving Risk Prediction of Methicillin-Resistant Staphylococcus aureus Using Machine Learning Methods With Network
Methun Kamruzzaman1, Jack Heavey1, Alexander Song1
1University of Virginia, Charlottesville, VA, United States.
Background:
Health care-associated infections due to multidrug-resistant organisms (MDROs), such as methicillin-resistant Staphylococcus aureus (MRSA) and Clostridioides difficile (CDI), place a significant burden on our health care infrastructure.
Objective:
Screening for MDROs is an important mechanism for preventing spread but is resource intensive. The objective of this study was to develop automated tools that can predict colonization or infection risk using electronic health record (EHR) data, provide useful information to aid infection control, and guide empiric antibiotic coverage.
Methods:
We retrospectively developed a machine learning model to detect MRSA colonization and infection in undifferentiated patients at the time of sample collection from hospitalized patients at the University of Virginia Hospital. We used clinical and nonclinical features derived from on-admission and throughout-stay information from the patient's EHR data to build the model. In addition, we used a class of features derived from contact networks in EHR data; these network features can capture patients' contacts with providers and other patients, improving model interpretability and accuracy for predicting the outcome of surveillance tests for MRSA. Finally, we explored heterogeneous models for different patient subpopulations, for example, those admitted to an intensive care unit or emergency department or those with specific testing histories, which perform better.
Results:
We found that the penalized logistic regression performs better than other methods, and this model's performance measured in terms of its receiver operating characteristics-area under the curve score improves by nearly 11% when we use polynomial (second-degree) transformation of the features. Some significant features in predicting MDRO risk include antibiotic use, surgery, use of devices, dialysis, patient's comorbidity conditions, and network features. Among these, network features add the most value and improve the model's performance by at least 15%. The penalized logistic regression model with the same transformation of features also performs better than other models for specific patient subpopulations.
Conclusions:
Our study shows that MRSA risk prediction can be conducted quite effectively by machine learning methods using clinical and nonclinical features derived from EHR data. Network features are the most predictive and provide significant improvement over prior methods. Furthermore, heterogeneous prediction models for different patient subpopulations enhance the model's performance.
Insights
Machine learning accurately predicts methicillin-resistant Staphylococcus aureus (MRSA) risk using electronic health records. Network features significantly improve prediction accuracy for healthcare-associated infections, aiding infection control.
Area of Science:
- Computational epidemiology
- Health informatics
- Machine learning in healthcare
Background:
- Healthcare-associated infections (HAIs) from multidrug-resistant organisms (MDROs) like MRSA and CDI pose a significant burden.
- Current MDRO screening is resource-intensive, necessitating innovative approaches.
Purpose of the Study:
- To develop automated tools for predicting MDRO colonization or infection risk using electronic health record (EHR) data.
- To enhance infection control strategies and guide empiric antibiotic coverage decisions.
Main Methods:
- Retrospective development of a machine learning model using EHR data to detect MRSA colonization/infection.
- Inclusion of clinical, nonclinical, and network-based features derived from patient data.
- Exploration of heterogeneous models for specific patient subpopulations to optimize performance.
Main Results:
- Penalized logistic regression demonstrated superior performance, with an 11% AUC improvement using polynomial feature transformation.
- Key predictors of MDRO risk included antibiotic use, surgery, device use, dialysis, comorbidities, and network features.
- Network features provided the most significant performance improvement, increasing model accuracy by at least 15%.
Conclusions:
- Machine learning effectively predicts MRSA risk using EHR data, integrating clinical and nonclinical factors.
- Network features are highly predictive, substantially improving upon existing methods for MDRO risk assessment.
- Heterogeneous models tailored to patient subpopulations enhance predictive accuracy for infection control.
