Related Experiment Video
Updated: Jun 29, 2025
Characterization of a Pathogenic Escherichia coli Strain Derived from Oreochromis spp. Farms Using Whole-Genome Sequencing
Published on: December 23, 2022
Leveraging Large Data, Statistics, and Machine Learning to Predict the Emergence of Resistant E. coli Infections
Rim Hur1,2,3, Stephine Golik1,4, Yifan She1,3
1Department of Inpatient Pharmacy, Kaiser Permanente, One Kaiser Plaza, Oakland, CA 94612, USA.
Abstract:
Drug-resistant Gram-negative bacterial infections, on average, increase the length of stay (LOS) in U.S. hospitals by 5 days, translating to approximately $15,000 per patient. We used statistical and machine-learning models to explore the relationship between antibiotic usage and antibiotic resistance over time and to predict the clinical and financial costs associated with resistant E. coli infections. We acquired data on antibiotic utilization and the resistance/sensitivity of 4776 microbial cultures at a Kaiser Permanente facility from April 2013 to December 2019. The ARIMA (autoregressive integrated moving average), neural networks, and random forest time series algorithms were employed to model antibiotic resistance trends. The models' performance was evaluated using mean absolute error (MAE) and root mean squared error (RMSE). The best performing model was then used to predict antibiotic resistance rates for the year 2020. The ARIMA model with cefazolin, followed by the one with cephalexin, provided the lowest RMSE and MAE values without signs of overfitting across training and test datasets. The study showed that reducing cefazolin usage could decrease the rate of resistant E. coli infections. Although piperacillin/tazobactam did not perform as well as cefazolin in our time series models, it performed reasonably well and, due to its broad spectrum, might be a practical target for interventions in antimicrobial stewardship programs (ASPs), at least for this particular facility. While a more generalized model could be developed with data from multiple facilities, this study acts as a framework for ASP clinicians to adopt statistical and machine-learning approaches, using region-specific data to make effective interventions.
Insights
Reducing cefazolin use can lower resistant E. coli infections, a key finding for antimicrobial stewardship. This study models antibiotic resistance trends to predict and manage healthcare costs.
Area of Science:
- Infectious Diseases
- Computational Biology
- Health Economics
Background:
- Drug-resistant Gram-negative bacterial infections significantly increase hospital length of stay and costs.
- Escherichia coli (E. coli) is a common pathogen, and resistance to antibiotics poses a growing threat.
- Understanding the relationship between antibiotic usage and resistance is crucial for effective antimicrobial stewardship.
Purpose of the Study:
- To explore the relationship between antibiotic usage and antibiotic resistance over time using statistical and machine-learning models.
- To predict the clinical and financial costs associated with resistant E. coli infections.
- To provide a framework for antimicrobial stewardship programs (ASPs) to use data-driven interventions.
Main Methods:
- Acquired data on antibiotic utilization and microbial culture resistance/sensitivity from a Kaiser Permanente facility (April 2013 - December 2019).
- Employed time series algorithms including Autoregressive Integrated Moving Average (ARIMA), neural networks, and random forest to model antibiotic resistance trends.
- Evaluated model performance using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE), with the best model predicting 2020 resistance rates.
Main Results:
- The ARIMA model demonstrated the best performance for predicting antibiotic resistance trends, particularly with cefazolin and cephalexin.
- Reducing cefazolin usage was identified as a potential strategy to decrease the rate of resistant E. coli infections.
- Piperacillin/tazobactam, despite not being the top performer in models, shows potential as an intervention target in ASPs due to its broad spectrum.
Conclusions:
- Statistical and machine-learning models can effectively predict antibiotic resistance trends and inform antimicrobial stewardship interventions.
- Region-specific data is valuable for tailoring interventions within ASPs.
- This study provides a framework for adopting advanced analytical approaches to combat antibiotic resistance and manage associated costs.
More Related Videos
08:58Isolation and Identification of Waterborne Antibiotic-Resistant Bacteria and Molecular Characterization of their Antibiotic Resistance Genes
Published on: March 3, 2023
08:03Heuristic Mining of Hierarchical Genotypes and Accessory Genome Loci in Bacterial Populations
Published on: December 7, 2021
Related Concept Videos
01:18Steps in Outbreak Investigation
01:25Statistical Methods for Analyzing Epidemiological Data
01:12Statistical Software for Data Analysis and Clinical Trials
01:11Residuals and Least-Squares Property
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...