Related Experiment Video
Updated: Aug 11, 2026
Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis
Published on: June 18, 2020
Large-Scale Samples Based Rapid Detection of Ciprofloxacin Resistance in Klebsiella pneumoniae Using Machine Learning
Chunxuan Wang1,2, Zhuo Wang1,3, Hsin-Yao Wang4,5
1Warshel Institute for Computational Biology, The Chinese University of Hong Kong, Shenzhen, China.
Abstract:
Klebsiella pneumoniae is one of the most common causes of hospital- and community-acquired pneumoniae. Resistance to the extensively used quinolone antibiotic, such as ciprofloxacin, has increased in Klebsiella pneumoniae, which leads to the increase in the risk of initial antibiotic selection for Klebsiella pneumoniae treatment. Rapid and precise identification of ciprofloxacin-resistant Klebsiella pneumoniae (CIRKP) is essential for clinical therapy. Nowadays, matrix-assisted laser desorption ionization time-of-flight mass spectrometry (MALDI-TOF MS) is another approach to discover antibiotic-resistant bacteria due to its shorter inspection time and lower cost than other current methods. Machine learning methods are introduced to assist in discovering significant biomarkers from MALDI-TOF MS data and construct prediction models for rapid antibiotic resistance identification. This study examined 16,997 samples taken from June 2013 to February 2018 as part of a longitudinal investigation done by Change Gung Memorial Hospitals (CGMH) at the Linkou branch. We applied traditional statistical approaches to identify significant biomarkers, and then a comparison was made between high-importance features in machine learning models and statistically selected features. Large-scale data guaranteed the statistical power of selected biomarkers. Besides, clustering analysis analyzed suspicious sub-strains to provide potential information about their influences on antibiotic resistance identification performance. For modeling, to simulate the real antibiotic resistance predicting challenges, we included basic information about patients and the types of specimen carriers into the model construction process and separated the training and testing sets by time. Final performance reached an area under the receiver operating characteristic curve (AUC) of 0.89 for support vector machine (SVM) and extreme gradient boosting (XGB) models. Also, logistic regression and random forest models both achieved AUC around 0.85. In conclusion, models provide sensitive forecasts of CIRKP, which may aid in early antibiotic selection against Klebsiella pneumoniae. The suspicious sub-strains could affect the model performance. Further works could keep on searching for methods to improve both the model accuracy and stability.
Insights
Rapid identification of ciprofloxacin-resistant Klebsiella pneumoniae (CIRKP) is crucial. Machine learning models using MALDI-TOF MS data achieved high accuracy (AUC 0.89) for predicting CIRKP, aiding early antibiotic selection.
Area of Science:
- Medical Microbiology
- Clinical Diagnostics
- Computational Biology
Background:
- Klebsiella pneumoniae is a leading cause of hospital- and community-acquired pneumonia.
- Increasing quinolone resistance in K. pneumoniae complicates treatment and necessitates rapid identification.
- Ciprofloxacin-resistant Klebsiella pneumoniae (CIRKP) poses a significant clinical challenge.
Purpose of the Study:
- To develop and evaluate machine learning models for rapid identification of CIRKP.
- To leverage MALDI-TOF MS data for predicting antibiotic resistance in K. pneumoniae.
- To assess the impact of patient data and specimen types on prediction model performance.
Main Methods:
- Analysis of 16,997 longitudinal samples using MALDI-TOF MS.
- Application of statistical approaches and machine learning (SVM, XGB, logistic regression, random forest) for biomarker identification and model construction.
- Inclusion of patient demographics and specimen types, with time-based training and testing splits.
Main Results:
- Machine learning models, particularly SVM and XGB, achieved high predictive performance with an AUC of 0.89.
- Logistic regression and random forest models demonstrated strong performance with AUCs around 0.85.
- Identified significant biomarkers and explored the influence of sub-strains on model accuracy.
Conclusions:
- Machine learning models effectively predict CIRKP, supporting timely antibiotic selection.
- MALDI-TOF MS combined with machine learning offers a rapid and cost-effective diagnostic approach.
- Further research is needed to enhance model accuracy and stability, considering bacterial sub-strains.
