Scopus İndeksli Yayınlar Koleksiyonu

Permanent URI for this collectionhttps://hdl.handle.net/20.500.14627/7

Browse

Filters

20252

Settings

Scopus Q: search.filters.scopusQuartile.N/ASubject: search.filters.subject.Machine Learning

Search Results

Now showing 1 - 2 of 2
  • Article
    Machine Learning Model for Predicting Multidrug Resistance in Clinical Escherichia Coli Isolates: A Retrospective General Surgery Study
    (Multidisciplinary Digital Publishing Institute (MDPI), 2025) Tolan, H.K.; Aydın, İ.; Tanyildizi-Kökkülünk, H.; Karakuş, M.; Akkaya, Y.; Kaya, O.; Işman, F.K.
    Background/Objectives: Escherichia coli is one of the leading causes of surgical site infections (SSIs) and poses a growing public health concern due to its increasing antimicrobial resistance. High rates of extended-spectrum beta-lactamase (ESBL) production among E. coli strains complicate treatment outcomes and emphasize the need for effective surveillance and control strategies. Methods: A total of 691 E. coli isolates from general surgery clinics (2020–2025) were identified using MALDI-TOF MS. Antibiotic susceptibility data and patient variables were cleaned, encoded, and used to predict resistance using the Random Forest, CatBoost, and Naive Bayes algorithms. SMOTE addressed class imbalance, and model performance was assessed through various validation methods. Results: Among the three machine learning models tested, Random Forest (RF) showed the best performance in predicting antibiotic resistance of E. coli, achieving median accuracy, precision, recall, and F1-scores of 0.90 and AUC values up to 0.99 for key antibiotics. CatBoost performed similarly but was less stable with imbalanced data, while Naive Bayes showed lower accuracy. Feature importance analysis highlighted strong inter-antibiotic resistance links, especially among β-lactams, and some influence of demographic factors. Conclusions: This study highlights the potential of simple, high-performing models using structured clinical data to predict antimicrobial resistance, especially in resource-limited clinical settings. By incorporating machine learning into antimicrobial resistance (AMR) surveillance systems, our goal is to support the advancement of rapid diagnostics and targeted antimicrobial stewardship approaches, which are essential in addressing the growing challenge of multidrug resistance. © 2025 by the authors.
  • Conference Object
    Reflection Coefficient Prediction in Triple-Layer Microwave Absorbers: A Machine Learning Perspective
    (Institute of Electrical and Electronics Engineers Inc., 2025) Nas, Abdurrahim; Kankilic, Sueda; Karpat, Esin
    Electromagnetic absorbers prevent the reflection and transmission of electromagnetic waves. Electromagnetic absorbers have a wide range of applications from military to medical applications. In these areas, absorber designs have different importance in terms of parameters such as reflection coefficient, selected material and thickness. Many difficulties are encountered to achieve the optimal design. In this paper, we propose a machine learning regression method for three-layer microwave absorber architecture to obtain the optimum parameters, overcome the difficulties and speed up the process. The material and thickness of each layer are used as parameters to feed the models and the reflection coefficient is estimated using these parameters. Predictions are made with various regression algorithms. These algorithms are KNeighbors Regression, Random Forest Regressor, XGBoost Regression, CatBoost Regressor, AdaBoost Regressor which uses similarities between observations, Gradient Boosting Regressor which is tree based or boosted tree based algorithms, Linear Regression which uses a linear model, Partial Least Squares Regression which uses cross decomposition, Gaussian Process Regressor which uses statistical distribution, Stochastic Gradient Descent Regressor which uses a linear model to reduce empirical loss to predict an output. Mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), R-squared (R2) are used with the predictions of each model to obtain the metrics for the analysis of the results. The predicted values and actual values of the metrics are used to compare the regression algorithms used in the research. After the comparison, our observations show that in most cases CatBoost Regressor is better than other models used in the research. In general, it is observed that most of the machine learning regression algorithms used in this paper can be used to predict the reflection coefficient of three-layer microwave absorbers as output and input parameters used in the research. © 2025 Elsevier B.V., All rights reserved.