A machine learning and neural network approach for classifying multidrug-resistant bacterial infections

Antimicrobial resistance (AMR) represents a major public health challenge, significantly complicating infection prevention and treatment. This study employs machine learning and neural network techniques to classify multidrug-resistant Gram-negative bacterial (MDR-GNB) infections using electronic he...

Full description

Saved in:
Bibliographic Details
Main Authors: Preeda Mengsiri, Ratchadaporn Ungcharoen, Sethavidh Gertphol
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Healthcare Analytics
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2772442525000073
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849422446839463936
author Preeda Mengsiri
Ratchadaporn Ungcharoen
Sethavidh Gertphol
author_facet Preeda Mengsiri
Ratchadaporn Ungcharoen
Sethavidh Gertphol
author_sort Preeda Mengsiri
collection DOAJ
description Antimicrobial resistance (AMR) represents a major public health challenge, significantly complicating infection prevention and treatment. This study employs machine learning and neural network techniques to classify multidrug-resistant Gram-negative bacterial (MDR-GNB) infections using electronic health records from 624 patients at Thatphanom Crown Prince Hospital in Thailand. We compared several algorithms, including Logistic Regression, Random Forest, Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), Multilayer Perceptron (MLP), and Light Gradient Boosting Machine (LightGBM), with the MLP model exhibiting the highest accuracy and specificity. Performance was further enhanced by integrating feature selection methods such as Sequential Forward Selection (SFS), Recursive Feature Elimination with Cross-Validation (RFE-CV), and SelectKBest with data augmentation techniques, including ADASYN and SMOTE variants. Utilizing SHapley Additive exPlanations (SHAP) provided valuable insights into the most influential predictors for MDR-GNB. Notably, the MLP model achieved an AUC of 0.70, surpassing prior studies and highlighting its potential to advance clinical decision-making in managing MDR-GNB infections.
format Article
id doaj-art-955ff6ed2ebe4daab7c084ad9b1598b7
institution Kabale University
issn 2772-4425
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Healthcare Analytics
spelling doaj-art-955ff6ed2ebe4daab7c084ad9b1598b72025-08-20T03:31:06ZengElsevierHealthcare Analytics2772-44252025-06-01710038810.1016/j.health.2025.100388A machine learning and neural network approach for classifying multidrug-resistant bacterial infectionsPreeda Mengsiri0Ratchadaporn Ungcharoen1Sethavidh Gertphol2Biomedical Data Science Program, Faculty of Science, Kasetsart University, ThailandBiomedical Data Science Program, Faculty of Science, Kasetsart University, Thailand; Faculty of Public Health, Kasetsart University, Chalermphrakiat Sakon Nakhon Province Campus, Thailand; Corresponding author. Faculty of Public Health, Kasetsart University, Chalermphrakiat Sakon Nakhon Province Campus, Thailand.Biomedical Data Science Program, Faculty of Science, Kasetsart University, Thailand; Department of Computer Science, Faculty of Science, Kasetsart University, ThailandAntimicrobial resistance (AMR) represents a major public health challenge, significantly complicating infection prevention and treatment. This study employs machine learning and neural network techniques to classify multidrug-resistant Gram-negative bacterial (MDR-GNB) infections using electronic health records from 624 patients at Thatphanom Crown Prince Hospital in Thailand. We compared several algorithms, including Logistic Regression, Random Forest, Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), K-Nearest Neighbors (KNN), Multilayer Perceptron (MLP), and Light Gradient Boosting Machine (LightGBM), with the MLP model exhibiting the highest accuracy and specificity. Performance was further enhanced by integrating feature selection methods such as Sequential Forward Selection (SFS), Recursive Feature Elimination with Cross-Validation (RFE-CV), and SelectKBest with data augmentation techniques, including ADASYN and SMOTE variants. Utilizing SHapley Additive exPlanations (SHAP) provided valuable insights into the most influential predictors for MDR-GNB. Notably, the MLP model achieved an AUC of 0.70, surpassing prior studies and highlighting its potential to advance clinical decision-making in managing MDR-GNB infections.http://www.sciencedirect.com/science/article/pii/S2772442525000073Machine learningNeural networkElectronic health recordsMultidrug resistanceGram-negative bacteria
spellingShingle Preeda Mengsiri
Ratchadaporn Ungcharoen
Sethavidh Gertphol
A machine learning and neural network approach for classifying multidrug-resistant bacterial infections
Healthcare Analytics
Machine learning
Neural network
Electronic health records
Multidrug resistance
Gram-negative bacteria
title A machine learning and neural network approach for classifying multidrug-resistant bacterial infections
title_full A machine learning and neural network approach for classifying multidrug-resistant bacterial infections
title_fullStr A machine learning and neural network approach for classifying multidrug-resistant bacterial infections
title_full_unstemmed A machine learning and neural network approach for classifying multidrug-resistant bacterial infections
title_short A machine learning and neural network approach for classifying multidrug-resistant bacterial infections
title_sort machine learning and neural network approach for classifying multidrug resistant bacterial infections
topic Machine learning
Neural network
Electronic health records
Multidrug resistance
Gram-negative bacteria
url http://www.sciencedirect.com/science/article/pii/S2772442525000073
work_keys_str_mv AT preedamengsiri amachinelearningandneuralnetworkapproachforclassifyingmultidrugresistantbacterialinfections
AT ratchadapornungcharoen amachinelearningandneuralnetworkapproachforclassifyingmultidrugresistantbacterialinfections
AT sethavidhgertphol amachinelearningandneuralnetworkapproachforclassifyingmultidrugresistantbacterialinfections
AT preedamengsiri machinelearningandneuralnetworkapproachforclassifyingmultidrugresistantbacterialinfections
AT ratchadapornungcharoen machinelearningandneuralnetworkapproachforclassifyingmultidrugresistantbacterialinfections
AT sethavidhgertphol machinelearningandneuralnetworkapproachforclassifyingmultidrugresistantbacterialinfections