Related Experiment Video
Updated: May 10, 2026
An In vitro Model to Study Immune Responses of Human Peripheral Blood Mononuclear Cells to Human Respiratory Syncytial Virus Infection
Published on: December 10, 2013
Development of a host-signature-based machine learning model to diagnose bacterial and viral infections in febrile
Fang Bai1, Zelong Gong2, Dong Cui2
1Dongguan Key Laboratory of Pathogenesis and Experimental Diagnosis of Infectious Diseases, Institute of Laboratory Medicine of School of Medical Technology, The First Dongguan Affiliated Hospital, Guangdong Medical University, Dongguan, Guangdong, China.
Insights
A novel five-gene host signature accurately diagnoses bacterial or viral infections in febrile children. This host gene signature enables the development of artificial neural network (ANN) and random forest (RF) models for improved clinical decision-making.
Area of Science:
- Bioinformatics
- Infectious Disease Diagnostics
- Host Gene Expression Analysis
Background:
- Accurate etiological diagnosis is crucial for managing febrile children, guiding treatment and impacting outcomes.
- Host gene-based diagnostic strategies offer high accuracy and clinical utility.
- Traditional methods for differentiating bacterial and viral infections in children can be time-consuming and may lead to delayed treatment.
Purpose of the Study:
- To develop and validate artificial neural network (ANN) and random forest (RF) models for diagnosing bacterial versus viral (B/V) infections in febrile children.
- To identify a host gene signature predictive of B/V infection.
- To assess the diagnostic performance of the developed models.
Main Methods:
- Integrative bioinformatics analysis of whole blood transcriptome data from febrile children.
- Differential gene expression (DEG) analysis and weighted gene co-expression network analysis (WGCNA).
- Development of ANN (multilayer perceptron) and RF models using identified host gene signatures, including L1 regularization for feature selection.
Main Results:
- A five-gene signature (LCN2, IFI27, SLPI, IFIT2, PI3) was identified as a top predictor of B/V infection.
- The RF model achieved an AUC of 0.9517 in testing for B/V diagnosis, while the ANN model achieved an AUC of 0.9540.
- A generalized RF model demonstrated an AUC of 0.8968 in testing for predicting diverse etiological infections.
Conclusions:
- A five-gene host signature effectively distinguishes bacterial from viral infections in febrile children.
- The developed RF and ANN models demonstrate high diagnostic accuracy, sensitivity, and specificity for B/V infection.
- These gene-based models offer a promising approach for rapid and accurate etiological diagnosis in pediatric infectious diseases.
Background:
Early aetiological diagnosis is critical for the management of febrile children with infectious illness, as it strongly influences the choice of appropriate medication and can affect a child's complications and outcome. New diagnostic strategies based on host genes have recently been developed and have achieved high accuracy and clinical practicability. In this study, through integrative bioinformatics analysis, we aimed to construct artificial neural network (ANN, multilayer perceptron) and random forest (RF) models based on host gene signatures to diagnose bacterial or viral (B/V) infection in febrile children.
Results:
Transcriptome data from the whole blood of children were collected from a public database. Of these, 384 febrile young children (definite bacterial: n = 135, definite viral: n = 249) were involved in the construction of the RF model. For the generalized RF model, 1,042 patients were included with various aetiological infections, such as Staphylococcus aureus, pathogenic Escherichia coli, Salmonella, Shigella, adenovirus, HHV6, enterovirus, rhinovirus, human rotavirus, human norovirus, and influenza A pneumonia. The overlap of 57 candidate genes between the 117 differentially expressed genes (DEGs) and the 264 module member genes was identified through DEGs analysis and weighted gene co-expression network analysis (WGCNA). Subsequently, L1 regularization algorithms and variable significance analysis (multilayer perceptron) were used to simplify and rank the predictive features, and LCN2 (100.0%), IFI27 (84.4%), SLPI (63.2%), IFIT2 (44.6%) and PI3 (44.5%) were identified as the top predictors. By utilizing the transformed value RefValue (i) of these five genes, the RF model achieved an AUC of 0.9917 in training and 0.9517 in testing for diagnosing B/V infection in children. The ANN model achieved an AUC of 0.9540 in testing. Furthermore, a generalized RF model involving 1,042 patients was developed to predict different aetiological types of samples, achieving an AUC of 0.9421 in training and 0.8968 in testing.
Conclusions:
A five-gene host signature (IFIT2, SLPI, IFI27, LCN2, and PI3) was identified and successfully used to construct an RF model that distinguishes B/V infection in febrile children, achieving 85.3% accuracy, 95.1% sensitivity, and 80.0% specificity, and to construct an ANN model that achieves 92.4% accuracy, 86.8% sensitivity, and 95% specificity.
Related Concept Videos
01:26Patterns of Fever
01:30Urinary Tract Infection III: Diagnostic Studies and Interprofessional Care
01:24Automated Microbial Diagnostics