Related Experiment Video
Updated: Jul 18, 2025
A High-throughput Platform for the Screening of Salmonella spp./Shigella spp.
Published on: November 7, 2018
Identification of Pediatric Bacterial Gastroenteritis From Blood Counts and Interviews Based on Machine Learning
1Department of Pediatrics, Haibara General Hospital, Shizuoka, JPN.
Introduction:
Differentiating between bacterial and viral gastroenteritis is crucial in pediatric enteritis practice. Our objective was to use machine learning (ML) to identify acute gastroenteritis (AG) caused by bacteria based on blood cell counts and interview findings.
Methods:
ML was performed using a decision tree classifier based on data from previously published papers. We included 164 children between one and 108 months diagnosed with gastroenteritis, with 112 having bacterial AG and 52 having viral AG as subjects and controls. Feature selection was performed using least absolute shrinkage and selection operator (LASSO), and the classifier's performance was evaluated by five-fold cross-validation. Additionally, we presented a tree diagram of the decision tree classifier as a flowchart for practical applications.
Results:
The area under curve (AUC) was 0.80, indicating a moderate model. Three important features in this model were platelet-lymphocyte ratio, eosinophil count, and leukocyte count.
Conclusions:
In conclusion, this study demonstrates that bacterial AG can be estimated from blood cell counts with moderate accuracy. These findings may be valuable in narrowing down bacterial AG in children with gastrointestinal symptoms.
Insights
Machine learning models can help distinguish bacterial gastroenteritis from viral causes in children using blood cell counts. This approach offers moderate accuracy in identifying bacterial infections, aiding clinical decisions.
Area of Science:
- Pediatric Gastroenterology
- Medical Informatics
- Machine Learning in Medicine
Background:
- Distinguishing bacterial from viral gastroenteritis is critical in pediatric care.
- Machine learning (ML) offers a potential tool for identifying bacterial acute gastroenteritis (AG).
Purpose of the Study:
- To develop and evaluate an ML model for identifying bacterial AG in children.
- To utilize blood cell counts and interview data for diagnostic classification.
Main Methods:
- A decision tree classifier was employed, trained on data from published studies.
- 164 children (1-108 months) with gastroenteritis were analyzed (112 bacterial AG, 52 viral AG).
- Feature selection used LASSO, and performance was assessed via five-fold cross-validation.
Main Results:
- The ML model achieved an area under the curve (AUC) of 0.80, indicating moderate performance.
- Key predictive features included platelet-lymphocyte ratio, eosinophil count, and leukocyte count.
Conclusions:
- Bacterial AG can be estimated with moderate accuracy using blood cell counts via ML.
- These findings can assist in differentiating bacterial AG in children presenting with gastrointestinal symptoms.
More Related Videos
Related Concept Videos
01:28Methods of Classification and Identification
01:18Steps in Outbreak Investigation
01:30Serum Laboratory Studies, Stool Test, Breath Test