Related Experiment Video
Updated: Jan 8, 2026
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Utilizing data mining to improve asthma control in children: a study on influential factors
Omid Mahmoudi Topkanlo1, Hamidreza Dezfoulian1, Mohammad Reza Fazlollahi2,3
1Department of Industrial Engineering, Bu-Ali Sina University, Hamedan, Iran.
Insights
Feature selection improved asthma control prediction in children by identifying key factors like smoke exposure and allergic rhinitis. This approach enhances model accuracy and clinical interpretability for better asthma management.
Area of Science:
- Pediatric Allergy and Immunology
- Computational Health Informatics
- Machine Learning in Medicine
Background:
- Asthma control in children is crucial for long-term health outcomes.
- Identifying predictive features for asthma control can optimize clinical decision-making.
- Current models may benefit from refined feature selection for improved accuracy.
Purpose of the Study:
- To pinpoint the most significant indicators of asthma control in pediatric patients.
- To evaluate if employing feature selection techniques enhances the performance of predictive models for childhood asthma control.
Main Methods:
- Analysis of 890 pediatric asthma patient records (2013-2018).
- Comparison of 13 feature selection (FS) methods against an 83-feature baseline model using XGBoost.
- Performance evaluation via cross-validation, assessing metrics like Recall, F1, ROC-AUC, and PR-AUC.
Main Results:
- Models utilizing feature-selected subsets demonstrated improved performance across key metrics compared to the baseline.
- Specifically, Recall increased to 90.32% and F1 score to 82.84% with SVM-selected features.
- Consistently selected features included modifiable triggers (smoke, climate) and medical history (allergic rhinitis, eczema).
Conclusions:
- Feature selection enhances predictive model performance for pediatric asthma control, yielding more interpretable results.
- Identified key features highlight the importance of modifiable triggers and allergic history.
- Findings suggest potential for improved clinical management through targeted interventions, though external validation is recommended.
Objective:
To identify the most influential features of asthma control in children and to assess whether feature selection improves model performance.
Methods:
Records of 890 patients (<18 years) from the Immunology, Asthma, and Allergy Research Institute, Children's Medical Center, Tehran (2013-2018) were analyzed. The binary outcome was asthma control (controlled vs uncontrolled). Eighty-three candidate features (demographics, comorbidities, history, triggers) were considered. Thirteen FS methods (filters, wrappers, embedded methods, plus PCA) were compared. For each method, the top 20 features were used to train an XGBoost classifier; the full 83-feature model served as the baseline. Performance was estimated with repeated holdout cross-validation (10 repeats, 90/10 splits) and summarized using Accuracy, Precision, Recall, F1, ROC-AUC, and PR-AUC.
Results:
Relative to the all-features baseline model, the model trained on the SVM-selected subset showed consistent gains in key metrics: Recall increased from 86.12% to 90.32%, F1 from 77.37% to 82.84%, PR-AUC from 77.37% to 82.84%, and ROC-AUC from 52.18% to 64.21%. Features with high consensus across methods were primarily related to modifiable triggers (e.g. smoke exposure and climate-related factors) and medical history (e.g. allergic rhinitis and eczema).
Conclusions:
Applying feature selection generally improved performance across multiple metrics, yielding compact, stable subsets that highlight modifiable factors - particularly triggers and allergic history - and support clinical interpretability. These findings are associative; therefore, external validation is recommended.
Related Concept Videos
01:30Asthma-IV: Diagnostic and Management
Clinical Assessment for Asthma:
This is the first step in diagnosing and managing asthma. It includes:
01:20Asthma: Pathogenesis and Management
Asthma is classified as allergic and non-allergic. Allergens such as dust mites, pollen, and pet dander trigger allergic asthma, while factors like cold air, intense emotions, or exercise can induce non-allergic asthma.
01:29Asthma-I: Introduction
01:30Asthma-IV: Nursing Management
First, in...
01:26Asthma-II: Pathophysiology and Classification
Additionally, environmental and genetic factors play crucial roles in determining an individual's susceptibility to asthma and the severity of their condition.
Critical processes in asthma pathophysiology include:
01:25Antiasthma Drugs: Mast Cell Stabilizers and Anti-IgE Drugs
Mast cell stabilizers, such as cromolyn (also known as sodium cromoglycate) and nedocromil (Tilade), are effective drugs in asthma management. These stabilizers hinder histamine release by skillfully obstructing the activation of mast cells and other cellular entities. Notably, they navigate this task without...