Related Experiment Video
Updated: May 25, 2026

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Characterization of asthma exacerbations in primary care using cluster analysis
Hector Ortega1, David P Miller, Hao Li
1Respiratory & Immuno-Inflammation, Medicines Development Center, GlaxoSmithKline, Research Triangle Park, NC 27709-3398, USA. hector.g.ortega@gsk.com
Asthma exacerbation risk is linked to specific patient traits. Supervised cluster analysis identified distinct adult and pediatric groups, aiding in pinpointing individuals needing targeted asthma management strategies.
Area of Science:
- Pulmonology
- Clinical Research
- Data Science
Background:
- Patients with a history of asthma exacerbations face increased risk of future severe events.
- Characterizing asthma phenotypes is crucial for improving asthma management and reducing exacerbations.
Purpose of the Study:
- To identify distinctive patient characteristics associated with a history of asthma exacerbations.
- To utilize cluster analysis for improved asthma exacerbation risk stratification.
Main Methods:
- Employed supervised cluster analysis with recursive partitioning on cross-sectional survey data.
- Analyzed asthma control data from adult and pediatric primary care patients.
- Identified characteristics that maximized differences across patient subgroups.
Main Results:
- Seven adult clusters revealed predictors like specialist visits, work hours, and rescue medication use. Adult Cluster 7 showed a higher exacerbation rate (RR 2.88) linked to female sex, high BMI, comorbidities (sinus infections, GERD), and allergies.
- Six pediatric clusters identified predictors including specialist visits, missed school days, race/ethnicity, and age. Pediatric Cluster 6 had a higher exacerbation rate (RR 2.36) associated with severe disease, allergies, and lower asthma control.
- The study included 2205 adults and 2435 children and adolescents with asthma.
Conclusions:
- Supervised cluster analysis effectively identifies specific risk factors for asthma exacerbations.
- This approach enables grouping patients with unique characteristics to better identify those at higher risk.
- Findings support personalized asthma management strategies based on identified risk profiles.
Related Concept Videos
Asthma-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:
Asthma III: Clinical Manifestations
Asthma-IV: Diagnostic and Management
Clinical Assessment for Asthma:
This is the first step in diagnosing and managing asthma. It includes:
Asthma: 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.
Asthma-III: Symptoms and Complications
Classification of Asthma
Asthma I: Introduction
