Related Experiment Video
Updated: Apr 23, 2026

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
Published on: July 22, 2025
Characterizing thunderstorm asthma emergency department presentations using natural language processing for improved
Sedigh Khademi1,2, Gerardo Luis Dimaguila1,2, Christopher Palmer1
1Health Informatics Group, Centre for Health Analytics, Melbourne Children's Campus, Melbourne, Australia.
Rapid detection of thunderstorm asthma is crucial. This study found distinct patterns in emergency department visits during these events, aiding public health preparedness.
Area of Science:
- Environmental Health
- Epidemiology
- Public Health Surveillance
Background:
- Thunderstorm asthma events pose significant public health risks, rapidly overwhelming emergency departments.
- Effective preparedness necessitates rapid detection and understanding of thunderstorm asthma presentation patterns.
Purpose of the Study:
- To identify distinctive demographic, temporal, and clinical patterns of thunderstorm asthma presentations in emergency departments.
- To enhance the real-time detection and surveillance of thunderstorm asthma incidence.
Main Methods:
- Analysis of triage notes from three thunderstorm asthma events (2022-2024) in Victoria, Australia, using the SynSurv surveillance system.
- Comparison of 687 thunderstorm-related presentations with 687 control presentations using natural language processing and manual review.
- Statistical comparison of demographic, symptom-onset, and comorbidity data via chi-square tests and temporal analysis.
Main Results:
- Thunderstorm asthma cases exhibited significantly higher acute symptom onset within 24 hours (63.0% vs. 47.2%).
- Presentations peaked 3-8 hours post-storm, returning to baseline within 24 hours.
- Affected individuals skewed towards young adults (21-40 years), with threefold higher rates of allergic comorbidities.
Conclusions:
- Distinct demographic, temporal, and allergic profiles characterize thunderstorm asthma presentations.
- These findings can inform the development of refined detection models for enhanced real-time surveillance and emergency preparedness.
- Improved surveillance can bolster public health responses to severe weather-related asthma events.
More Related Videos
Related Concept Videos
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-I: Introduction
Asthma I: Introduction
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: 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.

