Investigation of an Indoor Air Quality Sensor for Asthma Management in Children

Area of Science:

• Environmental Health
• Sensor Technology
• Asthma Management

Background:

• Indoor air quality significantly impacts health, with Americans spending 93% of their time indoors.
• Asthma affects millions of children, exacerbated by environmental triggers like smoking and cooking.
• Continuous environmental monitoring is crucial for effective asthma management.

Purpose of the Study:

• To develop a data-driven system for passively monitoring indoor air quality.
• To detect specific asthma-exacerbating activities: smoking and cooking.
• To correlate environmental data with asthma exacerbations for improved clinical insights.

Main Methods:

• Utilized the Foobot sensor for unobtrusive, continuous monitoring of indoor environments.
• Employed a data-driven approach to analyze sensor data for activity detection.
• Classified events including control (no activity), cooking, and smoking.

Main Results:

• Successfully detected high concentrations of particulate matter, volatile organic compounds, and carbon dioxide during target activities.
• Achieved a 1% error rate for smoking detection and an 11% error rate for cooking detection.
• Obtained an overall classification accuracy of 95.7% across all monitored events.

Conclusions:

• The developed system effectively identifies key indoor air quality triggers for asthma.
• This technology enables correlation between environmental factors and patient-reported asthma symptoms.
• Facilitates improved asthma management by providing clinicians with objective environmental data.