Decoding Physical and Cognitive Impacts of Particulate Matter Concentrations at Ultra-Fine Scales

Area of Science:

• Environmental Science
• Biomedical Engineering
• Physiology

Background:

• The human body possesses sophisticated neurophysiological responses to environmental stimuli.
• Biometric sensors can record these physiological responses in real-time.
• Understanding environment-physiology interactions is crucial for health research.

Purpose of the Study:

• To develop a method for holistically capturing and evaluating environment-physiology interactions.
• To demonstrate the feasibility of estimating environmental factors using only biometric data.
• To establish a foundation for future research on various environmental exposures.

Main Methods:

• Utilized a cyclist equipped with a biometric sensing suite during outdoor rides.
• Collected environmental data using a survey vehicle.
• Developed empirical machine learning models to correlate biometric data with environmental conditions.
• Focused on estimating particulate matter concentrations.

Main Results:

• Biometric variables accurately estimated particulate matter concentrations at ultra-fine spatial scales (r² = 0.91).
• Smaller particulate matter particles were estimated more accurately than larger ones.
• Machine learning models successfully inferred environmental conditions from biometric data alone.

Conclusions:

• Biometric data can serve as a proxy for environmental conditions, specifically particulate matter.
• This approach allows for disentangling the complex interactions between the environment and human physiology.
• The study paves the way for using the body's 'built-in' sensing for health and performance insights.